Put a commit subject and diff on trial and return a structured verdict.
AI agents call court.prosecute_commit to retrieve information from Commit Conventional Message Court (CCMCP) without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool takes a commit subject and diff as input, performs AI analysis, and returns a structured verdict. This is a read/query operation that produces output based on its inputs without modifying any data, executing code, or causing external side effects. The 'trial' and 'verdict' language is metaphorical for an analysis pipeline.
From the tool's definition 'Put a commit subject and diff on trial and return a structured verdict' — the tool analyzes input (commit subject and diff) and returns a verdict; no side effects described.
Attacks that exploit this kind of access
Put a commit subject and diff on trial and return a structured verdict. It is categorised as a Read tool in the Commit Conventional Message Court (CCMCP) MCP Server, which means it retrieves data without modifying state.
Register the Commit Conventional Message Court (CCMCP) MCP server in PolicyLayer and add a rule for court.prosecute_commit: 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 Commit Conventional Message Court (CCMCP). Nothing to install.
court.prosecute_commit 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 court.prosecute_commit 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 court.prosecute_commit. 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.
court.prosecute_commit is provided by the Commit Conventional Message Court (CCMCP) MCP server (jiseong-choi/ccmcp). 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 →