AI agents call search_docs to retrieve information from DocShark without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries indexed documentation data without modifying, deleting, or executing any operations. It is a passive information retrieval function analogous to a search engine query. The local nature of the indexed knowledge base and public documentation sources present no destructive or financial risk.
From the tool's definition Tool performs 'full-text searches on a local knowledge base' and 'returns ranked sections with URLs'. The verb 'search' and the action of retrieving documentation sections are read-only operations with no side effects.
Attacks that exploit this kind of access
Search indexed docs by keyword or library. Returns ranked sections with URLs. It is categorised as a Read tool in the DocShark MCP Server, which means it retrieves data without modifying state.
Register the DocShark MCP server in PolicyLayer and add a rule for search_docs: 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 DocShark. Nothing to install.
search_docs 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_docs 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_docs. 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_docs is provided by the DocShark MCP server (michael-obele/docshark). 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 →