lexicon_request · Lexicon MCP: Risk & Policy

WHAT IT DOES

What lexicon_request does on Lexicon

AI agents invoke lexicon_request to trigger actions in Lexicon. 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 lexicon_request needs a policy

This tool is a generic HTTP client that can invoke any endpoint including DELETE and PATCH, making it capable of destructive, write, and read operations depending on arguments. Since it spans multiple categories, the most severe applicable is chosen.

From the tool's definition Call any Lexicon /v1 endpoint (GET, PATCH, POST, DELETE)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

lexicon_request Rate-limited

lexicon_request 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": {
    "lexicon_request": {
      "limits": [
        {
          "counter": "lexicon_request_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 Lexicon, so you can run agents against it safely.

FAQ

Questions about lexicon_request

What does the lexicon_request tool do? +

Call any Lexicon /v1 endpoint (GET, PATCH, POST, DELETE). See https://www.lexicondj.com/developer/api-docs.yaml. Non-GET requires LEXICON_MCP_ALLOW_WRITES=1. It is categorised as a Execute tool in the Lexicon MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on lexicon_request? +

Register the Lexicon MCP server in PolicyLayer and add a rule for lexicon_request: 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 Lexicon. Nothing to install.

What risk level is lexicon_request? +

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

Can I rate-limit lexicon_request? +

Yes. Add a rate_limit block to the lexicon_request 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 lexicon_request completely? +

Set action: deny in the PolicyLayer policy for lexicon_request. 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 lexicon_request? +

lexicon_request is provided by the Lexicon MCP server (turbotailz/lexicon-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.