evaluate_chunking · ChunkTuner MCP: Risk & Policy

WHAT IT DOES

What evaluate_chunking does on ChunkTuner

AI agents invoke evaluate_chunking to trigger actions in ChunkTuner. 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 evaluate_chunking needs a policy

The tool runs a chunking evaluation process (execute/benchmark pipeline), which may involve computational operations and embedding calls. It's not a simple read/query — it actively executes an evaluation workflow. No destructive, financial, or write side-effects are indicated, but the execution of a full evaluation with embedding models can have significant resource implications.

From the tool's definition 'Dry-run cost estimate or full evaluation' — triggers an evaluation pipeline execution, potentially running embedding functions or benchmarking operations depending on arguments

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

evaluate_chunking Rate-limited

evaluate_chunking 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": {
    "evaluate_chunking": {
      "limits": [
        {
          "counter": "evaluate_chunking_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 ChunkTuner, so you can run agents against it safely.

FAQ

Questions about evaluate_chunking

What does the evaluate_chunking tool do? +

Dry-run cost estimate or full evaluation (DummyEmbeddingFunction if no model). It is categorised as a Execute tool in the ChunkTuner MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on evaluate_chunking? +

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

What risk level is evaluate_chunking? +

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

Can I rate-limit evaluate_chunking? +

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

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

evaluate_chunking is provided by the ChunkTuner MCP server (shantanu-deshmukh/chunktuner). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.