Get latest market news from Finnhub
AI agents call get_market_news to retrieve information from MCP Finnhub Server 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 market news data without creating, modifying, deleting, or executing operations. The blast radius of misuse is minimal—an AI agent could fetch unwanted news, but cannot alter market data, execute trades, or cause financial harm. No irreversible actions or code execution are possible.
From the tool's definition Tool name 'get_market_news' and description 'Get latest market news from Finnhub' indicates data retrieval with no side effects. Sibling tools (get_stock_quote, get_company_profile, get_earnings_calendar, etc.) are all read-only queries against financial data.
Attacks that exploit this kind of access
Get latest market news from Finnhub. It is categorised as a Read tool in the MCP Finnhub Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Finnhub Server MCP server in PolicyLayer and add a rule for get_market_news: 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 Finnhub Server. Nothing to install.
get_market_news 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 get_market_news 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 get_market_news. 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.
get_market_news is provided by the MCP Finnhub Server MCP server (nimblebraininc/mcp-finnhub). 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 →