embed_corpus · Pg MCP: Risk & Policy

WHAT IT DOES

What embed_corpus does on Pgmcp

AI agents invoke embed_corpus to trigger actions in Pgmcp. 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 embed_corpus needs a policy

Embedding all documents is a large-scale computational operation that processes and transforms existing data. It is not a simple read, nor a targeted write, but an execution of a bulk pipeline that modifies the internal state of all documents (adding vector embeddings). This is Execute category.

From the tool's definition 'Embed all documents in a corpus to enable semantic search and retrieval' — triggers a bulk processing operation across all documents in a corpus

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

embed_corpus Rate-limited

embed_corpus 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": {
    "embed_corpus": {
      "limits": [
        {
          "counter": "embed_corpus_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 Pgmcp, so you can run agents against it safely.

FAQ

Questions about embed_corpus

What does the embed_corpus tool do? +

Embed all documents in a corpus to enable semantic search and retrieval. It is categorised as a Execute tool in the Pgmcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on embed_corpus? +

Register the Pg MCP server in PolicyLayer and add a rule for embed_corpus: 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 Pgmcp. Nothing to install.

What risk level is embed_corpus? +

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

Can I rate-limit embed_corpus? +

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

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

embed_corpus is provided by the Pg MCP server (veloper/pgmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.