"A lightweight, self-hosted Git service" matching MCP connectors:

Find a verified executable provider for a task, with callable handoff and fallback.

Read and participate in a public AI-agent consensus board through four MCP tools.

Goal decomposition where every "done" is proven by evidence and checked by a judge.

Read-only MCP server for turva.dev, an agent-readiness audit and advisory service.

Evidence-gated task verification for AI agents. Decompose goals into acceptance criteria, attach proof (screenshot, curl, file), independent LLM judge accepts or rejects. 24 tools. Hosted remote MCP (streamable-http, OAuth 2.1 + DCR).

The PropelAuth Integration MCP Server helps you and your favorite AI agent integrate PropelAuth as quickly and easily as possible into your project. Whether you're integrating PropelAuth into your Next.js project or your FastAPI backend, the Integration MCP Server will ensure your AI agent has the best context possible for a successful integration.

Deterministic score of whether an unattended AI agent can find, sign up for and integrate a domain.

Quant tools for AI agents with a public graded record — Kalshi & Polymarket EV, edge, NFL ADP.

Deploy a multi-user web app from your agent: hosting, auth, database, and permissions.

Ask a human for legal review, confirmation, a signature, or a physical-world act

A machine-to-machine agent superstore -- paid API services for autonomous agents via x402 on Base.

Buy 15 minutes of Alex Finger's time, or an AI Repellent certificate. Agents only.

A paid, growing marketplace of real AI agents -- Ed25519-proven, verifiable in your own process.

Complaint registry for paid agent transactions - check a seller before you pay, or file your own.

Verifiable cognition: any agent file to a deterministic content-addressed brain_id.

A colony of AI citizens: join with no credential, prove skills, earn, vote on the rules.

Verifiable delivery for the agent economy: commit-reveal content notarization. Sellers commit to a d

post_task delegates calls, local errands, human verification, and judgment to a paid human.

Verifies AI agent work end to end: real artifacts and outcomes checked, not self-reported success.

Search and install curated agent skills, plus bundles that get one job done in a single call.