Get the definition location(s) for a symbol at a position (go-to-definition)
AI agents call getDefinition to retrieve information from TypeScript LSP MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a pure information retrieval operation analogous to IDE navigation features. It queries type information and returns location data without creating, modifying, deleting, or executing anything. The low severity reflects the minimal risk from an AI agent accessing symbol definition locations.
From the tool's definition Tool performs a read-only 'go-to-definition' query that retrieves definition location(s) for a symbol without modifying any files or executing code. The description explicitly states 'Get the definition location(s)' with no mention of side effects.
Attacks that exploit this kind of access
Get the definition location(s) for a symbol at a position (go-to-definition). It is categorised as a Read tool in the TypeScript LSP MCP MCP Server, which means it retrieves data without modifying state.
Register the TypeScript LSP MCP server in PolicyLayer and add a rule for getDefinition: 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 TypeScript LSP MCP. Nothing to install.
getDefinition 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 getDefinition 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 getDefinition. 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.
getDefinition is provided by the TypeScript LSP MCP server (jaenster/ts-lsp-mcp). 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 →