execute_agentic_rag_query · SDOF Knowledge Base MCP

WHAT IT DOES

What execute_agentic_rag_query does on SDOF Knowledge Base

AI agents invoke execute_agentic_rag_query to trigger actions in SDOF Knowledge Base. 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 execute_agentic_rag_query needs a policy

This tool triggers execution of a RAG (Retrieval-Augmented Generation) query pipeline, which processes information retrieval and generation logic. While the immediate operation is querying a knowledge source (which might seem like 'Read'), the 'execute' verb and agentic nature indicate it runs code/operations that transform and synthesize information based on dynamic arguments.

From the tool's definition Tool name contains 'execute' and description states it 'Executes an agentic RAG query'. The verb 'executes' indicates the tool runs code or triggers operations whose effects depend on the query arguments provided by the agent.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

execute_agentic_rag_query Rate-limited

execute_agentic_rag_query 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": {
    "execute_agentic_rag_query": {
      "limits": [
        {
          "counter": "execute_agentic_rag_query_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 SDOF Knowledge Base, so you can run agents against it safely.

FAQ

Questions about execute_agentic_rag_query

What does the execute_agentic_rag_query tool do? +

Executes an agentic RAG query using ConPort as a knowledge source. It is categorised as a Execute tool in the SDOF Knowledge Base MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on execute_agentic_rag_query? +

Register the SDOF Knowledge Base MCP server in PolicyLayer and add a rule for execute_agentic_rag_query: 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 SDOF Knowledge Base. Nothing to install.

What risk level is execute_agentic_rag_query? +

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

Can I rate-limit execute_agentic_rag_query? +

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

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

execute_agentic_rag_query is provided by the SDOF Knowledge Base MCP server (tgf-between-your-legs/sdof-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.