mcp-docs
by pgupta1795
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP server port | 5004 |
| DB_PATH | No | SQLite database path | ./data/mcp-docs.db |
| LOG_PATH | No | Optional log file path | |
| LOG_LEVEL | No | Log level: debug, info, warn, error | info |
| SEED_URLS | Yes | Documentation sources (format: name|url|navigationMode|recrawlIntervalHours) | |
| TRANSPORT | No | Transport mode: stdio or http | http |
| CACHE_SIZE | No | LRU cache size | 100 |
| SEARCH_MODE | No | Search mode: FTS_ONLY, SEMANTIC_ONLY, HYBRID | SEMANTIC_ONLY |
| INIT_ON_START | No | Auto-index on startup | true |
| SEMANTIC_TOP_K | No | Top K results for semantic search | 20 |
| CRAWL_MAX_DEPTH | No | Max crawl depth | 5 |
| CRAWL_MAX_PAGES | No | Max pages per source | 1000 |
| EMBEDDING_MODEL | No | Embedding model for semantic search | Xenova/all-MiniLM-L6-v2 |
| HYBRID_FTS_WEIGHT | No | FTS weight in hybrid mode (0-1) | 0.4 |
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 | |
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
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/pgupta1795/mcp-docs'
If you have feedback or need assistance with the MCP directory API, please join our Discord server