AI agents call molmcp_search_symbols to retrieve information from Molmcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool searches an indexed symbol database to help LLM agents discover available code symbols and their metadata. It performs read-only queries against pre-indexed code information with no side effects, data modification, or execution capability. The lack of description slightly lowers confidence, but the context strongly indicates a search/query function typical of Read category tools.
From the tool's definition Tool name 'molmcp_search_symbols' combined with server description indicating 'indexed code symbols, signatures, and relationships' and sibling tools like 'get_command_doc', 'get_doc_index', 'get_howto' all suggest query/search operations.
Attacks that exploit this kind of access
molmcp_search_symbols. It is categorised as a Read tool in the Molmcp MCP Server, which means it retrieves data without modifying state.
Register the Mol MCP server in PolicyLayer and add a rule for molmcp_search_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 Molmcp. Nothing to install.
molmcp_search_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 molmcp_search_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 molmcp_search_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.
molmcp_search_symbols is provided by the Mol MCP server (molcrafts/molmcp). 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 →