Search LPM packages using natural language or structured filters. Uses hybrid semantic search for natural language queries. Supports filtering by category, distribution mode, package type, ecosystem, license, and more.
AI agents call lpm_search to retrieve information from Lpm Registry without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The lpm_search tool is a pure query/search operation that retrieves information about packages from a registry. It supports natural language and structured filters but does not create, modify, delete, or execute any operations. No packages are installed, modified, or affected by this search operation—it only returns results. This is a classic Read category tool with minimal risk even if misused by an AI agent.
From the tool's definition Tool description explicitly states it 'Search[es] LPM packages' and 'Uses hybrid semantic search for natural language queries.
Attacks that exploit this kind of access
Search LPM packages using natural language or structured filters. Uses hybrid semantic search for natural language queries. Supports filtering by category, distribution mode, package type, ecosystem, license, and more. It is categorised as a Read tool in the Lpm Registry MCP Server, which means it retrieves data without modifying state.
Register the Lpm Registry MCP server in PolicyLayer and add a rule for lpm_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 Lpm Registry. Nothing to install.
lpm_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 lpm_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 lpm_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.
lpm_search is provided by the Lpm Registry MCP server (lpm-dev/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 →