AI agents call search_library to retrieve information from Dag 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 information from library documentation and code without side effects. It is a passive search functionality that returns results but does not create, modify, delete, or execute anything. The server's purpose of providing 'version-aware access to npm library documentation' and 'semantic search' further confirms this is a Read category tool with low severity risk.
From the tool's definition Tool name 'search_library' combined with description 'Semantic search across library documentation and code' indicates a read-only query operation. No modification, deletion, or execution of code is implied.
Attacks that exploit this kind of access
Semantic search across library documentation and code. It is categorised as a Read tool in the Dag MCP Server, which means it retrieves data without modifying state.
Register the Dag MCP server in PolicyLayer and add a rule for search_library: 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 Dag. Nothing to install.
search_library 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_library 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_library. 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_library is provided by the Dag MCP server (vamfi/dag-mcp-server). 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 →