Get autocomplete suggestions at a position
AI agents call getCompletions 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.
The tool queries type information to provide autocomplete suggestions, similar to IDE IntelliSense. It does not execute code, modify files, delete data, or commit financial transactions. It is a pure query operation that returns data to inform the user, making it a Read category risk with low severity.
From the tool's definition Tool name is 'getCompletions' and description states 'Get autocomplete suggestions at a position'. This is a read-only operation that retrieves IDE-style completion suggestions without modifying code, executing arbitrary operations, or causing side effects.
Attacks that exploit this kind of access
Get autocomplete suggestions at a position. 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 getCompletions: 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.
getCompletions 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 getCompletions 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 getCompletions. 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.
getCompletions 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 →