list_apis
AI agents call list_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 retrieves and lists available APIs from the Eolink OpenAPI catalog. This is a read-only operation with no side effects—it queries existing data for display purposes. No data is created, modified, deleted, or executed. Confidence is slightly reduced because the description is empty, but the tool name and server context strongly indicate a read operation consistent with similar tools on the same server.
From the tool's definition Tool name 'list_apis' indicates a listing/retrieval operation. The server description emphasizes 'fetching API information' and the sibling tools ('get_api', 'get_project', 'list_projects', 'search_apis') are all read-only information retrieval operations,…
Attacks that exploit this kind of access
list_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 list_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.
list_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 list_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 list_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.
list_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 →