Full-text keyword search across all wiki pages. Returns paths, scores, and snippets sorted by relevance.
AI agents call wiki_search to retrieve information from Agent Wiki without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves wiki content without modifying, executing code, or causing side effects. It is a pure read operation that searches and returns information (paths, scores, snippets) to the user. The search-and-retrieve pattern with no mutation capability places it squarely in the Read category.
From the tool's definition Full-text keyword search across all wiki pages. Returns paths, scores, and snippets sorted by relevance.
Attacks that exploit this kind of access
Full-text keyword search across all wiki pages. Returns paths, scores, and snippets sorted by relevance. It is categorised as a Read tool in the Agent Wiki MCP Server, which means it retrieves data without modifying state.
Register the Agent Wiki MCP server in PolicyLayer and add a rule for wiki_search: 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 Agent Wiki. Nothing to install.
wiki_search 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 wiki_search 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 wiki_search. 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.
wiki_search is provided by the Agent Wiki MCP server (xinhuagu/agent-wiki). 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 →