search_apis
AI agents call search_apis to retrieve information from MCP-APIKit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool name 'search_apis' suggests querying or retrieving API information from the Eolink OpenAPI system. Although the tool description is empty, the sibling tools and server purpose (fetching API information) establish strong context that this is a read operation with no side effects. Confidence is moderated to 0.85 rather than higher due to the lack of explicit description.
From the tool's definition Tool is named 'search_apis' in a list of sibling tools that includes 'get_api', 'get_project', 'list_apis', and 'list_projects'.
Attacks that exploit this kind of access
search_apis. It is categorised as a Read tool in the MCP-APIKit MCP Server, which means it retrieves data without modifying state.
Register the MCP-APIKit 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-APIKit. 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-APIKit MCP server (scarqin/mcp-apikit). 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 →