ControlAPI-MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BASE_URL | No | The base URL of the API server (optional, e.g., http://your-api.com) | |
| OPENAPI_URL | No | The URL of the OpenAPI specification (e.g., http://your-api.com/openapi.json) | |
| SERVER_NICKNAME | No | A nickname for the server (optional) | |
| REFRESH_INTERVAL | No | Interval in seconds for refreshing the schema (optional, default is 300) |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_endpointsA | List API endpoints. Returns compact one-liners default (saves tokens). Use compact=false for full details. Supports pagination with limit/offset. |
| execute_requestA | Execute HTTP requests to API endpoints. Returns compact response by default (no headers, no server_context). Use include_headers/include_server_context for full details. Full unfiltered response is always cached — use replay_response to re-inspect without re-executing. PREFERRED: If you know or can predict the response structure, always pass a jsonpath param to extract only the needed fields — this saves tokens and avoids re-execution. e.g. jsonpath='$.data.access_token' to get a token, '$.results' for a list. Root $ = response body directly. |
| replay_responseA | Re-inspect a cached API response WITHOUT re-executing the request. Critical for POST/PUT/DELETE — avoids duplicate side effects. Supports JSONPath to drill into specific fields. Use index=-1 for latest (default), or negative index for older responses. |
| set_variableA | Store values (like auth tokens) for reuse in requests via {{varname}} syntax |
| get_variablesA | Get all stored variables |
| search_schemaA | Search endpoints by query (multiple words = OR match). Returns compact one-liners by default. Supports pagination with limit/offset. |
| reload_schemaB | Reload OpenAPI schema to get latest endpoints |
| get_endpoint_detailsA | Get detailed schema for a specific endpoint. Returns compact field:type summary by default. Use compact=false for raw OpenAPI schema. Use sections to request only specific parts. |
| get_server_infoA | Get current server configuration and status. Returns debug_ui_url — if the user asks to open the debug monitor, fetch this then open that URL in their browser. |
| set_server_configA | Connect to an OpenAPI server. If no server is configured yet, use this tool first to set the OpenAPI URL. Switches between different API servers dynamically. |
| get_server_historyA | View recent server switches with timestamps and last operations |
| health_checkA | Test connectivity to current OpenAPI server |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/fellowabhi/ControlAPI-openapi-to-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server