Type-check inline TypeScript code without creating a file
AI agents invoke checkInlineCode to trigger actions in TypeScript LSP MCP. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes TypeScript type-checking on arbitrary inline code provided by the caller. While it doesn't persist files, it runs the TypeScript compiler/LSP on user-supplied code, which constitutes executing an external operation. The blast radius is medium since it processes arbitrary code through the TS compiler but doesn't write files or execute the code at runtime.
From the tool's definition Type-check inline TypeScript code without creating a file
Attacks that exploit this kind of access
Type-check inline TypeScript code without creating a file. It is categorised as a Execute tool in the TypeScript LSP MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the TypeScript LSP MCP server in PolicyLayer and add a rule for checkInlineCode: 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.
checkInlineCode is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the checkInlineCode 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 checkInlineCode. 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.
checkInlineCode 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 →