Search post contents on-demand for the query and return matches with snippets.
AI agents call search_full_text to retrieve information from Blog RSS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs full-text search across blog post content and returns matching results. It is a query operation that retrieves data without creating, modifying, deleting, or executing any side effects. The worst-case misuse would be information disclosure of already-public blog content, which is inherently low-risk.
From the tool's definition Tool description states 'Search post contents' and 'return matches with snippets' - pure retrieval operations with no modification or deletion.
Attacks that exploit this kind of access
Search post contents on-demand for the query and return matches with snippets. It is categorised as a Read tool in the Blog RSS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Blog RSS MCP Server MCP server in PolicyLayer and add a rule for search_full_text: 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 Blog RSS MCP Server. Nothing to install.
search_full_text 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_full_text 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_full_text. 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_full_text is provided by the Blog RSS MCP Server MCP server (s1r15h/blog-mcp-server). 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 →