// SCAN REPORT

Agent MCP

6 tools. 3 can modify or destroy data without limits.

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

Last updated: 10 Jun 2026

3 can modify or destroy data

3 read-only

6 tools total

Community server · catalogue entry verified 10/06/2026

How to control Agent MCP ↓

TOOL MAP

Read (3) Write / Execute (2) Destructive / Financial (1)

MOST DANGEROUS TOOLS

Critical Risk

Destructive · High clear_session_state This tool irreversibly deletes data (session states) that cannot be undone. Write · Medium create_testing_task The tool primarily creates a new testing task (Write), which is a reversible data creation action. Write · Low save_session_state This tool creates or modifies session state records for recovery purposes.

3 of Agent MCP's 6 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL AGENT MCP

PolicyLayer is an MCP gateway — it sits between your AI agents and Agent MCP, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "clear_session_state": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

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

Rate limit write operations

{
  "create_testing_task": {
    "limits": [
      {
        "counter": "create_testing_task_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_audit_report": {
    "limits": [
      {
        "counter": "get_audit_report_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

Create a free account and register Agent MCP — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON AGENT →

Free to start. No card required.

ALL 6 AGENT MCP TOOLS

DESTRUCTIVE 1 tools

Destructive clear_session_state Clear a specific saved session state or all states for this agent/session.

WRITE 2 tools

Write create_testing_task Create a testing task with full access to original work Write save_session_state Save agent working state for session recovery. Use this to preserve important context, task progress, or conve

READ 3 tools

Read get_audit_report Get comprehensive audit report of agent work Read list_session_states List all saved session states for this agent and session. Useful for seeing what context is available after a Read load_session_state Load previously saved agent working state. Use this after a connection recovery to restore your context and co

RELATED SERVERS

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

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

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

How do I prevent bulk modifications through Agent MCP? +

The Agent MCP server has 2 write tools including create_testing_task, save_session_state. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Agent MCP.

How many tools does the Agent MCP server expose? +

6 tools across 3 categories: Destructive, Read, Write. 3 are read-only. 3 can modify, create, or delete data.

How do I enforce a policy on Agent MCP? +

Register the Agent MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Agent MCP tool call.

Deterministic rules across all 6 Agent MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON AGENT →

Free to start. No card required.

6 Agent MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

Agent MCP

// TOOL MAP

// MOST DANGEROUS TOOLS

// HOW TO CONTROL AGENT MCP

// ALL 6 AGENT MCP TOOLS

// RELATED SERVERS

// FAQ