MCP Documentation Server
by andrea9293
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WEB_HOST | No | Bind address for the web UI (use 0.0.0.0 to expose on all interfaces) | 127.0.0.1 |
| WEB_PORT | No | Port for the web UI | 3080 |
| MCP_BASE_DIR | No | Base directory for data storage | ~/.mcp-documentation-server |
| START_WEB_UI | No | Set to false to disable the built-in web interface | true |
| GEMINI_API_KEY | No | Google Gemini API key (enables search_documents_with_ai) | |
| MCP_CACHE_ENABLED | No | Enable/disable LRU embedding cache | true |
| MCP_EMBEDDING_MODEL | No | Embedding model name | Xenova/all-MiniLM-L6-v2 |
| MCP_STREAMING_ENABLED | No | Enable streaming reads for large files | true |
| MCP_STREAM_CHUNK_SIZE | No | Streaming buffer size in bytes (64KB) | 65536 |
| MCP_STREAM_FILE_SIZE_LIMIT | No | Threshold to switch to streaming (10MB) | 10485760 |
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
ActivityMaintained
ResponsivenessWithin a week