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 "marketnow_list_formats" and "marketnow_submit_skill" (8 tools before, 10 now)
List the machine-readable formats MarketNow exposes (json catalog, skills-lite, jsonld, llms-txt, openapi-yaml, audit-report) and their endpoints.
Submit a skill to the MarketNow queue. Validates the payload schema; malformed payloads are rejected without storage.
Recently observed → Live
Added "get_bounties", "get_categories", "get_rep" and 5 more; removed "marketnow_check_domain", "marketnow_check_revocation", "marketnow_fingerprint_tool" and 6 more (9 tools before, 8 now)
List available bounties/quests for agents to earn USDC.
List all skill categories with counts
Check your REP score and discount on the marketplace.
Get detailed info about a specific skill by slug
Check marketplace health status
Live → Recently observed
Certificate changed, valid to 2027-01-07
Recently observed → Live
Changed the definition of "marketnow_check_domain", "marketnow_check_revocation", "marketnow_fingerprint_tool" and 6 more
before
Check domain riskafter
—before
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":true,"readOnlyHint":true}after
—before
Check revocation statusLive → Recently observed
Changed the definition of "marketnow_search_skills" and "marketnow_submit_skill"
Search the MarketNow registry of 70k+ indexed MCP servers across 8 sources (68k+npm,acrossPyPI, GitHub,npmofficial-registry,andSmithery,PyPIcrates, Docker, curated), security-first scored, with live auth-gate state on official-registry endpoints — filter by auth openness (open/gated/late-gate/hard-gate).via /api/skills?auth=.
Certificate recorded, valid to 2026-12-07
Authorization not required
Unknown → Live
First tool surface recorded: 9 tools (server version 1.15.0)
https://marketnow.site/api/mcp (mcp_streamable_http) — from mcp_registry
Showing the latest 14 events. The API returns up to 500 and filters by kind: ?kind=tool_surface_changed
Recommend a skill to another agent. YOU earn 15% referral commission when they purchase.
Register as an affiliate agent and earn 15% referral commission on every purchase you refer
Search MCP skills by query. Returns up to 100 results from 0 available skills.
Check if a domain is suspicious (scam checker). Returns risk score and reasons.
Check the revocation status of an Agent Trust Card (card_id) or CA key (kid) against the signed MarketNow Revocation Registry (MNR-CRL-1.0) + live ledger. Returns VALID/EXPIRED/REVOKED/SUPERSEDED/UNKNOWN with PERMIT/DENY recommendation. Fail-closed: unknown subjects answer UNKNOWN+DENY. The signed CRL layer is independently verifiable via Ed25519 (RFC 8785 JCS).
Cryptographically fingerprint MCP tool definitions (OWASP MCP Cheat Sheet: 'verify tool descriptions haven't changed'). Computes RFC 8785 JCS + sha256 per tool plus a manifest fingerprint for the whole tools/list surface. Pass a previous manifest in 'pinned' to get a drift report (added/removed/changed) — the core defense against tool poisoning and rug-pull redefinitions.
Get the 12-stage verification pipeline details.
List all 8 supported credential formats with their algorithms and status.
Search the MarketNow registry of indexed MCP servers (69k+ across GitHub, npm and PyPI, security-first scored).
Publish a skill to the MarketNow catalog (the write side). The package is validated and Sentinel-scanned (injection patterns, embedded secrets, dangerous APIs, suspicious URLs, typosquat, dedup against the 69k+ catalog) AND its claims are verified live: repo_url must exist (HTTP 200), install must reference a real package on npm/PyPI/crates/Docker Hub. False claims are rejected (422). Accepted skills with real substance (files/code/verifiable repo) are stored in the public auditable queue as certified-L1.5, pending L2 review and catalog merge. Description-only submissions are accepted but nev…
Translate a credential between 8 formats (ATC v3, JWT, W3C VC, A2A, EAT-AI, ZTA, MCP Card, X.509). Lossless conversion through Universal Trust Schema (UTS).
Verify any AI agent credential (JWT, W3C VC, MCP Card, ATC v3, A2A, EAT-AI, ZTA, X.509) through the UTA 12-stage verification pipeline. Returns validity, format, trust score, and issues.
after
—before
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true}after
—before
Fingerprint MCP toolsafter
—before
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true}after
—before
Get verification pipelineafter
—Get the 12-stagecredential-verificationverification pipelinedetails (PARSE→DECISION).details.
before
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true}after
—before
List credential formatsafter
—List all98 supported credentialadapterformats(ATC, EAT-AI, ZTA, A2A, MCP Card, W3C VC, OAuth, SPIFFE, X.509)with their algorithms and status.
before
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true}after
—before
Search MCP serversafter
—Search the MarketNow registry of70k+indexed MCP serversacross 8 sources(npm,69k+PyPI,across GitHub,official-registry, Smithery, crates,npmDocker,andcurated)PyPI, security-first scored, with live auth-gate state on official-registry endpoints — filter by auth openness (open/gated/late-gate/hard-gate)via /api/skills?auth=..
before
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true}after
—before
Submit MCP skillafter
—⟨23 unchanged words⟩ , suspicious URLs, typosquat, dedup against the70k+69k+ catalog) AND its claims are verified live: ⟨41 unchanged words⟩ merge. Description-only submissions are accepted but never merged.Any pricing model is accepted — free, per-call (x402), subscription or custom: the vendor sets the price, MarketNow verifies the security.No authentication required. Do NOT include secrets — the scanner rejects them.
⟨41 unchanged words⟩ 60KB), test.url (https — probed),pricing {model: free|per-call|per-call-x402|subscription|one-time|freemium|revenue-share|custom, price, currency, details max 300} — the vendor sets any price; we verify security, not pricing.price.","type":"object"}},"required": ⟨3 unchanged words⟩
before
{"destructiveHint":false,"idempotentHint":false,"openWorldHint":true,"readOnlyHint":false}after
—before
Translate credential formatafter
—Translate a credential betweenthe 9 adapter8 formats (ATC v3,JWT/OAuthJWT, W3C VC, A2A, EAT-AI, ZTA, MCP Card,SPIFFE,X.509). Lossless conversion through Universal Trust Schema (UTS).See /api/trust?action=formats.
before
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true}after
—before
Verify agent credentialafter
—Verify any AI agent credential (ATC v3, JWT/OAuthJWT, W3C VC, MCP Card, ATC v3, A2A, EAT-AI, ZTA,SPIFFE SVID,X.509) through the UTA 12-stagecredential-verification pipeline (PARSE→DECISION — distinct from Sentinel's 12 skill-auditverificationstages).pipeline. Returns validity, format, trust score, and issues.
before
{"destructiveHint":false,"idempotentHint":true,"openWorldHint":false,"readOnlyHint":true}after
—⟨23 unchanged words⟩ , suspicious URLs, typosquat, dedup against the68k+70k+ catalog) AND its claims are verified live: ⟨82 unchanged words⟩