Find feeds at a specific hostname or URL fragment. Use this when the user already knows the site (e.g.
AI agents call search_feeds_by_url to retrieve information from Feedbagel MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or discovers feed metadata by URL/hostname pattern matching. It has no capacity to modify, delete, execute code, or move money. It is a classic Read operation: a search that returns information without side effects. Severity is low because misuse (e.g., querying many hostnames) poses minimal risk compared to write or destructive operations.
From the tool's definition Tool name 'search_feeds_by_url' and description 'Find feeds at a specific hostname or URL fragment' indicate a query/search operation.
Attacks that exploit this kind of access
Find feeds at a specific hostname or URL fragment. Use this when the user already knows the site (e.g. It is categorised as a Read tool in the Feedbagel MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Feedbagel MCP Server MCP server in PolicyLayer and add a rule for search_feeds_by_url: 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 Feedbagel MCP Server. Nothing to install.
search_feeds_by_url 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_feeds_by_url 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_feeds_by_url. 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_feeds_by_url is provided by the Feedbagel MCP Server MCP server (prototypr/feedbagel-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 →