Compare multiple repositories.
AI agents call compare_repositories 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 comparative information about GitHub repositories without modifying, deleting, or executing any code. It is a read operation with no side effects, making it low severity. The confidence is high because the intent is unambiguous from both the tool name and server purpose.
From the tool's definition Tool name 'compare_repositories' and description 'Compare multiple repositories' indicate data retrieval and analysis only. The server description confirms this is about 'searching, filtering, ranking, and evaluating' repositories—all read-only operations.
Attacks that exploit this kind of access
Compare multiple repositories. 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 compare_repositories: 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.
compare_repositories 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 compare_repositories 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 compare_repositories. 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.
compare_repositories 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 →