search-everything
AI agents call search-everything to retrieve information from NewsDigest MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, the tool name 'search-everything' in the context of a news aggregation server almost certainly performs a query or search operation against NewsAPI.org. This retrieves data with no side effects. The confidence is moderate (0.85) rather than high due to the missing description, but the server's stated purpose and naming convention strongly indicate a Read operation.
From the tool's definition Tool name 'search-everything' combined with server description indicating the MCP fetches and searches news articles from NewsAPI.org. The sibling tools (format-news-markdown, get-news-digest) and server purpose confirm this is a search/query operation.
Attacks that exploit this kind of access
search-everything. It is categorised as a Read tool in the NewsDigest MCP MCP Server, which means it retrieves data without modifying state.
Register the NewsDigest MCP server in PolicyLayer and add a rule for search-everything: 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 NewsDigest MCP. Nothing to install.
search-everything 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 search-everything 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 search-everything. 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.
search-everything is provided by the NewsDigest MCP server (someilam/news-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 →