com.knitli/codeweaver

com.knitli/codeweaver

Semantic code search built for AI agents. Hybrid, AST-aware, context for 166 languages.

View repository →Homepage →

Connect this server

Add this to your MCP client config — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor).Suits: Claude Desktop · Cursor.

{
  "mcpServers": {
    "codeweaver": {
      "command": "uvx",
      "args": [
        "code-weaver"
      ],
      "env": {
        "CODEWEAVER_DEBUG": "false",
        "CODEWEAVER_EMBEDDING_API_KEY": "<your CODEWEAVER_EMBEDDING_API_KEY>",
        "CODEWEAVER_EMBEDDING_MODEL": "voyage-code-3",
        "CODEWEAVER_EMBEDDING_PROVIDER": "voyage",
        "CODEWEAVER_HOST": "localhost",
        "CODEWEAVER_LOG_LEVEL": "WARNING",
        "CODEWEAVER_MCP_PORT": "9328",
        "CODEWEAVER_PORT": "9329",
        "CODEWEAVER_RERANKING_API_KEY": "<your CODEWEAVER_RERANKING_API_KEY>",
        "CODEWEAVER_RERANKING_MODEL": "rerank-2.5",
        "CODEWEAVER_RERANKING_PROVIDER": "voyage",
        "CODEWEAVER_SPARSE_EMBEDDING_MODEL": "prithivida/Splade_pp_en_v1",
        "CODEWEAVER_SPARSE_EMBEDDING_PROVIDER": "fastembed",
        "CODEWEAVER_VECTOR_STORE_API_KEY": "<your CODEWEAVER_VECTOR_STORE_API_KEY>",
        "CODEWEAVER_VECTOR_STORE_PORT": "6333",
        "CODEWEAVER_VECTOR_STORE_PROVIDER": "qdrant",
        "CODEWEAVER_VECTOR_STORE_URL": "http://localhost",
        "CODEWEAVER__TELEMETRY__DISABLE_TELEMETRY": "false",
        "CODEWEAVER__TELEMETRY__TOOLS_OVER_PRIVACY": "false",
        "OPENAI_API_KEY": "<your OPENAI_API_KEY>",
        "AI_GATEWAY_API_KEY": "<your AI_GATEWAY_API_KEY>",
        "AWS_SECRET_ACCESS_KEY": "<your AWS_SECRET_ACCESS_KEY>",
        "AZURE_COHERE_API_KEY": "<your AZURE_COHERE_API_KEY>",
        "AZURE_OPENAI_API_KEY": "<your AZURE_OPENAI_API_KEY>",
        "DEEPSEEK_API_KEY": "<your DEEPSEEK_API_KEY>",
        "INFERENCE_KEY": "<your INFERENCE_KEY>",
        "QDRANT__SERVICE__API_KEY": "<your QDRANT__SERVICE__API_KEY>",
        "TOGETHER_API_KEY": "<your TOGETHER_API_KEY>",
        "VERCEL_OIDC_TOKEN": "<your VERCEL_OIDC_TOKEN>",
        "VOYAGE_API_KEY": "<your VOYAGE_API_KEY>"
      }
    }
  }
}
Environment variables
  • CODEWEAVER_DEBUGEnable debug mode for CodeWeaver.
  • CODEWEAVER_EMBEDDING_API_KEYsecretSpecify the API key for the embedding provider, if required. Note: {', '.join([p for p in _providers_for_kind('embedding') if p.])}
  • CODEWEAVER_EMBEDDING_MODELSpecify the embedding model to use.
  • CODEWEAVER_EMBEDDING_PROVIDERSpecify the embedding provider to use.
  • CODEWEAVER_HOSTSet the server host for CodeWeaver.
  • CODEWEAVER_LOG_LEVELSet the log level for CodeWeaver (e.g., DEBUG, INFO, WARNING, ERROR).
  • CODEWEAVER_MCP_PORTSet the MCP server port for CodeWeaver if using http transport for mcp. Not required if using the default port (9328), or stdio transport.
  • CODEWEAVER_PORTSet the port for the codeweaver management server (information and management endpoints).
  • CODEWEAVER_RERANKING_API_KEYsecretSpecify the API key for the reranking provider, if required.
  • CODEWEAVER_RERANKING_MODELSpecify the reranking model to use.
  • CODEWEAVER_RERANKING_PROVIDERSpecify the reranking provider to use.
  • CODEWEAVER_SPARSE_EMBEDDING_MODELSpecify the sparse embedding model to use.
  • CODEWEAVER_SPARSE_EMBEDDING_PROVIDERSpecify the sparse embedding provider to use.
  • CODEWEAVER_VECTOR_STORE_API_KEYsecretSpecify the API key for the vector store, if required.
  • CODEWEAVER_VECTOR_STORE_PORTSpecify the port for the vector store.
  • CODEWEAVER_VECTOR_STORE_PROVIDERSpecify the vector store provider to use.
  • CODEWEAVER_VECTOR_STORE_URLSpecify the URL for the vector store.
  • CODEWEAVER__TELEMETRY__DISABLE_TELEMETRYDisable telemetry data collection.
  • CODEWEAVER__TELEMETRY__TOOLS_OVER_PRIVACYOpt-in to potentially identifying collection of query and search result data. This is invaluable for helping us improve CodeWeaver's search capabilities. If privacy is a higher priority, do not enable this setting.
  • OPENAI_API_KEYsecretAPI key for OpenAI-compatible services (not necessarily an API key *for* OpenAI). The OpenAI client also requires an API key, even if you don't actually need one for your provider (like local Ollama). So provide a dummy key if needed. (Used by: Azure, Cerebras, Deepseek, Fireworks, Github, Groq, Heroku, Moonshot, Ollama, Openai, Openrouter, Perplexity, Together, Vercel, X Ai)
  • AI_GATEWAY_API_KEYsecretAPI key for Vercel service
  • AWS_SECRET_ACCESS_KEYsecretAWS Secret Access Key for Bedrock service
  • AZURE_COHERE_API_KEYsecretAPI key for Azure Cohere service (cohere models on Azure)
  • AZURE_OPENAI_API_KEYsecretAPI key for Azure OpenAI service (OpenAI models on Azure)
  • DEEPSEEK_API_KEYsecretAPI key for DeepSeek service
  • INFERENCE_KEYsecretAPI key for Heroku service
  • OPENAI_API_KEYsecretAPI key for OpenAI-compatible services (not necessarily an API key *for* OpenAI). The OpenAI client also requires an API key, even if you don't actually need one for your provider (like local Ollama). So provide a dummy key if needed.
  • QDRANT__SERVICE__API_KEYsecretAPI key for Qdrant service
  • TOGETHER_API_KEYsecretAPI key for Together service
  • VERCEL_OIDC_TOKENsecretOIDC token for Vercel service
  • VOYAGE_API_KEYsecretAPI key for Voyage service

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
AI & ML
Version
0.1.0-alpha.3
Registry
active
Published
12/3/2025

More AI & ML servers

Browse all AI & ML →

Knowa

sonal-sithara

Team docs served to AI agents over MCP - search, Markdown reads, version pinning, read audit.

AI & MLAdded 3 months ago

Knowledge for Agents

com.knowledgeforagents

Search real problems, solutions, failed approaches and observed outcomes shared by AI agents.

AI & MLAdded 2 months ago

KnownGate

FocusedCreativity

Food verification for people and AI agents: evidence-backed verdicts, with sources and dates.

AI & MLAdded 2 months ago

Kompressr

kompressrcdn

Upload, optimize and manage files, wait for processing, and generate private delivery links.

AI & MLAdded 2 weeks ago

Kordi — Subscription Intelligence

kordi-labs

Track, analyze, and act on your streaming and SaaS subscriptions from any AI agent.

AI & MLAdded 5 months ago

Kova

kovatools

Saves a declared investment strategy so any agent can check a portfolio against it.

AI & MLAdded 4 weeks ago

Add the badge to your site

Show visitors that com.knitli/codeweaver is listed here — it’s also the link we check for a free listing.

com.knitli/codeweaver — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/com-knitli-codeweaver?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="com.knitli/codeweaver — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![com.knitli/codeweaver — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/com-knitli-codeweaver?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.