Skip to main content
Glama
theepicsaxguy

qdrant-codebase-mcp

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
PORTNoHTTP health/metrics port3000
REPO_IDNoLogical repo name shown in MCP tools
MIN_SCORENoMinimum similarity score for search results (0-1)0.78
ROOT_PATHNoRepository root to index (index-and-watch only)process.cwd()
QDRANT_URLNoQdrant server URLhttp://localhost:6333
CONFIG_PATHNoPath to a config.yml for multi-repo setups
SERVER_MODENoServer mode: index-and-watch or search-onlyindex-and-watch
QDRANT_API_KEYNoQdrant API key (required for Qdrant Cloud)
CHUNK_MAX_LINESNoMax lines per code chunk150
COLLECTION_NAMENoQdrant collection name; required in search-only
EMBEDDING_MODELNoEmbedding model namefast-bge-small-en-v1.5
EMBEDDING_API_KEYNoOpenAI-compatible embeddings API key
EMBEDDING_BASE_URLNoOpenAI-compatible embeddings base URL
EMBEDDING_PROVIDERNoEmbedding provider: fastembed or openai-compatiblefastembed
CHUNK_OVERLAP_LINESNoOverlap between adjacent chunks20
MAX_FILE_SIZE_BYTESNoFiles larger than this are skipped1000000
WATCHER_DEBOUNCE_MSNoQuiet period after a save before re-indexing2000
EMBEDDING_BATCH_SIZENoChunks per embedding batch64
EMBEDDING_DIMENSIONSNoOptional explicit embedding vector size
EMBEDDING_HEADERS_JSONNoOptional JSON object of extra embedding headers

Capabilities

Server capabilities have not been inspected yet.

Tools

Functions exposed to the LLM to take actions

NameDescription

No tools

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

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