Watch code changes and trigger documentation drift detection in near real-time.
AI agents invoke change_watcher to trigger actions in Documcp. 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.
This tool executes automated operations (drift detection workflows) triggered by repository events. While the action itself (running drift detection) is not destructive or financial, it represents triggering external code execution whose effects depend on the repository state and detection configuration.
From the tool's definition The tool 'watches code changes and trigger[s] documentation drift detection' - this involves monitoring repository activity and automatically triggering detection operations, which constitutes executing an external process/workflow in response to events.
Documented attack patterns abuse exactly the kind of access change_watcher gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Documcp, and nothing reaches the server without passing your rules. This is the rule we recommend for change_watcher:
{
"version": "1",
"default": "deny",
"tools": {
"change_watcher": {
"limits": [
{
"counter": "change_watcher_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}change_watcher 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.
Free to start. No card required.
Watch code changes and trigger documentation drift detection in near real-time. It is categorised as a Execute tool in the Documcp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Docu MCP server in PolicyLayer and add a rule for change_watcher: 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 Documcp. Nothing to install.
change_watcher is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the change_watcher 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.
Set action: deny in the PolicyLayer policy for change_watcher. 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.
change_watcher is provided by the Docu MCP server (tosin2013/documcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Documcp, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
52 Documcp tools catalogued and risk-classified — across an index of 43,000+ MCP servers.