qdrant-codebase-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP health/metrics port | 3000 |
| REPO_ID | No | Logical repo name shown in MCP tools | |
| MIN_SCORE | No | Minimum similarity score for search results (0-1) | 0.78 |
| ROOT_PATH | No | Repository root to index (index-and-watch only) | process.cwd() |
| QDRANT_URL | No | Qdrant server URL | http://localhost:6333 |
| CONFIG_PATH | No | Path to a config.yml for multi-repo setups | |
| SERVER_MODE | No | Server mode: index-and-watch or search-only | index-and-watch |
| QDRANT_API_KEY | No | Qdrant API key (required for Qdrant Cloud) | |
| CHUNK_MAX_LINES | No | Max lines per code chunk | 150 |
| COLLECTION_NAME | No | Qdrant collection name; required in search-only | |
| EMBEDDING_MODEL | No | Embedding model name | fast-bge-small-en-v1.5 |
| EMBEDDING_API_KEY | No | OpenAI-compatible embeddings API key | |
| EMBEDDING_BASE_URL | No | OpenAI-compatible embeddings base URL | |
| EMBEDDING_PROVIDER | No | Embedding provider: fastembed or openai-compatible | fastembed |
| CHUNK_OVERLAP_LINES | No | Overlap between adjacent chunks | 20 |
| MAX_FILE_SIZE_BYTES | No | Files larger than this are skipped | 1000000 |
| WATCHER_DEBOUNCE_MS | No | Quiet period after a save before re-indexing | 2000 |
| EMBEDDING_BATCH_SIZE | No | Chunks per embedding batch | 64 |
| EMBEDDING_DIMENSIONS | No | Optional explicit embedding vector size | |
| EMBEDDING_HEADERS_JSON | No | Optional JSON object of extra embedding headers |
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/theepicsaxguy/qdrant-codebase-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server