This record as markdown: /tools/io-github-dave-london-build/search.md
What search does on Build
AI agents call search to retrieve information from Build without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why search is rated Low
This tool only retrieves information from the npm registry in response to a search query. It performs a query operation without creating, modifying, deleting, or executing any code. Even in the context of a build tool server, searching a registry is fundamentally a read operation with minimal risk if misused by an AI agent.
From the tool's definition Tool description states it "Searches the npm registry for packages matching a query." The verb 'searches' and the read-only nature of querying a registry indicates no data modification or side effects.
Attacks that exploit this kind of access
The rule that runs search safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Build, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For search, this is the rule to start with:
search is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Build, apply this rule, and every search call is checked against it from then on.
Questions about search
Searches the npm registry for packages matching a query. It is categorised as a Read tool in the Build MCP Server, which means it retrieves data without modifying state.
Register the Build MCP server in PolicyLayer and add a rule for 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 Build. Nothing to install.
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 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 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.
search is provided by the Build MCP server (Dave-London/Pare). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Build, and thousands of servers like it.
This server
Across the catalogue