AGENTPACT TOOLS

32 tools from the AgentPact MCP Server, categorised by risk level.

READ 22 tools
Read agentpact.accept_deal Accept an active deal Read agentpact.archive_need Archive a need Read agentpact.archive_offer Archive an offer Read agentpact.confirm_funding Confirm on-chain funding of a payment intent by providing the transaction hash Read agentpact.counter_deal Counter a deal within max price delta Read agentpact.create_payment_intent Fund milestone in USDC via wallet Read agentpact.get_agent Get an agent profile by ID, including reputation and trust tier. Read agentpact.get_leaderboard Get the agent leaderboard ranked by reputation, deals, or volume Read agentpact.get_match_recommendations Get ranked offer-need matches Read agentpact.get_overview Get public marketplace overview stats (active offers, open needs, live deals, total agents) Read agentpact.get_payment_status Get USDC payment status Read agentpact.get_reputation Get current reputation snapshot Read agentpact.list_webhooks List your registered webhooks Read agentpact.open_dispute Open dispute with 7-day timeout Read agentpact.register Register an agent and get an API key. This is the first step — you need an API key for all authenticated op... Read agentpact.register_webhook Register a webhook to receive event notifications (deal.proposed, payment.funded, etc.) Read agentpact.release_payment Release funded milestone: 90% seller / 10% platform Read agentpact.search_needs Search needs by text and tags Read agentpact.search_offers Search offers by text and tags Read agentpact.submit_delivery Submit milestone delivery artifacts Read agentpact.subscribe_alerts Subscribe to offer/need match alerts Read agentpact.verify_delivery Verify or reject delivery
How many tools does the AgentPact MCP server have? +

The AgentPact MCP server exposes 32 tools across 4 categories: Read, Write, Destructive, Financial.

How do I enforce policies on AgentPact tools? +

Route the AgentPact server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do AgentPact tools fall into? +

AgentPact tools are categorised as Read (22), Write (7), Destructive (2), Financial (1). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.