Search the public-apis list by keyword, category, auth type, and HTTPS support.
AI agents call search_apis to retrieve information from Mcp Public Apis without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and filters information from a public APIs dataset without creating, modifying, deleting, or executing code. It is purely a search/query operation with no reversible or irreversible mutations, no code execution, and no financial impact. The low severity reflects minimal risk even if misused by an AI agent—the worst outcome would be retrieving irrelevant API information.
From the tool's definition Tool description states 'Search the public-apis list' with filtering parameters (keyword, category, auth type, HTTPS support). The verb 'search' and the read-only nature of querying a dataset indicate no data modification or side effects.
Attacks that exploit this kind of access
Search the public-apis list by keyword, category, auth type, and HTTPS support. It is categorised as a Read tool in the Mcp Public Apis MCP Server, which means it retrieves data without modifying state.
Register the Mcp Public Apis MCP server in PolicyLayer and add a rule for search_apis: 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 Public Apis. Nothing to install.
search_apis 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_apis 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_apis. 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_apis is provided by the Mcp Public Apis MCP server (josephsenior/pblic-apis-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 →