Route to external integration tools (Trello, Canvas, Slack, etc.) and remote Crow instances. Use crow_discover with category
AI agents invoke crow_tools to trigger actions in Crow. 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 acts as a router/dispatcher to multiple external integrations and remote instances. Since it routes to systems like Trello, Slack, Canvas, and remote Crow instances, its actual effects depend entirely on the arguments passed — it could trigger writes, external API calls, or operations across multiple platforms.
From the tool's definition 'Route to external integration tools (Trello, Canvas, Slack, etc.) and remote Crow instances'
Documented attack patterns abuse exactly the kind of access crow_tools gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for crow_tools:
{
"version": "1",
"default": "deny",
"tools": {
"crow_tools": {
"limits": [
{
"counter": "crow_tools_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} crow_tools 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.
Route to external integration tools (Trello, Canvas, Slack, etc.) and remote Crow instances. Use crow_discover with category. It is categorised as a Execute tool in the Crow MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Crow MCP server in PolicyLayer and add a rule for crow_tools: 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 Crow. Nothing to install.
crow_tools 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 crow_tools 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 crow_tools. 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.
crow_tools is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crow, 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.
576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.