Search recent news and compute bullish/bearish/neutral sentiment.
AI agents call news_sentiment to retrieve information from Financial Research Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes publicly available news data to derive sentiment metrics. It performs no writes, deletions, or financial operations. While the output may inform investment decisions, the tool itself only reads and processes information.
From the tool's definition Tool description states 'Search recent news and compute...sentiment' — a query and analysis operation with no data modification, deletion, or financial transaction capability. The verb 'search' and 'compute' indicate retrieval and processing of external data.
Attacks that exploit this kind of access
Search recent news and compute bullish/bearish/neutral sentiment. It is categorised as a Read tool in the Financial Research Agent MCP Server, which means it retrieves data without modifying state.
Register the Financial Research Agent MCP server in PolicyLayer and add a rule for news_sentiment: 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 Financial Research Agent. Nothing to install.
news_sentiment 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 news_sentiment 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 news_sentiment. 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.
news_sentiment is provided by the Financial Research Agent MCP server (rahul-jajala/ai-financial-research-agent). 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 →