Execute a named pipeline immediately. Pipelines are predefined multi-agent workflows (e.g. memory-consolidation, daily-summary). Returns a job ID — poll with crow_orchestrate_status.
AI agents invoke crow_run_pipeline 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.
The tool triggers execution of predefined workflows that perform actions on external systems or data. While the pipelines are predefined (reducing arbitrary code execution risk), the tool still initiates multi-agent operations that can have broad side effects across integrated platforms (project management, memory consolidation, etc.).
From the tool's definition Tool executes a named pipeline immediately, runs multi-agent workflows, and initiates external operations whose effects depend on pipeline arguments and configuration.
Documented attack patterns abuse exactly the kind of access crow_run_pipeline 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_run_pipeline:
{
"version": "1",
"default": "deny",
"tools": {
"crow_run_pipeline": {
"limits": [
{
"counter": "crow_run_pipeline_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}crow_run_pipeline 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.
Execute a named pipeline immediately. Pipelines are predefined multi-agent workflows (e.g. memory-consolidation, daily-summary). Returns a job ID — poll with crow_orchestrate_status. 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_run_pipeline: 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_run_pipeline 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_run_pipeline 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_run_pipeline. 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_run_pipeline 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.