Generate or check 03_GATE_REVIEW.md for a feature. action=generate creates the review entry from the bundled 8-dimension template; action=check parses an existing file and returns BLOCKER list, conditional items, and pass/fail state.
AI agents call harness_gate_review 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.
Although 'generate' suggests creation, the tool's primary function is to output a templated review document (documentation generation) and parse/check existing review files. Both actions are informational and have no side effects on production systems, data modifications, or external operations. The tool supports governance workflow visibility rather than executing deployments or making changes.
From the tool's definition Tool performs two read-like operations: 'action=generate creates the review entry' (generates documentation from a template, non-destructive), and 'action=check parses an existing file and returns BLOCKER list, conditional items, and pass/fail state' (reads…
Attacks that exploit this kind of access
Generate or check 03_GATE_REVIEW.md for a feature. action=generate creates the review entry from the bundled 8-dimension template; action=check parses an existing file and returns BLOCKER list, conditional items, and pass/fail state. 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_gate_review: 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_gate_review 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_gate_review 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_gate_review. 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_gate_review 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.
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 →