Agent Discover

1 tools. 1 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated:

1 can modify or destroy data
0 read-only
1 tools total
Read (0) Write / Execute (0) Destructive / Financial (1)

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

Deny destructive operations
registry:
  rules:
    - action: deny

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

DESTRUCTIVE 1 tools
Can an AI agent delete data through the Agent Discover MCP server? +

Yes. The Agent Discover server exposes 1 destructive tools including registry. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How many tools does the Agent Discover MCP server expose? +

1 tools across 1 categories: Destructive. 0 are read-only. 1 can modify, create, or delete data.

How do I add Intercept to my Agent Discover setup? +

One line change. Instead of running the Agent Discover server directly, prefix it with Intercept: intercept -c agent-discover.yaml -- npx -y @agent-discover. Download a pre-built policy from policylayer.com/policies/agent-discover 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.

Let agents act without letting them run wild.

Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.

Currently onboarding teams running MCP in production.
// GET IN TOUCH

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

Message sent.

We'll get back to you soon.

// REQUEST EARLY ACCESS

We're letting people in as fast as we can.

You're in the queue.

We'll be in touch as soon as we can let you in.