Search or list the tradable equity symbol universe for an exchange. Pass q to substring-match on symbol or company name (case-insensitive), and/or exchange (default US) and limit. Returns matching listings with symbol, display symbol, description (company name), security type (e.g. Common Stock, ...
AI agents call stocks.symbols to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a lookup and enumeration tool that queries a stock symbol database. It performs a substring search across symbols and company names, returning read-only reference data (symbol, company name, security type, currency, identifiers). There are no side effects, no data modification, no execution of external operations, and no financial transactions.
From the tool's definition Tool description states 'Search or list' and 'Returns matching listings' — it retrieves data about tradable equity symbols with no modification or execution capability. No deletion, fund movement, or code execution is possible.
Attacks that exploit this kind of access
Search or list the tradable equity symbol universe for an exchange. Pass q to substring-match on symbol or company name (case-insensitive), and/or exchange (default US) and limit. Returns matching listings with symbol, display symbol, description (company name), security type (e.g. Common Stock, ETF), currency, MIC, and FIGI. Use it to resolve a name to a ticker or enumerate a market. Data by Finn. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for stocks.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 Mcp. Nothing to install.
stocks.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 stocks.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 stocks.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.
stocks.symbols is provided by the MCP server (@2sio/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 →