WATCHER: get a signed callback when a new news article is published about a US company. Arm once, pay once. Pass ticker; optionally keyword to only fire on headlines containing it. Fires once per new article (deduped by id); bounded by maxFires/expiry. Existing articles at arm time are baselined....
AI agents call watchers.company-news 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 queries and retrieves publicly available company news data. While it establishes a watcher/subscription mechanism, it does not create, modify, delete, or execute code. The payment model (pay-per-call in USDC) is a billing mechanism, not a financial operation that moves money on behalf of the user or commits financial obligations beyond the subscription itself.
From the tool's definition Tool retrieves news articles about companies via Finnhub API and sets up callbacks when new articles are published.
Attacks that exploit this kind of access
WATCHER: get a signed callback when a new news article is published about a US company. Arm once, pay once. Pass ticker; optionally keyword to only fire on headlines containing it. Fires once per new article (deduped by id); bounded by maxFires/expiry. Existing articles at arm time are baselined. News via Finnhub. Signed (verify offline) + retried; recoverable via watchers.status. Returns a watche. 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 watchers.company-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. Nothing to install.
watchers.company-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 watchers.company-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 watchers.company-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.
watchers.company-news 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 →