Act for a person on websites: sandboxed browser, phone approvals, saved logins, scheduled plans.
Auth, SSO, permissions.
Act for a person on websites: sandboxed browser, phone approvals, saved logins, scheduled plans.
Protect an MCP server with Authio: token verification, protected resource metadata, WWW-Authenticate challenges and connected-account token exchange.
BCS fork of GitLab MCP server for pipelines, repositories, merge requests, issues, and content masking
Dual-rail Lightning paywall for MCP servers: accepts L402 and x402 bip122/exact, one LNBits backend.
Extract user identity (name, emails, accounts, addresses, payments) from browser data into a self-ranking SQLite database. Install as a Claude Code agent skill.
An ability-resolution and governed execution layer for AI agents: use prepared providers first, then resolve abilities from the broader software world.
Ask a human before your agent acts: approval requests decided on a phone.
NoxSoft's agent runtime: persistent identity, memory, heartbeat, feelings and learning, with a local UI. No dependencies beyond Node.
Model Context Protocol server exposing TrustRail governed-action evaluation to MCP-capable agents
MCP server for interacting with APIs and web services
The Rakomi CLI — sign in, connect an AI agent (Claude Code, Claude Desktop) to your tenant, and provision tenants. EU-native auth-as-a-service.
Use Verifik identity verification, document checks, and background-screening APIs from Cursor, Claude Desktop, or any MCP client — across Latin America and worldwide.
Scoped session grants for .agt owners: build, describe and redeem per-name record-write mandates enforced on-chain (EIP-7702 + MetaMask Delegation Framework).
MCP server for 01 Protocol — AI agent identity tools for Claude Desktop and MCP-compatible apps
Stop AI coding agents (Claude Code, Codex, Copilot and more) from reading your .env secrets — sets up per-agent permission configs automatically.
Give Claude Code a soul — persistent identity, cross-session learning, and evolving cognitive frameworks
Cryptographic delegation chains for AI agent authorization — sign, verify, delegate
Model Context Protocol (MCP) client support for Forgewisp agents — expose an MCP server's tools as agent FunctionDefinitions
Read-only MCP server for DMARC, SPF, DKIM, BIMI and MTA-STS checks, DMARC record generation, and aggregate-report analysis — powered by plaindmarc.com's public tools. No API key, no account.
Governs an agent's existing MCP tools by configuration instead of by code change