Find a repository by its full name (owner/repo format). Returns repository details including ID, URLs, and configuration. If required information is not provided, use the git command or any available tool to get more context about the current commit, the repository, or the author of the commit.
AI agents call search_repository to retrieve information from Woodpecker without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves repository metadata and configuration information without creating, modifying, or deleting any data. It performs a search/lookup query which is a classic Read operation. The severity is low as the blast radius is minimal—an AI agent misusing this tool would only be able to discover information about repositories, not cause operational harm or data loss.
From the tool's definition Tool name is 'search_repository' and description states it 'Find a repository' and 'Returns repository details including ID, URLs, and configuration.' The verb 'Find' and 'Returns' indicate a retrieval operation with no modification of data.
Documented attack patterns abuse exactly the kind of access search_repository gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Woodpecker, and nothing reaches the server without passing your rules. This is the rule we recommend for search_repository:
{
"version": "1",
"default": "deny",
"tools": {
"search_repository": {}
}
}search_repository is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Find a repository by its full name (owner/repo format). Returns repository details including ID, URLs, and configuration. If required information is not provided, use the git command or any available tool to get more context about the current commit, the repository, or the author of the commit. It is categorised as a Read tool in the Woodpecker MCP Server, which means it retrieves data without modifying state.
Register the Woodpecker MCP server in PolicyLayer and add a rule for search_repository: 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 Woodpecker. Nothing to install.
search_repository 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 search_repository 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 search_repository. 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.
search_repository is provided by the Woodpecker MCP server (j04n-f/woodpecker-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Woodpecker, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Woodpecker tools catalogued and risk-classified — across an index of 43,000+ MCP servers.