AI agents call lsp_find_implementations to retrieve information from Lsp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves structural information about code (concrete implementations of abstractions) without executing code, modifying files, or triggering side effects. It is a static analysis read operation that queries a language server for navigation and understanding purposes.
From the tool's definition The tool description states it 'finds' implementations and is used to 'understand' how abstractions are used—purely informational queries with no modification or execution.
Attacks that exploit this kind of access
Find all concrete implementations of an interface, abstract class, or abstract method. Use to understand how an abstraction is actually used in practice. It is categorised as a Read tool in the Lsp MCP Server, which means it retrieves data without modifying state.
Register the Lsp MCP server in PolicyLayer and add a rule for lsp_find_implementations: 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 Lsp. Nothing to install.
lsp_find_implementations 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 lsp_find_implementations 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 lsp_find_implementations. 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.
lsp_find_implementations is provided by the Lsp MCP server (lsp-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 →