Skip to main content
Glama
catlog22

codexlens

by catlog22

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CODEXLENS_TOP_KNoSearch result limit10
CODEXLENS_DEVICENoDevice (auto/cuda/directml/cpu)auto
CODEXLENS_FUSION_KNoRRF fusion k parameter60
CODEXLENS_ANN_TOP_KNoANN fine search candidates50
CODEXLENS_EMBED_DIMNoVector dimension (must match model)384
CODEXLENS_FTS_TOP_KNoFTS results per method50
CODEXLENS_HF_MIRRORNoHuggingFace mirror (e.g. https://hf-mirror.com)
CODEXLENS_AUTO_WATCHNoAuto-start file watcher after indexingfalse
CODEXLENS_ANN_BACKENDNoANN backend (auto/usearch/faiss/hnswlib)auto
CODEXLENS_EMBED_MODELNoLocal fastembed model nameBAAI/bge-small-en-v1.5
CODEXLENS_AST_CHUNKINGNoEnable AST chunking + symbol extractiontrue
CODEXLENS_BINARY_TOP_KNoBinary coarse search candidates200
CODEXLENS_EMBED_API_KEYNoAPI key for embedding API
CODEXLENS_EMBED_API_URLNoAPI base URL for embedding (overrides local model)
CODEXLENS_INDEX_WORKERSNoParallel indexing workers2
CODEXLENS_MAX_FILE_SIZENoMax file size in bytes1000000
CODEXLENS_RERANKER_TOP_KNoResults to rerank20
CODEXLENS_EMBED_API_MODELNoModel name for embedding API
CODEXLENS_MODEL_CACHE_DIRNoModel download cache directory
CODEXLENS_EMBED_BATCH_SIZENoTexts per API batch32
CODEXLENS_EMBED_MAX_TOKENSNoMax tokens per text (0=no limit)8192
CODEXLENS_FIND_MAX_RESULTSNofind_files result limit100
CODEXLENS_LLM_EXPAND_MODELNoModel name for LLM query expansionglm-5-turbo
CODEXLENS_RERANKER_API_KEYNoAPI key for reranker
CODEXLENS_RERANKER_API_URLNoReranker API base URL
CODEXLENS_EXPANSION_ENABLEDNoTwo-hop query expansion for NL queriestrue
CODEXLENS_LLM_EXPAND_API_KEYNoAPI key for LLM query expansion
CODEXLENS_LLM_EXPAND_ENABLEDNoEnable LLM expansion globally for search_filesfalse
CODEXLENS_RERANKER_API_MODELNoModel name for reranker
CODEXLENS_EMBED_API_ENDPOINTSNoMulti-endpoint: url|key|model,...
CODEXLENS_GITIGNORE_FILTERINGNoRecursive .gitignore filteringtrue
CODEXLENS_LLM_EXPAND_API_BASENoAPI base URL for LLM query expansionhttps://open.bigmodel.cn/api/paas/v4/

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/catlog22/codexlens-search'

If you have feedback or need assistance with the MCP directory API, please join our Discord server