Search for symbols in indexed external libraries (node_modules). Requires running index_external_libraries first.
AI agents call search_external_library_symbols to retrieve information from TypeScript MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a search/query operation over pre-indexed library symbols, returning information about external dependencies. It has no side effects, cannot modify code, execute operations, or delete data. It is purely a retrieval function operating on static indexed data, making it a straightforward Read category tool with low severity.
From the tool's definition Tool description states it 'Search[es] for symbols in indexed external libraries' with no write, delete, or execute capabilities mentioned. It queries existing indexed data.
Documented attack patterns abuse exactly the kind of access search_external_library_symbols gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and TypeScript MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for search_external_library_symbols:
{
"version": "1",
"default": "deny",
"tools": {
"search_external_library_symbols": {}
}
}search_external_library_symbols is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Search for symbols in indexed external libraries (node_modules). Requires running index_external_libraries first. It is categorised as a Read tool in the TypeScript MCP MCP Server, which means it retrieves data without modifying state.
Register the TypeScript MCP server in PolicyLayer and add a rule for search_external_library_symbols: 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 MCP. Nothing to install.
search_external_library_symbols 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 search_external_library_symbols 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 search_external_library_symbols. 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.
search_external_library_symbols is provided by the TypeScript MCP server (mizchi/lsmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from TypeScript MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
3 TypeScript MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.