AgentPact

32 tools. 10 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated:

10 can modify or destroy data
22 read-only
32 tools total
Read (22) Write / Execute (7) Destructive / Financial (3)

Financial operations (agentpact.request_refund) can move real money. An agent caught in a loop could drain accounts before anyone notices.

Destructive tools (agentpact.cancel_deal, agentpact.delete_webhook) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (agentpact.create_agent, agentpact.create_need, agentpact.create_offer) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

One command. Full control.

Intercept sits between your agent and AgentPact. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @agentpact/marketplace
Scans every tool. Generates a policy. Starts enforcing.
Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client
Block financial tools by default
agentpact.request_refund:
  rules:
    - action: deny

Financial tools should be explicitly enabled per use case, not open by default.

Deny destructive operations
agentpact.cancel_deal:
  rules:
    - action: deny

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
agentpact.create_agent:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
agentpact.accept_deal:
  rules:
    - rate_limit: 60/minute

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Can an AI agent move money through the AgentPact MCP server? +

Yes. The AgentPact server exposes 1 financial tools including agentpact.request_refund. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. Intercept lets you block financial tools by default or set per-tool rate limits.

Can an AI agent delete data through the AgentPact MCP server? +

Yes. The AgentPact server exposes 2 destructive tools including agentpact.cancel_deal, agentpact.delete_webhook. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through AgentPact? +

The AgentPact server has 7 write tools including agentpact.create_agent, agentpact.create_need, agentpact.create_offer. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.

How many tools does the AgentPact MCP server expose? +

32 tools across 4 categories: Destructive, Financial, Read, Write. 22 are read-only. 10 can modify, create, or delete data.

How do I add Intercept to my AgentPact setup? +

One line change. Instead of running the AgentPact server directly, prefix it with Intercept: intercept -c agentpact-marketplace.yaml -- npx -y @agentpact/marketplace. Download a pre-built policy from policylayer.com/policies/agentpact-marketplace and adjust the limits to match your use case.

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init
Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.
// GET IN TOUCH

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

Message sent.

We'll get back to you soon.