Search articles by keyword in title or body.
AI agents call search_artigos to retrieve information from Philosophy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs keyword search across a philosophical corpus, returning matching articles. It has no side effects, does not modify data, execute commands, or commit financial transactions. It is a straightforward Read operation with minimal blast radius if misused (e.g., excessive searches would at worst be a resource consumption issue, not a security breach).
From the tool's definition Tool description states 'Search articles by keyword in title or body' — a pure retrieval operation with no modification, deletion, or execution of external code.
Attacks that exploit this kind of access
Search articles by keyword in title or body. It is categorised as a Read tool in the Philosophy MCP Server, which means it retrieves data without modifying state.
Register the Philosophy MCP server in PolicyLayer and add a rule for search_artigos: 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 Philosophy. Nothing to install.
search_artigos 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_artigos 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_artigos. 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_artigos is provided by the Philosophy MCP server (s3b4hjr/philosophy-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 →