Composite diff verdict: auto_merge | single_review | dual_review | expert_review | block. Aggregates blast radius, community boundaries, findings, orphan grade, fix-follow-feat density, and ownership into a single decision with confidence, reasoning chain, decision-boundary distance, recommended ...
AI agents call verdict to retrieve information from OpenCodeHub MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only analytical tool that synthesizes code analysis into a recommendation artifact. No data is created, modified, or deleted; no code is executed or deployed; no financial transactions occur. The output informs human decision-making (e.g., who should review a PR) but the tool itself performs no side effects. It is similar to linting or static analysis tools that produce reports.
From the tool's definition The tool computes and returns a verdict decision (auto_merge | single_review | dual_review | expert_review | block) with supporting metadata (confidence, reasoning chain, decision-boundary distance, reviewers, labels, PR-comment).
Attacks that exploit this kind of access
Composite diff verdict: auto_merge | single_review | dual_review | expert_review | block. Aggregates blast radius, community boundaries, findings, orphan grade, fix-follow-feat density, and ownership into a single decision with confidence, reasoning chain, decision-boundary distance, recommended reviewers, GitHub labels, and a PR-comment markdown string. Exit codes: 0/1/2 mapped per PRD. It is categorised as a Read tool in the OpenCodeHub MCP Server MCP Server, which means it retrieves data without modifying state.
Register the OpenCodeHub MCP Server MCP server in PolicyLayer and add a rule for verdict: 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 OpenCodeHub MCP Server. Nothing to install.
verdict 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 verdict 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 verdict. 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.
verdict is provided by the OpenCodeHub MCP Server MCP server (theagenticguy/opencodehub). 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 →