index_directory · Code Context Manager MCP: Risk & Policy

WHAT IT DOES

What index_directory does on Code Context Manager

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

WHY IT NEEDS A POLICY

Why index_directory needs a policy

This tool reads files from a directory and writes/creates index entries (vector embeddings and metadata) in a search index. It creates new data structures but does not delete or overwrite existing source files, making it a Write operation. Misuse could lead to indexing sensitive codebases or consuming significant storage/compute resources.

From the tool's definition Indexes an entire project directory for file and entity context, making them available for vector search

Risk signalsBulk/mass operation — affects multiple targets

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

index_directory Rate-limited

index_directory 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_directory": {
      "limits": [
        {
          "counter": "index_directory_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 Code Context Manager, so you can run agents against it safely.

FAQ

Questions about index_directory

What does the index_directory tool do? +

Indexes an entire project directory for file and entity context, making them available for vector search. Supports Python, JavaScript, and TypeScript files. This must be called before using. It is categorised as a Write tool in the Code Context Manager 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_directory? +

Register the Code Context Manager MCP server in PolicyLayer and add a rule for index_directory: 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 Code Context Manager. Nothing to install.

What risk level is index_directory? +

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

Can I rate-limit index_directory? +

Yes. Add a rate_limit block to the index_directory 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_directory completely? +

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

index_directory is provided by the Code Context Manager MCP server (theraaz/code-context-manager-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.