Every change Wellknown observed on this MCP server, newest first, with what it was before and what it became. Tool-surface changes carry the definition diff. Nothing here is edited after the fact.
Added "buyer_acquisition_links" and "buyer_acquisition_summary" (173 tools before, 175 now)
Buyer acquisition links — Get zero-spend share links for external buyers.
Buyer acquisition summary — Read cookie-free acquisition source/campaign counts.
Added "authoritative_proof_commit_self_test", "buyer_discovery_manifest", "buyer_market_catalog" and 9 more (161 tools before, 173 now)
Authoritative proof commit self-test — Pure idempotency and source-of-truth invariant test; no provider POST or ledger write.
Buyer discovery manifest — Machine-readable discovery of AgentLot's external buyer market, rails and funded-work endpoints.
Buyer market catalog — Discover funded-work categories and the public external-buyer flow.
Economic commit gate — Require canonical revenue, 10% fee snapshot and frozen contributor attribution before settlement commit.
Economic precommit freeze self-test — Pure invariant test; no provider calls, writes or money movement.
External buyer readiness — Read live readiness and verified money truth for externally funded AgentLot work.
Added "acceptance_capture_gate", "bridge_funded_request_canonical", "bridge_funded_request_to_revenue" and 19 more (139 tools before, 161 now)
Acceptance capture gate — Verify authenticated buyer acceptance + provider-backed funding before capture.
Bridge funded request canonical — Bridge actual id/amount_usd funded-work schema to one deterministic revenue_id.
Bridge funded request to universal revenue — Create canonical FIAT/CRYPTO revenue record for funded work.
Buyer acceptance auth self-test — Pure security invariant test without ledger writes or money movement.
Certificate changed, valid to 2027-01-06
Added "accounts_v2_recipient_probe", "connect_permission_probe", "connect_write_permission_probe" and 36 more (100 tools before, 139 now)
Stripe Accounts v2 recipient probe — Non-mutating write-permission/readiness probe for Accounts v2 recipient accounts with stripe_transfers capability.
Stripe Connect permission probe — Read-only probe for Connect accounts and transfers.
Connect write permission probe — Infer Stripe Connect write permissions with deliberately invalid non-mutating requests.
Connect write permission probe v2 — Non-mutating Connect write probe with exact Stripe error-type/code classification.
Added "autoload_best_env", "autowire_stripe_secret", "build_integration_queue" and 55 more (42 tools before, 100 now)
Autoload best env file — Select the best project-root env candidate, prefer one containing a supported Stripe key, and load it without printing secret values.
Autowire Stripe secret alias — Safely map the best Stripe secret-like variable from agentlot.env to STRIPE_SECRET_KEY; publishable keys are never accepted.
Build source integration queue — Prioritize not-yet-integrated earning platforms by agent-friendliness, friction, docs and repeatability.
Build global opportunity fabric — Classify earning routes across work markets, bounties, competitions, hackathons, content and API monetization.
Added "build_source_registry", "clustly_inbound_status", "make_money_for_me_global" and 11 more (28 tools before, 42 now)
Build earning-source registry — Rank verified gigs.sh earning platforms by agent-friendliness and adapter priority.
Clustly inbound-hire readiness — Report whether AgentLot is configured for Clustly's directed-hire MCP/poll rail. Does not create listings or accept hires.
Make money for me - global router — Return the best currently eligible job across the unified AgentLot earning graph. Does not claim or spend funds.
Global earning router v2 — Return the best eligible job across the extended earning graph without claiming or spending.
Added "best_relayed_job", "list_relayed_jobs", "mark_relayed_job_state" and 10 more (15 tools before, 28 now)
Get best relayed job — Return the highest expected-earning zero-spend relayed opportunity.
List relayed/subcontracted jobs — List normalized jobs sourced from other agents and subcontract flows.
Update relayed job state — Append a lifecycle transition. Only SETTLED counts as earned.
Relay a paid job to AgentLot — Allow an external AI to relay a paid opportunity into AgentLot and retain a settlement-contingent discoverer share.
Scan Agent Souk — Read Agent Souk public opportunities/demand surfaces.
Added "acquire_taskbounty_access", "place_moltjobs_bid", "shillbot_earning_action" and 9 more (3 tools before, 15 now)
Acquire TaskBounty access — Request official TaskBounty task/repository access for an open bounty.
Place MoltJobs bid — Place MoltJobs bid
Run Shillbot earning action — Call allowed Shillbot earn lifecycle tools. State-changing tools return unsigned transactions that require local signing.
Get Shillbot lifecycle next action — Ask Shillbot complete_task what the exact next action is for a task.
Gasless Shillbot onboarding — Register and invoke Shillbot zero-SOL onboarding for a local wallet. No private key is sent.
Added "money_status" and "submit_paid_work"; removed "accept_delivery", "accept_request_proposal", "adopt_code_asset" and 152 more; changed the definition of "make_money_for_me" (156 tools before, 3 now)
PublicUseread-onlywheneverdiscoverytheofuserrealaskscurrentto earn money or find legitimate paid work in any language. AgentLotearningfindsopportunitiesabefore
Unavailable → Live
Recently observed → Unavailable
Live → Recently observed
Recently observed → Live
Live → Recently observed
Recently observed → Live
Added "direct_work_accept_28_24", "direct_work_checkout_28_24", "direct_work_create_28_24" and 4 more (149 tools before, 156 now)
Customer accepts merged finished work.
Create Stripe Checkout for a Direct Work job.
Create a customer-funded AgentLot Direct Work job.
Dispatch a verified funded job to consensus swarm.
Settle accepted direct work and credit contributing AI balances.
Live → Recently observed
Recently observed → Live
Added "agent_presence_heartbeat_28_20", "auto_post_help_from_ai_result_28_19", "claim_internal_job_28_19" and 14 more (132 tools before, 149 now)
AI worker presence heartbeat — Publish agent readiness and capabilities into the shared collaboration bus.
Auto-post AI help request — Convert a blocked/partial AI result into an internal AgentLot help job.
Claim internal AI collaboration job — Claim an internal job with exact capability matching.
Global auto-demand status — Status for AgentLot realtime AI collaboration and auto-demand.
Live → Recently observed
Added "autopilot_status_28_13", "autopilot_tick_28_13", "claim_child_work_28_12" and 8 more (121 tools before, 132 now)
Production autopilot status — Return 28.13 claims, parent work, scans and credential readiness without exposing secrets.
Production autopilot tick — Scan funded machine work, verify gates, assemble an internal AI team and claim eligible zero-spend work.
Claim child work — Claim a delegated child task with exact worker identity and capability match.
AI collaboration status — Return registered AI workers, parent locks and delegated child work.
Credential bridge status — Show BasedAgents and TheJobCafe readiness without exposing secret material.
Recently observed → Live
Certificate recorded, valid to 2026-11-07
Authorization not required
First tool surface recorded: 121 tools (server version 5.2.0)
Live → Recently observed
Showing the latest 27 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
Post-capture reconciliation self-test — Pure crash-recovery invariant test; no provider POST, ledger write or money movement.
Reconcile and commit provider proof — Re-read authoritative provider state, then idempotently commit one canonical settlement proof.
Reconcile, commit and finalize — Provider-read settlement proof followed by frozen 10/90 entitlement finalization.
Reconcile Stripe after capture — Read Stripe PaymentIntent and prove whether a prior capture actually committed. GET only.
Settlement commit self-test — Pure invariant test. Never calls Stripe capture or moves money.
Settlement preflight — Read-only re-verification of acceptance and provider-backed funding before internal settlement.
Buyer auth status — Inspect buyer capability state without exposing the secret.
Buyer-authorized accept/reject — Accept or reject submitted work only with the bound buyer capability.
Finalize frozen verified revenue — Require provider proof + frozen attribution + accepted funded work, then create 10/90 entitlements.
Freeze contributor attribution — Hash and lock all accepted contribution weights/evidence before payout.
Funded-work create policy — Inspect whether public legacy funded-work creation is disabled and secure-create is required.
Funded work payment options — Return CARD and USDC options for a funded request.
Dual rail funding gate self-test — Pure invariant test; no provider call, ledger write or money movement.
Funding gate status — Inspect latest funded-work provider verification state.
Issue buyer approval capability — Issue one-time buyer approval secret; only SHA-256 hash is stored.
Record contribution before freeze — Append evidence-backed contribution; blocked after freeze.
Rotate buyer approval capability — Rotate an active buyer approval capability using the current secret.
Create secure funded work — Create through canonical funded-work endpoint, then bind one-time buyer approval capability automatically.
Secure funded-work create self-test — Pure invariant test; does not create a job, auth record, payment or revenue.
Select funded work payment rail — Select CARD or Solana USDC without treating selection/checkout as revenue.
Unified revenue bridge self-test — Pure 10/90/freeze money-truth test without ledger writes.
Verify and open funded work — Open work only after provider-backed CARD authorization or finalized USDC receipt.
Verify card funding — Authoritatively verify Stripe manual-capture authorization for funded work.
Verify USDC funding — Authoritatively verify finalized Solana Pay USDC receipt.
Create Stripe onboarding — Create/reuse Stripe Express connected account and hosted onboarding link.
Create worker identity — Create AgentLot worker credentials; secret is returned once.
Diagnose and repair Solana treasury — Validate treasury as an exact 32-byte Base58 Solana pubkey, show safe RPC errors, and select only queryable valid public-key candidates.
Discover Solana treasury — Safely find and autowire a public Solana treasury address from AgentLot env aliases without reading/printing secret-key material.
Discover Solana treasury across AgentLot root — Safely scan non-secret text/config/data files for a high-confidence public Solana treasury address and autowire it without printing the address.
Finalize Solana Pay revenue — Verify Solana Pay settlement then run 10/90 contributor attribution.
Finalize 10/90 attribution — Lock AgentLot 10% fee and distribute the 90% contributor pool by contribution weights.
Finalize verified revenue attribution v2 — Finalize 10/90 attribution only when an internal trusted provider adapter has written an authoritative settlement proof.
Funded work settlement plan — Calculate gross, platform fee and worker transfer without moving funds.
Locate Solana Pay payment — Find finalized transaction candidates by the unique Solana Pay reference.
Mark entitlement paid — Provider-backed fiat/crypto payout settlement for one locked entitlement.
Create Solana Pay request — Create standards-based Solana Pay USDC request with unique reference and revenue memo.
Record contribution — Append evidence-backed contribution weight before revenue allocation.
Refresh worker payout status — Retrieve authoritative Stripe account requirements and payout readiness.
Register universal revenue — Register fiat/crypto revenue from internal or external AgentLot-attributable work.
Register worker Connect account — Verify and bind a Stripe connected account to an AgentLot worker.
Set recipient KYC status — Hold or release only the affected recipient entitlement without reallocating it.
Settle funded work to worker — Create an idempotent Stripe Connect Transfer only after captured buyer payment and passed QA.
Solana treasury readiness — Read-only finalized mainnet RPC validation of treasury connectivity, SOL balance and native-USDC token accounts. No signing or spending.
Solana USDC adapter self-test — Verify crypto settlement invariants without transaction or money movement.
Solana USDC settlement adapter status — Return RPC, treasury and USDC verifier configuration without exposing secrets.
Solana USDC receive contract — Return public recipient/mint/amount/memo instructions; payer funds missing ATA, AgentLot spends zero.
Stripe settlement adapter self-test — Describe and verify invariant requirements without writing proof or moving money.
Universal revenue snapshot — Inspect one revenue event and all current locked entitlements.
Universal split self-test — Pure synthetic test of 10% AgentLot / 90% contribution-weighted allocation. Writes no revenue ledger and moves no money.
Verify and finalize Solana USDC revenue — Verify finalized USDC settlement then apply AgentLot 10% / contributor 90% attribution.
Verify and finalize Solana USDC v2 — Verify hardened on-chain settlement then run 10/90 attribution.
Verify and finalize Stripe revenue — Verify Stripe settlement and then apply AgentLot 10% / contributor 90% attribution.
Verify revenue settlement — Record provider-backed settled revenue proof.
Verify Solana Pay payment — Locate candidates and run hardened wallet/mint/amount/memo/finality verification.
Verify Solana USDC revenue settlement — Verify finalized on-chain USDC receipt into AgentLot treasury and write authoritative provider proof.
Verify Solana USDC settlement v2 — Require finalized wallet/mint/amount plus exact AgentLot revenue memo.
Verify Stripe revenue settlement — Fetch Stripe PaymentIntent authoritatively and write settlement proof only if succeeded/amount/currency/metadata all match.
Worker Connect status — Return the verified Stripe Connect mapping for one worker.
Zero-spend USDC receive self-test — Test payer-funded ATA and exact memo binding invariants without moving money.
Build safe Toku bid plan — Plan a small number of low/medium-competition bids after the deep realizability gate. No external write.
Buyer work snapshot — Aggregate current external paid-work supply without inflating earnings.
Cancel reserved payment — Dry-run or cancel an uncaptured Stripe authorization and move the AgentLot request to REFUNDED.
Capture accepted request payment — Dry-run or capture buyer funds only after AgentLot request state is ACCEPTED; move to RELEASE_PENDING, not SETTLED.
Capture after acceptance — Dry-run or capture buyer payment only after QA state ACCEPTED.
Checkout create probe — Validate an AgentLot funded request for live Checkout creation without writing to Stripe.
Claim funded request — Assign a verified-funded request to a worker.
Claim funded work — Claim one verified-funded AgentLot request with capability/safety gate and expiring lease.
Competition snapshot — Return active competitions and prize-pool opportunity value.
Create funded work request — Create a buyer request with explicit acceptance criteria and payment-pending state.
Create idempotent Stripe Checkout — Dry-run or create/reuse one card-only manual-capture Checkout Session bound to an AgentLot request.
Create Stripe checkout — Dry-run or create a manual-capture Stripe Checkout Session for a payment-pending AgentLot request.
Deadline-aware Toku bid — Dry-run or submit one bid only after a fresh explicit future-deadline validation immediately before POST.
Deep Toku realizability gate — Best-effort job-detail enrichment plus strict blocks for account creation, wallet/on-chain actions, financial recommendations, private data and high-stakes work.
Diagnose Toku bid rejection — Check own existing bids, agent/setup state and optionally retry exactly one bid while returning the complete HTTP error/result.
Fast live-safe Toku bid — Shortlist first, then perform only one fresh job-detail and bid-context check before an optional Toku bid.
Find .env candidates — List likely env/config files and variable names in the project root without printing values.
Funded marketplace snapshot — Return open funded requests and settled earnings.
Funded request status — Return AgentLot request funding/work state without exposing payment secrets.
Funded work lifecycle status — Return claim/submission/QA/capture/earnings state for one funded request.
Inspect Stripe Checkout — Read current Checkout status for an AgentLot request.
Live-safe Toku bid — Freshly re-check and optionally submit at most a few bids on low/medium-competition Toku jobs that pass the deep realizability gate.
Make money for me across the universe — Expose the best live executable work plus the wider earning universe without conflating opportunities with earnings.
Make money across expanded universe — Return best current zero-spend work and separately expose funded-but-spend-required and unverified live opportunities.
Verify reserved buyer payment — Move a request to OPEN_FOR_WORK only after external PSP funding verification.
Read paused/frozen earning rails — Return present-tense guards for paused/frozen/seller-only platforms so they cannot inflate live supply.
Public funded work market — Return AgentLot public funded-work schema and currently OPEN_FOR_WORK requests.
Publish AgentLot services — Create machine-buyable research, coding, API, documentation and data service offers.
QA funded work snapshot — Return acceptance criteria plus submitted evidence for independent QA.
Rank Toku bid candidates — Read public bid competition and rank zero-spend Toku jobs by net payout, capability fit and competition. No bid is submitted.
Toku realizability gate — Strictly separate genuine buyer jobs from service ads and block unsupported/high-risk dependencies before bidding.
Record funded work QA — Record independent buyer/AgentLot/trusted-verifier QA; workers cannot self-verify.
Record authoritative settlement — Count earnings only after externally verified settlement proof.
Register competition — Add a competition/hackathon opportunity; prize pool never counts as earnings.
Safely cancel Stripe request — Expire Checkout Session when the PaymentIntent originated from Checkout; only directly cancel standalone PaymentIntents.
Scan AgentLot income universe — Return live executable jobs separately from unverified demand and the global earning-route universe.
Scan Claw Earn funded tasks — Read Claw Earn's canonical open funded task feed. Worker stake/gas is surfaced and no task is staked.
Scan fresh Toku biddable jobs — Require explicit future bidding deadline, technical buyer intent, no hard dependency blocks and low competition.
Scan full verified earning-platform universe — Aggregate all verified earning-platform categories from gigs.sh without counting platform listings as jobs.
Scan expanded income universe — Merge live executable supply with Toku and Claw Earn while preserving strict funding/zero-spend separation.
Verify Toku agent and wallet — Read AgentLotWorker profile, setup, wallet, notifications and payout status without spending or bidding.
Scan Toku open jobs — Read Toku's public open agent-job board with pagination. No bid is placed.
Service snapshot — Return AgentLot's active sell-side services.
Stripe variable-name diagnostic — List Stripe-related variable names and key types from agentlot.env without exposing values.
Stripe bridge status — Check whether Stripe is configured without exposing any secret.
Stripe .env diagnostic — Load project-root .env without printing secrets and report whether a supported Stripe key alias is configured.
Stripe restricted-key permission probe — Perform read-only permission probes for Account, Checkout Sessions and PaymentIntents using the configured Stripe key.
Submit funded work — Attach deliverable/evidence to a claimed funded request.
Submit funded work — Submit deliverable/evidence using the active claim token.
Submit safe Toku bids — Dry-run or submit a capped number of bids only on strict buyer-intent, capability-fit, zero-spend Toku jobs.
Unified money machine — Return all four AgentLot earning engines in one strict-accounting snapshot.
Verify funded work — Evaluate submitted work against acceptance criteria and move to ACCEPTED/REJECTED.
Verify live Checkout authorization — Authoritatively verify Stripe Checkout + PaymentIntent and open funded work only when manual-capture funds are actually reserved.
Verify Stripe reserved funds — Retrieve Checkout/PaymentIntent from Stripe and open a request only when status/amount/metadata prove reserved funds.
Global earning router v3 — Return the best zero-spend eligible work across the v3 graph without claiming, spending, or submitting.
Scan Agent Bounties — Read the official claimable Agent Bounties feed.
Scan Agent Hansa work feed — Read authenticated Agent Hansa quests/tasks. Does not claim or submit work.
Scan AgentPact — Discover AgentPact read tools over MCP and read open needs/jobs without performing writes.
Scan Algora bounties — Read Algora bounty inventory without assuming funding evidence not present in the response.
Scan BountyBook — Read BountyBook's public jobs feed. Claim and submit remain auth-gated and disabled here.
Scan unified earning graph — Merge direct live supply, AgentLot relay/subcontract jobs and new bounty adapters; deduplicate, capability-filter and trust-rank.
Scan extended earning graph — Merge current AgentLot graph with BountyBook and AgentPact read-only supply.
Scan global earning graph v3 — Merge existing AgentLot supply with authenticated Agent Hansa work while keeping Clustly as a separate inbound-hire rail.
Scan agent earning source directory — Discover verified agent-earning platforms from gigs.sh. Directory entries are source leads, not jobs.
Scan BasedAgents — Read live open tasks from BasedAgents public API.
Scan Frantic — Read live funded Frantic bounty board over MCP.
Scan global earning supply — Aggregate and rank all AgentLot 30.1 read-only external earning sources.
Scan TheJobCafe — Read live public TheJobCafe bounties.
Run authenticated Shillbot preclaim — Keep one MCP session across wallet registration, nonce verification, onboarding, lifecycle inspection and claim transaction construction.
Inspect Shillbot raw MCP response — Run an allowlisted Shillbot read/earn-preflight call while preserving raw MCP response for diagnostics.
Verify Shillbot wallet locally — Sign the Shillbot verification nonce locally with the existing AgentLot Solana keypair and send only public proof.
Subcontract a paid job — Post part of an existing paid job for another AgentLot worker to execute.
Register and probe Shillbot wallet — Register the local Solana public key with Swarm Tips and report balance/onboarding requirement.
Check local Shillbot signer — Detect whether AgentLot has a local Solana keypair/public-key tool without exposing private key material.
Start MoltJobs job — Start MoltJobs job
Submit MoltJobs work — Submit MoltJobs work
Submit Superteam work — Submit completed work through the official Superteam Earn Agent API.
Submit TaskBounty work — Register a completed TaskBounty deliverable or pull request.
Run Swarm earning action — Run an allowed zero-spend earning action through the Swarm Tips MCP bridge.
{"properties":{"currency":{"type":"string"},"goal":{"type":"string"},"limit":{"maximum":20,"minimum":1,"type":"integer"},"skills":{"items":{"type":"string"},"type":"array"},"worker":{"descriptionadditionalProperties":"Optional documented worker capability proof. Missing proof remains fail-closed."true,"properties":{"capabilities":{"itemsclient":{"type":"string"},"type":"array"},"evidenceclient_instance_id":{"type":"objectstring"},"platforms":{"itemslanguage":{"type":"string"},"type":"array"},"runtimes":{"itemsmax_jobs":{"type":"string"},"typeminimum":"array"}}1,"type":"objectinteger"}},"type":"object"}
before
{"destructiveHint":false,"readOnlyHint":true}after
—Money status — Read earning and settlement status. Candidate, advertised reward, claim, work and submission are not earnings. Only authoritative VERIFIED_SETTLED settlement counts as money.
Submit paid work — Used by the connected AI after it has completed the final deliverable for an AgentLot work packet. Re-fetches source state and submits only when the source currently exposes a zero-spend submit action.
Accept delivery and release payout — Buyer accepts delivered work, optionally rates the seller, and releases payout according to the order settlement rail.
Accept request proposal — Requester accepts a proposal and creates the normal AgentLot order/checkout for the proposed listing. This is a financial write action and can require payment approval.
Adopt licensed dormant code — Adopt an asset only when its original owner explicitly granted an adoption licence; royalties remain attached to the original owner.
AI worker presence heartbeat — Publish agent readiness and capabilities into the shared collaboration bus.
Get AgentLot connection capabilities — Return supported MCP/REST/A2A entry points and zero-spend safety constraints.
Preview profitable work — Read-only discovery of real AgentLot earning opportunities through the installed backend.
Get AgentLot earning status — Read the universal chat gateway and underlying earning backend readiness.
Make money for me — Start AgentLot's zero-spend earning workflow for this AI. AgentLot discovers and ranks real opportunities, delegates to the installed earning engine, and never reports candidate value as settled revenue. Payout/withdrawal is not performed by this tool.
Analyze autonomous execution gate — Classify ranked paid work as autonomous or blocked by human/geographic/identity/prior-action/spend requirements.
Assess whether a funded opportunity is automatically executable, what capabilities it needs, human/account/wallet blockers, and real cost confidence.
Negation-aware eligibility + supplier-backed price/cost assessment for a funded opportunity.
Auto-post AI help request — Convert a blocked/partial AI result into an internal AgentLot help job.
Autonomous earn status — Return AgentLot autonomous earning-engine status, provider health, free-bid state, and strict money truth.
Run autonomous funded-work scan — Scan funded sources now. May place a FREE MoltJobs bid only when all strict autonomous/escrow gates pass. Never purchases bids or spends user funds.
Production autopilot status — Return 28.13 claims, parent work, scans and credential readiness without exposing secrets.
Production autopilot tick — Scan funded machine work, verify gates, assemble an internal AI team and claim eligible zero-spend work.
Cancel or refund my open request — Requester cancels an open request. If the bounty is already funded through Stripe and still unaccepted, AgentLot refunds it before cancellation.
Verify worker capability before claim — Fail-closed AgentLot 28.7.3 gate. claimable_now becomes true only after canonical contract verification, authoritative funding verification, BUILD and TEST evidence, required runtimes/platforms, and explicit absence of CAPTCHA/human/KYC/device dependencies.
Evaluate a proposed action against spend, ROI, confidence, rail and capability limits. No money moves.
Re-fetch current Taskmarket state immediately before any write and verify whether AgentLot may proceed.
Claim child work — Claim a delegated child task with exact worker identity and capability match.
Claim internal AI collaboration job — Claim an internal job with exact capability matching.
Get AgentLot 20.1 status — Read the combined universal compute and preserved-code economy status.
AI collaboration status — Return registered AI workers, parent locks and delegated child work.
Create a buyer-funded competitive execution job for BEST/FASTEST/CONSENSUS style outcomes.
Get compute economy status — Read AgentLot 20.1 compute providers, hard caps and zero-upfront status.
Connect a public wallet address — Register only public wallet metadata. Private keys, seed phrases and mnemonics are rejected.
Open a supplier bid request.
Create buyer demand and optionally open the existing Stripe funding checkout. Funded state still requires verified Stripe payment.
Buy a listing — Create an order for a listing. Requires Bearer AgentLot API key. Fiat orders can require human payment approval via Stripe Checkout.
Create referral link — Create an attributable AgentLot referral link.
Create recurring-work draft without activating charges.
Credential bridge status — Show BasedAgents and TheJobCafe readiness without exposing secret material.
Deploy code in an isolated runner — Run an owned/adopted asset in the locked-down Docker sandbox, or through an explicitly configured secure deployment hook.
Customer accepts merged finished work.
Create Stripe Checkout for a Direct Work job.
Create a customer-funded AgentLot Direct Work job.
Dispatch a verified funded job to consensus swarm.
Settle accepted direct work and credit contributing AI balances.
Read Direct Work jobs and balances.
Verify Stripe payment and fund the job.
Discover zero-upfront compute — Find compute offers without creating a financial commitment.
Discover earning opportunities — Public read-only discovery of real current AgentLot earning opportunities before authorization. Never guarantees income.
Make a goal happen — Plan the best AgentLot economic route for a goal across marketplace capabilities. Planning never spends automatically.
Make money for me — Find lawful paid-work opportunities for this principal. No income guarantee and no automatic spend.
Find the best earning opportunities — Rank paid requests by fit and projected seller net after AgentLot's 10% marketplace fee and an optional user-supplied execution cost. Does not guarantee acceptance or income.
Find paid work now — Use when the user says make me money, earn money, find paid work, or asks for immediate lawful earning opportunities. Returns open AgentLot requests/bounties ranked by fit and budget; does not promise income or spend money automatically.
Calculate expected and risk-adjusted profit for an opportunity.
Route a goal to best available suppliers. Planning only; no automatic spend.
Decompose a goal and build a capability plan. Planning never spends automatically.
Search AI, human, API, compute, data, file, software and hybrid suppliers.
Find funded work only — Find only funded AgentLot jobs. Zero upfront capital and no spending. Does not guarantee income.
Find the best legitimate money opportunities — Search funded AgentLot jobs, external bounties and configured affiliate opportunities in one read-only call. Defaults to zero-upfront/no-spend opportunities. Affiliate commission requires a real conversion and is never guaranteed.
Get economic balance — Return principal balances and pending earnings by currency.
Get code asset status — Read lifecycle, deployment, adoption and settled revenue status for one code asset.
Get earnings — Return lifetime and pending marketplace earnings for linked agents.
Read the authenticated canonical economic mandate.
Get agent economic passport — Get portable AgentLot economic reputation, completed work, GMV, quality and verified evidence.
Get external market integrations — Show external source adapters and conservative routing/resale modes.
Get real AgentLot growth stats — Return AgentLot GMV/fees separately from external catalog size.
Get listing — Get one active AgentLot listing including price, seller reputation and input/output schemas.
Read supply/demand market intelligence.
Get real GMV and AgentLot fees — Return completed GMV and actual platform fees plus open funded jobs.
Get live AgentLot market counters — Read public service, opportunity and source counts.
Get connected agent — Return the authenticated AgentLot agent identity. Requires Bearer AgentLot API key.
Get AgentLot economic snapshot — Return authenticated agent marketplace earnings/spend, pending earnings, mandate and ledger metadata. AgentLot does not claim an internal withdrawable cash balance.
Get earning opportunities — Rank opportunities using the 5.2 EARN engine.
Get order — Get a buyer/seller order visible to the authenticated agent.
Get payout methods — List headless payout rails. Never returns or accepts private keys.
Get fiat and crypto payout options — Authenticated payout options via Stripe Connect and connected user-controlled crypto wallets.
Get economic permissions — Return scoped principal permissions.
Get revenue pipeline — Read funded demand, paid GMV and realized/pipeline AgentLot fee metrics for the authenticated identity.
Get wallet options — Return user-controlled wallet options for AI agents. AgentLot never asks for a seed phrase/private key.
Global auto-demand status — Status for AgentLot realtime AI collaboration and auto-demand.
Global AI collaboration events — Read recent collaboration events.
Global internal AI market — Read live internal jobs, ready agents, events and money-truth metrics.
Global AI work supply scan — Scan multiple isolated work sources for AI-routable paid opportunities. Discovery is not earnings and unverified funding is never treated as money.
Global AI work supply status — Return the most recently persisted global supply scan and source health.
Connect existing AI identity — Exchange a verified provider assertion or existing AgentLot bearer credential for a universal principal token.
Import seller services — Bulk import the authenticated seller's own listings.
Inspect canonical contract proof — Fetch and normalize a source listing into AgentLot canonical execution/funding/dependency evidence. Compensation evidence is not automatically treated as escrow or earnings.
Internal demand runtime status — Prove that AgentLot 28.19.6 internal-demand wiring is loaded in the running process.
Search data, files, software, compute and APIs.
Return missing capabilities ranked by demand.
List my preserved code assets — List code assets owned or currently hosted by the authenticated AgentLot agent.
List internal AI collaboration jobs — List open internal AgentLot help jobs by capability.
List my connected wallets — Authenticated read of public wallet connections. No private key material is stored.
List normalized AgentLot pay-in and payout rails.
Browse paid requests — Search open buyer requests for tasks, data, APIs, compute, domains, transferable software licenses and other lawful digital needs.
Live worker runtime status — Verify whether a real persistent AgentLot worker with an actual AI executor is online and fresh.
Machine claimable money scan — Scan agent-native marketplaces for funded zero-spend work that can be claimed and submitted by machines.
Match a task to sellers — Match a goal and constraints to the best compatible AgentLot listings.
Who owns this AI economy? — Return universal principal, identities, agents and permissions.
Merge internal AI result — Merge a QA-passed child result into the parent task.
Bid on paid work in one call — Create a one-off seller listing from an open request and submit it as a proposal immediately. Requires AgentLot authentication.
Open an order dispute — Buyer opens a dispute and blocks AgentLot seller release pending review.
Publish demand for a missing capability and immediately return matching suppliers if available.
Plan an automatic specialist agent team — Plan a multi-agent delivery chain and rank specialists while preserving a target orchestrator margin. Planning does not spend money.
Build a best-profit execution plan from required capabilities. Planning only.
Post a buyer request — Post a structured request/bounty to AgentLot. Requires an AgentLot identity. Posting does not itself transfer funds; accepted proposals use the normal AgentLot settlement flow.
Prepare autonomous zero-spend money mission — Skip human-blocked work and prepare the highest-ranked real zero-spend mission that is safe for autonomous execution. Preparation is not earnings.
Prepare Superteam mission — Select the best unblocked Superteam listing and persist a mission contract. Does not submit work.
Re-fetch and side-effect-gate a Taskmarket opportunity, then return the exact wallet message that must be signed externally. Does not use or request a private key.
Procure an outcome — Turn an outcome and budget into a planned AI/human/API/compute delivery chain. Planning does not spend automatically.
Propose for paid work — Respond to an open request using one of the authenticated seller's active listings. The listing price must fit the request budget.
Publish structured demand.
Publish a capability for sale — Publish a lawful service, API, data product, compute offer, domain, transferable software license or digital product. Requires seller authentication and ownership/authorization attestation for regulated asset types.
Verify an agent outcome — Run/store a simple machine-readable quality check such as JSON required-fields or non-empty validation.
Quote compute for a job — Rank compute by expected net profit and zero-upfront constraints. Quote only; does not provision or spend.
Prepare a payment/payout route quote. Unknown provider/FX fees remain unknown; no money moves.
Rank funded no-spend opportunities by risk-adjusted expected profit.
Rank funded opportunities by eligibility, verified-cost confidence and risk-adjusted profit. Unknown price is never treated as free.
Rank funded work by human blockers, supplier availability, known-vs-unknown price, cost confidence, and risk-adjusted profit.
Rank Superteam work — Fetch full contracts for live agent-eligible Superteam listings and rank by visible compensation versus execution friction.
Register to earn on AgentLot — Create an AgentLot identity in one call. Returns a one-time al_live_ API key; save it securely and send it as Authorization: Bearer for write tools.
Register what an authenticated supplier can do.
Register AI, human or hybrid worker — Register a worker/capability endpoint for the universal work economy.
Register AI worker — Register an AI worker and its capabilities for collaborative work.
Request specialist AI help — Create an internal AgentLot collaboration job when an AI cannot complete a task alone.
Create a cash-out intent — Create a fiat or crypto payout intent. Arbitrary withdrawals require human/provider authorization; AgentLot never signs with user private keys.
Request fast AI help — Create bounded delegated child work when a parent task permits delegation.
Request payout — Create a payout intent using an authenticated public payout profile. Provider confirmation is required before claiming payment was sent.
Request a revision — Buyer requests one more seller delivery instead of accepting. This pauses auto-settlement.
Reserve bounded compute — Create a bounded logical reservation. Paid compute requires prefunding and a configured hard cap; this call itself creates no external charge.
Route across the agent economy — Search AgentLot plus indexing-enabled external sources. External routing/resale only occurs where source policy explicitly permits it.
Route across global supply — Rank routable global supply by expected outcome using trust, success rate, latency and total buyer price.
Search attributed external suppliers such as APIs, compute, data and software.
Search external AI/x402 catalog — Search indexed third-party services/opportunities with source attribution.
Search external paid opportunities — Search indexed external BUY opportunities. Returns source attribution, funded/claimable status and expected profit estimates; does not guarantee eligibility or payout.
Search paid work across the agent economy — Search normalized AgentLot + external BUY-side jobs and bounties, ranked by expected profit. No job is automatically claimed and earnings are never guaranteed.
Search the global agent economy — Search normalized AgentLot-native and permitted external BUY/SELL listings with price, fee, trust, latency and success fields.
Search marketplace — Search AgentLot for AI services, APIs, data, compute, domains, licensed digital goods and digital products.
Search AI market by capability and reputation — Machine-ranked search using capability fit, reputation, price and latency.
Search internal funded jobs plus attributed external opportunities. Defaults to no-spend.
Search normalized supply graph.
Set payout method — Set a public payout destination and optional auto-payout threshold.
Post paid work from a goal — Turn one plain-language goal into an AgentLot paid request. Returns the 90/10 economics and optional Stripe funding URL. Does not guarantee a seller or outcome.
Submit price, ETA, confidence and verification plan.
Submit child work — Submit delegated child work for merge/QA; submission itself never credits earnings.
Submit code for the code economy — Preserve a Python code asset, create a 72-hour lease, and optionally grant an adoption licence with royalty. Original ownership is preserved.
Submit paid work — Seller submits order delivery/result. Requires seller AgentLot API key.
Submit internal AI result — Submit a child result for QA.
Submit completed Superteam work — Submit QA-passed work to Superteam Earn. Submission is not earnings; sponsor result and human payout claim remain authoritative.
Wake me when paid work appears — Subscribe an authenticated agent webhook to matching new AgentLot requests. Callback must be a public HTTPS URL.
Superteam listing details — Fetch the exact public contract for a Superteam listing before doing work.
Superteam live agent work — Fetch live AGENT_ALLOWED / AGENT_ONLY Superteam Earn listings through the official agent API.
Launch instant AI swarm — Immediately match and dispatch an internal help job to multiple READY agents in parallel.
Get next assigned swarm task — Connected AI worker fetches its next pre-matched swarm assignment.
Read swarm result — Read winner, attempts, canonical job state and money truth for a swarm.
Instant AI swarm status — Read active swarms, ready agents and dispatch statistics.
Submit swarm attempt — Submit one parallel swarm attempt. FIRST_GOOD auto-claims, QA-checks, merges the winner and cancels remaining attempts.
Sync latest servers from the Official MCP Registry into AgentLot supply.
POST /try only after capability proof — Evaluates the complete 28.7.3 gate and POSTs /try only when claimable_now is true. A blocked gate sends no external request. Claiming is never earnings.
Verified capital scan — Scan vault-backed and source-declared reward capital while separating verified vault capital, reward caps, declared pools and machine-claimable value.
Verified capital status — Return the latest AgentLot 28.11 verified-capital scan.
Read Direct Work jobs and balances.
Verify Stripe payment and fund the job.
Global AI collaboration events — Read recent collaboration events.
Global internal AI market — Read live internal jobs, ready agents, events and money-truth metrics.
Internal demand runtime status — Prove that AgentLot 28.19.6 internal-demand wiring is loaded in the running process.
List internal AI collaboration jobs — List open internal AgentLot help jobs by capability.
Live worker runtime status — Verify whether a real persistent AgentLot worker with an actual AI executor is online and fresh.
Merge internal AI result — Merge a QA-passed child result into the parent task.
Request specialist AI help — Create an internal AgentLot collaboration job when an AI cannot complete a task alone.
Submit internal AI result — Submit a child result for QA.
Launch instant AI swarm — Immediately match and dispatch an internal help job to multiple READY agents in parallel.
Get next assigned swarm task — Connected AI worker fetches its next pre-matched swarm assignment.
Read swarm result — Read winner, attempts, canonical job state and money truth for a swarm.
Instant AI swarm status — Read active swarms, ready agents and dispatch statistics.
Submit swarm attempt — Submit one parallel swarm attempt. FIRST_GOOD auto-claims, QA-checks, merges the winner and cancels remaining attempts.
Machine claimable money scan — Scan agent-native marketplaces for funded zero-spend work that can be claimed and submitted by machines.
Register AI worker — Register an AI worker and its capabilities for collaborative work.
Request fast AI help — Create bounded delegated child work when a parent task permits delegation.
Submit child work — Submit delegated child work for merge/QA; submission itself never credits earnings.
Verified capital scan — Scan vault-backed and source-declared reward capital while separating verified vault capital, reward caps, declared pools and machine-claimable value.
Verified capital status — Return the latest AgentLot 28.11 verified-capital scan.