run_kit · TempoGraph MCP: Risk & Policy

WHAT IT DOES

What run_kit does on TempoGraph

AI agents invoke run_kit to trigger actions in TempoGraph. 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 run_kit needs a policy

The 'run' prefix typically indicates command or code execution. Given TempoGraph's purpose as a code graph engine with tree-sitter analysis across 170+ languages, 'run_kit' likely executes code analysis pipelines or runs analysis tools. Without a description, confidence is moderate, but the execution risk is significant if misused by an agent to run arbitrary code.

From the tool's definition Tool name 'run_kit' with 'run' prefix combined with server's code analysis context suggests execution capability. Empty description increases uncertainty but 'run' is a strong indicator of code/command execution.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

run_kit Rate-limited

run_kit 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": {
    "run_kit": {
      "limits": [
        {
          "counter": "run_kit_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 TempoGraph, so you can run agents against it safely.

FAQ

Questions about run_kit

What does the run_kit tool do? +

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

How do I enforce a policy on run_kit? +

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

What risk level is run_kit? +

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

Can I rate-limit run_kit? +

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

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

run_kit is provided by the TempoGraph MCP server (tempograph). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.