process_query · Sentient Brain Smithery MCP: Risk & Policy

WHAT IT DOES

What process_query does on Sentient Brain Smithery

AI agents invoke process_query to trigger actions in Sentient Brain Smithery. 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 process_query needs a policy

The description is empty, which significantly lowers confidence. However, 'process_query' in the context of a multi-agent AI system with SurrealDB (a database) and orchestration capabilities suggests it likely executes queries against the database or triggers agent pipelines. Given sibling tools like 'run_diagnostics' and 'analyze_codebase', this tool likely executes some form of query or processing operation.

From the tool's definition Tool name 'process_query' combined with server context involving 'run_diagnostics', 'analyze_codebase', and SurrealDB/Groq execution capabilities.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

process_query Rate-limited

process_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": {
    "process_query": {
      "limits": [
        {
          "counter": "process_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 Sentient Brain Smithery, so you can run agents against it safely.

FAQ

Questions about process_query

What does the process_query tool do? +

process_query. It is categorised as a Execute tool in the Sentient Brain Smithery MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on process_query? +

Register the Sentient Brain Smithery MCP server in PolicyLayer and add a rule for process_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 Sentient Brain Smithery. Nothing to install.

What risk level is process_query? +

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

Can I rate-limit process_query? +

Yes. Add a rate_limit block to the process_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 process_query completely? +

Set action: deny in the PolicyLayer policy for process_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 process_query? +

process_query is provided by the Sentient Brain Smithery MCP server (mbpfws/sentient-brain-smithery). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.