LAST RESORT: Browse source code of an LPM package remotely. Only use this when you cannot install the package (e.g., evaluating before purchase, checking capabilities without access). If you can install the package, prefer lpm_add or lpm_install first, then read the local files directly — it is f...
AI agents call lpm_browse_source 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.
This tool retrieves source code content for inspection purposes with no side effects on the package, registry, or system. It requires authentication and appropriate licenses, but performs only data retrieval operations. The severity is low because browsing source code carries minimal risk—it cannot modify, delete, or execute code, only read it.
From the tool's definition Tool description explicitly states 'Browse source code' and 'fetch directory paths'. The function is to remotely retrieve and view source code without modifying it.
Attacks that exploit this kind of access
LAST RESORT: Browse source code of an LPM package remotely. Only use this when you cannot install the package (e.g., evaluating before purchase, checking capabilities without access). If you can install the package, prefer lpm_add or lpm_install first, then read the local files directly — it is faster. Requires authentication. Pool packages require Pool subscription, marketplace packages require a license. If you must use this tool: fetch directory paths (e.g.,. 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_browse_source: 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_browse_source 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_browse_source 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_browse_source. 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_browse_source 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 →