index_codebase · Claude Context MCP: Risk & Policy

WHAT IT DOES

What index_codebase does on Claude Context MCP

AI agents use index_codebase to create or update resources in Claude Context MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Context MCP environment.

WHY IT NEEDS A POLICY

Why index_codebase needs a policy

This tool reads files from a directory and writes (creates/updates) vector embeddings and index entries in a database. It does not delete or overwrite source files, but it does modify the shared index store. The blast radius is medium — misuse could corrupt or pollute the shared semantic search index used by all employees, but the source code itself is not altered.

From the tool's definition 'Index company documents and code for shared access by all employees. Indexes the entire branch directory'

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

index_codebase Rate-limited

index_codebase stays usable, but capped — an agent stuck in a loop can't make hundreds of changes 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_codebase": {
      "limits": [
        {
          "counter": "index_codebase_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Claude Context MCP, so you can run agents against it safely.

FAQ

Questions about index_codebase

What does the index_codebase tool do? +

Index company documents and code for shared access by all employees. Indexes the entire branch directory: {reposBasePath}/{defaultProject}/{defaultBranch}. It is categorised as a Write tool in the Claude Context MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on index_codebase? +

Register the Claude Context MCP server in PolicyLayer and add a rule for index_codebase: 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 Claude Context MCP. Nothing to install.

What risk level is index_codebase? +

index_codebase is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit index_codebase? +

Yes. Add a rate_limit block to the index_codebase 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_codebase completely? +

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

index_codebase is provided by the Claude Context MCP server (sahinrasit/ibtech-mcp-claude-context). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.