Qdrant MCP Server
by deveyus
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HTTP_PORT | No | Port for HTTP transport | 3000 |
| LOG_LEVEL | No | Logging level: fatal, error, warn, info, debug, trace, silent | info |
| QDRANT_URL | No | Qdrant server URL | http://localhost:6333 |
| GIT_TIMEOUT | No | Timeout for git commands in milliseconds | 300000 |
| COHERE_API_KEY | No | Cohere API key (required if using Cohere provider) | |
| GIT_BATCH_SIZE | No | Number of chunks to embed in one batch | 100 |
| OPENAI_API_KEY | No | OpenAI API key (required if using OpenAI provider) | |
| QDRANT_API_KEY | No | API key for Qdrant authentication (required for secured instances) | |
| TRANSPORT_MODE | No | Transport mode: 'stdio' or 'http' | stdio |
| VOYAGE_API_KEY | No | Voyage AI API key (required if using Voyage provider) | |
| CODE_BATCH_SIZE | No | Number of chunks to embed in one batch | 100 |
| CODE_CHUNK_SIZE | No | Maximum chunk size in characters for code vectorization | 2500 |
| CODE_ENABLE_AST | No | Enable AST-aware chunking (tree-sitter): 'true' or 'false' | true |
| EMBEDDING_MODEL | No | Embedding model name (provider-specific default) | |
| GIT_MAX_COMMITS | No | Maximum commits to index per run | 5000 |
| GIT_INCLUDE_DIFF | No | Include truncated diff in chunks: 'true' or 'false' | true |
| GIT_SEARCH_LIMIT | No | Default search result limit | 10 |
| GIT_ENABLE_HYBRID | No | Enable hybrid search with sparse vectors: 'true' or 'false' | true |
| GIT_INCLUDE_FILES | No | Include changed file list in chunks: 'true' or 'false' | true |
| GIT_MAX_DIFF_SIZE | No | Maximum diff size in bytes per commit | 5000 |
| CODE_CHUNK_OVERLAP | No | Overlap between chunks in characters | 300 |
| CODE_CUSTOM_IGNORE | No | Additional ignore patterns (comma-separated) | |
| CODE_DEFAULT_LIMIT | No | Default search result limit for code search | 5 |
| EMBEDDING_BASE_URL | No | Custom API URL for embedding provider | |
| EMBEDDING_PROVIDER | No | Embedding provider: 'ollama', 'openai', 'cohere', or 'voyage' | ollama |
| GIT_MAX_CHUNK_SIZE | No | Maximum characters per chunk | 3000 |
| PROMPTS_CONFIG_FILE | No | Path to prompts configuration JSON | prompts.json |
| EMBEDDING_RETRY_DELAY | No | Initial retry delay in milliseconds | 1000 |
| CODE_CUSTOM_EXTENSIONS | No | Additional file extensions (comma-separated) | |
| HTTP_REQUEST_TIMEOUT_MS | No | Request timeout for HTTP transport in milliseconds | 300000 |
| EMBEDDING_RETRY_ATTEMPTS | No | Retry count for embedding requests | 3 |
| GIT_BATCH_RETRY_ATTEMPTS | No | Retry attempts for failed batches | 3 |
| EMBEDDING_MAX_REQUESTS_PER_MINUTE | No | Rate limit for embedding requests per minute |
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 | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- 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/deveyus/qdrant-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server