indexfoundry_serve_start · IndexFoundry MCP: Risk & Policy

WHAT IT DOES

What indexfoundry_serve_start does on IndexFoundry MCP

AI agents invoke indexfoundry_serve_start to trigger actions in IndexFoundry MCP. 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 indexfoundry_serve_start needs a policy

Starting a server is an Execute action: it triggers an external operation (HTTP server startup) whose actual effects depend on arguments and system state (which run, what vectors/chunks are loaded, which endpoints become available). It is not a Read (doesn't just query/fetch), not Write (doesn't create/modify persistent data), not Destructive (reversible via stopping the server), and not Financial.

From the tool's definition Tool description states it will 'Start an HTTP search API server' and 'Loads vectors and chunks into memory, serves semantic/hybrid/keyword search endpoints' — these are external operational triggers that initiate a server process with effects dependent on…

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

indexfoundry_serve_start Rate-limited

indexfoundry_serve_start 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": {
    "indexfoundry_serve_start": {
      "limits": [
        {
          "counter": "indexfoundry_serve_start_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 IndexFoundry MCP, so you can run agents against it safely.

FAQ

Questions about indexfoundry_serve_start

What does the indexfoundry_serve_start tool do? +

Start an HTTP search API server for a run. Loads vectors and chunks into memory, serves semantic/hybrid/keyword search endpoints. It is categorised as a Execute tool in the IndexFoundry MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on indexfoundry_serve_start? +

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

What risk level is indexfoundry_serve_start? +

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

Can I rate-limit indexfoundry_serve_start? +

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

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

indexfoundry_serve_start is provided by the IndexFoundry MCP server (mnehmos/mnehmos.index-foundry.mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.