Use this to implement/execute existing tasks from tasks.md that have already been defined. This tool assumes tasks already exist and focuses on coordinating their implementation. DO NOT use this for generating new plans or tasks - only for executing tasks that have already been created.
AI agents invoke task-orchestrator to trigger actions in Spec MCP Server. 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 runs/executes pre-defined tasks from tasks.md, making it an Execute category tool rather than Read or Write. While it doesn't directly delete data (not Destructive) or move money (not Financial), it orchestrates the execution of arbitrary tasks whose side effects depend on what those tasks contain. This poses significant risk if a task is malicious or if the AI agent selects the wrong task to execute.
From the tool's definition Tool description states it "implement/execute existing tasks" and focuses on "coordinating their implementation." The name "task-orchestrator" and the execution-focused language (implement, execute, coordinating) indicate this triggers external operations…
Attacks that exploit this kind of access
Use this to implement/execute existing tasks from tasks.md that have already been defined. This tool assumes tasks already exist and focuses on coordinating their implementation. DO NOT use this for generating new plans or tasks - only for executing tasks that have already been created. It is categorised as a Execute tool in the Spec MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Spec MCP Server MCP server in PolicyLayer and add a rule for task-orchestrator: 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 Spec MCP Server. Nothing to install.
task-orchestrator 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 task-orchestrator 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 task-orchestrator. 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.
task-orchestrator is provided by the Spec MCP Server MCP server (karol-f/spec-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →