kin-mcp
by wandercom
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KIN_PROFILE | No | Selects the named profile (mapping to a separate data directory) that the MCP server binds to at process start. Resolution order after the --profile flag: KIN_PROFILE, the project's .kin/config `profile:` key, longest-prefix match against profile roots, default_profile, then the legacy single graph. Restart the MCP server to switch profiles. | |
| KIN_PROJECT | No | Alternative to KIN_PROJECT_PATH for specifying the project root used for project config and store selection. | |
| KIN_AGENT_ID | No | Agent identity used for coordination, locks, task claims, cursors and message targeting. Overrides `agent_id` in config; defaults to user@shorthost. | |
| GEMINI_API_KEY | No | Default API key environment variable for the Gemini embedding provider. Only needed when that provider is configured. | |
| OPENAI_API_KEY | No | Default API key environment variable for the OpenAI embedding provider (and for the OpenAI LLM provider when selected). Only needed when that provider is configured. | |
| VOYAGE_API_KEY | No | Default API key environment variable for the Voyage embedding provider (default embedding provider). Only needed when embeddings are used. | |
| KIN_PROJECT_PATH | No | Path to the project root used for project config/store resolution when running from outside the repo. Resolved after --project-path and before KIN_PROJECT, the git worktree root, and the current directory. | |
| ANTHROPIC_API_KEY | No | API key for the Anthropic LLM provider, read via `llm.api_key_env` (comma-separated fallback allowed). Only needed if LLM-backed features such as extraction, `ask`, or Dream deep mode are enabled. |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityActive
ResponsivenessUsually handled