index_context · Superkit MCP: Risk & Policy

WHAT IT DOES

What index_context does on Superkit

AI agents invoke index_context to trigger actions in Superkit. 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 index_context needs a policy

This tool triggers an active operation (re-indexing) rather than simply reading existing data. It scans and processes files to rebuild an index, which is an execution action with system-wide scope. While it doesn't delete or modify user data, it can alter the state of the index and affect how agents, skills, and workflows are discovered.

From the tool's definition 'Manually trigger re-indexing of all super-kit context (agents, skills, workflows)'

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

index_context Rate-limited

index_context 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": {
    "index_context": {
      "limits": [
        {
          "counter": "index_context_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 Superkit, so you can run agents against it safely.

FAQ

Questions about index_context

What does the index_context tool do? +

Manually trigger re-indexing of all super-kit context (agents, skills, workflows). Useful after adding new files. Returns indexing stats. It is categorised as a Execute tool in the Superkit MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on index_context? +

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

What risk level is index_context? +

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

Can I rate-limit index_context? +

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

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

index_context is provided by the Superkit MCP server (superkit-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.