Medium Risk

watch_repository

Start or stop watching a repository for changes. When watching is enabled, the system automatically detects file changes and updates the index accordingly.

How to control watch_repository ↓

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

Medium Risk

This tool modifies system behavior by enabling or disabling a watch process on a repository, and triggers automatic index updates when file changes are detected. It creates/modifies a watch configuration and causes ongoing write operations to the index. This is reversible (can be toggled on/off), placing it in the Write category rather than Execute, though it does trigger background automated processes.

From the tool's definition Start or stop watching a repository for changes. When watching is enabled, the system automatically detects file changes and updates the index accordingly.

Documented attack patterns abuse exactly the kind of access watch_repository gives an agent:

PolicyLayer is an MCP gateway — it sits between your AI agents and RAG Documentation MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for watch_repository:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "watch_repository": {
      "limits": [
        {
          "counter": "watch_repository_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

watch_repository 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.

  1. Create a free account and register RAG Documentation MCP Server — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Go deeper

What does the watch_repository tool do? +

Start or stop watching a repository for changes. When watching is enabled, the system automatically detects file changes and updates the index accordingly. It is categorised as a Write tool in the RAG Documentation MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on watch_repository? +

Register the RAG Documentation MCP Server MCP server in PolicyLayer and add a rule for watch_repository: 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 RAG Documentation MCP Server. Nothing to install.

What risk level is watch_repository? +

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

Can I rate-limit watch_repository? +

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

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

watch_repository is provided by the RAG Documentation MCP Server MCP server (rahulretnan/mcp-ragdocs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every RAG Documentation MCP Server tool call.

Deterministic rules across all 14 RAG Documentation MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

14 RAG Documentation MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.