Analyst recommendation trend for a US-listed company — the number of analysts rating it strong buy, buy, hold, sell, and strong sell, snapshotted per month (newest first). Pass ticker. Use it to see the consensus and how sentiment is shifting over time. Data by Finnhub.
AI agents call stocks.recommendations 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 tool retrieves and queries historical analyst sentiment data without side effects. It provides information for decision-making but does not execute trades, transfer funds, or modify data. The underlying server facilitates financial transactions (USDC payments via x402), but this specific tool is purely a Read operation that fetches market intelligence snapshots from Finnhub.
From the tool's definition Tool description states it retrieves 'analyst recommendation trend' and 'snapshotted per month' data for a given ticker. The verb 'see' indicates querying/viewing existing data.
Attacks that exploit this kind of access
Analyst recommendation trend for a US-listed company — the number of analysts rating it strong buy, buy, hold, sell, and strong sell, snapshotted per month (newest first). Pass ticker. Use it to see the consensus and how sentiment is shifting over time. Data by Finnhub. 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.recommendations: 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.recommendations 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.recommendations 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.recommendations. 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.recommendations 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 →