Route a user task description to the appropriate skill workflow. Returns skill name, deliverable checklist, and whether a forced upgrade is needed (>8h estimated, DB change, etc).
AI agents call harness_route_task to retrieve information from Harness Engineering MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool analyzes a task description and returns routing information (skill name, checklist, upgrade flag). It reads/evaluates input and returns recommendations without creating, modifying, executing, or deleting anything. It is a pure query/analysis operation with no side effects.
From the tool's definition Route a user task description to the appropriate skill workflow. Returns skill name, deliverable checklist, and whether a forced upgrade is needed
Attacks that exploit this kind of access
Route a user task description to the appropriate skill workflow. Returns skill name, deliverable checklist, and whether a forced upgrade is needed (>8h estimated, DB change, etc). It is categorised as a Read tool in the Harness Engineering MCP MCP Server, which means it retrieves data without modifying state.
Register the Harness Engineering MCP server in PolicyLayer and add a rule for harness_route_task: 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 Harness Engineering MCP. Nothing to install.
harness_route_task is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the harness_route_task 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 harness_route_task. 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.
harness_route_task is provided by the Harness Engineering MCP server (movebrickschi/harness-engineering-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
harness_route_task is one line of Harness Engineering's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →