Full-text search across entry titles and content.
AI agents call search_entries_tool to retrieve information from MCP Feed Reader without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that searches and retrieves feed entries. It does not create, modify, delete, or execute any operations. Full-text search is inherently a retrieval function with no blast radius if misused by an AI agent—the worst outcome is returning unwanted search results.
From the tool's definition Tool description states 'Full-text search across entry titles and content' with no modification, deletion, or execution capability. The tool only queries and retrieves data without side effects.
Attacks that exploit this kind of access
Full-text search across entry titles and content. It is categorised as a Read tool in the MCP Feed Reader MCP Server, which means it retrieves data without modifying state.
Register the MCP Feed Reader MCP server in PolicyLayer and add a rule for search_entries_tool: 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 Feed Reader. Nothing to install.
search_entries_tool 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_entries_tool 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_entries_tool. 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_entries_tool is provided by the MCP Feed Reader MCP server (pypi:mcp-feed-reader-crunchtools). 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 →