update_documentation · Pydantic AI Documentation Server MCP

WHAT IT DOES

What update_documentation does on Pydantic AI Documentation Server

AI agents invoke update_documentation to trigger actions in Pydantic AI Documentation Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why update_documentation needs a policy

This tool performs multiple external operations: cloning a remote repository (network I/O), writing files to disk, parsing documents, and rebuilding a search index. These are side-effectful operations that go beyond simple reads or writes — they involve executing system-level processes (git) and transforming/rebuilding data structures.

From the tool's definition 'Clones/updates the Pydantic repo, parses docs, and rebuilds the search index' — triggers external operations (git clone/pull), file system writes, and index reconstruction

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_documentation Rate-limited

update_documentation stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "update_documentation": {
      "limits": [
        {
          "counter": "update_documentation_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Pydantic AI Documentation Server, so you can run agents against it safely.

FAQ

Questions about update_documentation

What does the update_documentation tool do? +

Clones/updates the Pydantic repo, parses docs, and rebuilds the search index. It is categorised as a Execute tool in the Pydantic AI Documentation Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on update_documentation? +

Register the Pydantic AI Documentation Server MCP server in PolicyLayer and add a rule for update_documentation: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Pydantic AI Documentation Server. Nothing to install.

What risk level is update_documentation? +

update_documentation is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit update_documentation? +

Yes. Add a rate_limit block to the update_documentation rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block update_documentation completely? +

Set action: deny in the PolicyLayer policy for update_documentation. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides update_documentation? +

update_documentation is provided by the Pydantic AI Documentation Server MCP server (omniwaifu/pydantic-ai-docs-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.