api-mind
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SPECS_DIR | Yes | Absolute path to the directory containing .mind spec files. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| list_apisA | Lists all APIs loaded from the specs folder, with their names, titles, base URLs, and available environments. Use this when you need to know what APIs are loaded or what environments a specific API supports. Call this first when the user references an API you haven't seen yet. | ||||||||||||
| list_endpointsA | Lists all available endpoints across all loaded .mind files. Also surfaces the available environment names. Use this to discover what endpoints exist across all APIs. Filter by method, path, or section. Call this when the user references an API or asks what's available. | ||||||||||||
| get_endpoint_schemaA | Returns the full context for a specific endpoint including resolved URL, auth requirements, and schema. Use this to understand an endpoint before constructing a curl command to execute via the bash tool. Call this after list_endpoints to get the endpoint contract. Auth Patterns
NOTATION Legend
| ||||||||||||
| get_call_contextA | Returns the runtime context needed to execute API calls: resolved base URL, active environment, and default values for credentials and parameters. Call this before constructing a curl command when the user wants to actually invoke an endpoint. Do NOT call this just to browse or understand the API shape — use list_endpoints and get_endpoint_schema for that. Reads from ~/.config/api-mind/.env and ~/.config/api-mind//.env. Defaults to "dev" unless the user specifies otherwise. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a distinct purpose: list_apis for API overview, list_endpoints for endpoint discovery, get_endpoint_schema for endpoint contract details, and get_call_context for runtime execution details. The descriptions explicitly clarify when to use each, preventing overlap.
All tool names follow a consistent verb_noun pattern (list_* and get_*), with verbs clearly indicating read-only discovery actions. The naming is predictable and uniform.
Four tools is well-scoped for a server focused on API discovery and context provision. Each tool covers a necessary step in the workflow from discovering APIs to preparing API calls, without redundancy.
The tool surface covers the full lifecycle of API exploration: discovering APIs, discovering endpoints, understanding schema/auth, and obtaining runtime context for actual calls. There are no obvious gaps for the server's stated purpose.