Search, rank and return repositories as a Markdown report.
AI agents call rank_repositories_markdown to retrieve information from Repo Radar MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and presents repository information in ranked order as a formatted report. There are no side effects: it queries existing data, ranks results based on criteria, and returns formatted output. No creation, modification, deletion, or execution of external operations occurs.
From the tool's definition Tool returns ranked repositories as a Markdown report. Operations are 'Search, rank and return' - all read-only operations with no data modification, deletion, or code execution capabilities.
Attacks that exploit this kind of access
Search, rank and return repositories as a Markdown report. It is categorised as a Read tool in the Repo Radar MCP MCP Server, which means it retrieves data without modifying state.
Register the Repo Radar MCP server in PolicyLayer and add a rule for rank_repositories_markdown: 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 Repo Radar MCP. Nothing to install.
rank_repositories_markdown 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 rank_repositories_markdown 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 rank_repositories_markdown. 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.
rank_repositories_markdown is provided by the Repo Radar MCP server (javiermorron/repo-radar-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 →