news_sources
AI agents call news_sources to retrieve information from Mcp Everything without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name and context indicate a query or list operation to retrieve information about news sources. No evidence of side effects, data modification, or external state changes. Classified as Read with medium-low confidence due to empty description, but the pattern of sibling tools and naming convention strongly suggests a data retrieval function.
From the tool's definition Tool name 'news_sources' suggests retrieving or listing available news sources; no action words implying modification, deletion, or execution. Sibling tools (arxiv_get_paper, books_search, country_info) are all Read operations.
Attacks that exploit this kind of access
news_sources. It is categorised as a Read tool in the Mcp Everything MCP Server, which means it retrieves data without modifying state.
Register the Mcp Everything MCP server in PolicyLayer and add a rule for news_sources: 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 Everything. Nothing to install.
news_sources 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_sources 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_sources. 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_sources is provided by the Mcp Everything MCP server (wellix260/mcp-everything). 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 →