// SCAN REPORT

FastMCP

8 tools. 5 can modify or destroy data without limits.

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

Last updated: 5 Jul 2026

5 can modify or destroy data

3 read-only

8 tools total

Community server · catalogue entry verified 05/07/2026

How to control FastMCP ↓

TOOL MAP

What FastMCP exposes to your agents

Read (3) Write / Execute (4) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous FastMCP tools

Destructive · High delete_context This tool performs an irreversible deletion operation on a context resource. Execute · High query_model The tool explicitly executes a query against a context, which implies running dynamic operations whose effects depend on the query arguments. Write · Medium configure_datadog This tool writes/updates configuration settings for Datadog integration, including credentials. Write · Medium create_context The tool creates new contexts within the system.

5 of FastMCP's 8 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control FastMCP

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

Deny destructive operations

{
  "delete_context": {
    "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

{
  "configure_datadog": {
    "limits": [
      {
        "counter": "configure_datadog_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "get_context": {
    "limits": [
      {
        "counter": "get_context_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 FastMCP — 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 FASTMCP →

Instant setup, no code required.

FULL CATALOGUE

All 8 FastMCP tools

DESTRUCTIVE 1 tools

Destructive delete_context Delete a context by its ID

EXECUTE 1 tools

Execute query_model Execute a query against a specific context

WRITE 3 tools

Write configure_datadog Configure Datadog integration with the provided credentials Write create_context create_context Write update_context Update an existing context with new values

READ 3 tools

Read get_context Retrieve a specific context by its ID Read health_check Check the health status of the server Read list_contexts List all contexts with optional filtering by model name or tag

EXPLORE

Related servers

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

FAQ

Questions about FastMCP

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

Yes. The FastMCP server exposes 1 destructive tools including delete_context. 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 FastMCP? +

The FastMCP server has 3 write tools including configure_datadog, create_context, update_context. 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 FastMCP.

How many tools does the Fast MCP server expose? +

8 tools across 3 categories: Destructive, Read, Write. 3 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on FastMCP? +

Register the Fast 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 FastMCP tool call.

Deterministic rules across all 8 FastMCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON FASTMCP →

Instant setup, no code required.

8 FastMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.