Semantic code search built for AI agents. Hybrid, AST-aware, context for 166 languages.
com.knitli/codeweaver
https://github.com/knitli/codeweaver
STDIO
No auth required
How models use it and what it is built for.
Semantic code search built for AI agents. Hybrid, AST-aware, context for 166 languages.
Hosted endpoint — paste into any MCP client.
Configuration this server reads at startup.
Specify a custom config file path for CodeWeaver. Only needed if not using the default locations.
Enable debug mode for CodeWeaver.
Specify the API key for the embedding provider, if required. Note: {', '.join([p for p in _providers_for_kind('embedding') if p.])}
Specify the embedding model to use.
Specify the embedding provider to use.
Set the server host for CodeWeaver.
Set the log level for CodeWeaver (e.g., DEBUG, INFO, WARNING, ERROR).
Set the MCP server port for CodeWeaver if using http transport for mcp. Not required if using the default port (9328), or stdio transport.
Set the port for the codeweaver management server (information and management endpoints).
Use a premade provider settings profile for CodeWeaver.
Set the project name for CodeWeaver.
Set the project path for CodeWeaver.
Specify the API key for the reranking provider, if required.
Specify the reranking model to use.
Specify the reranking provider to use.
Specify the sparse embedding model to use.
Specify the sparse embedding provider to use.
Specify the API key for the vector store, if required.
Specify the port for the vector store.
Specify the vector store provider to use.
Specify the URL for the vector store.
Disable telemetry data collection.
Opt-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.
HTTP proxy for requests (Used by: Azure, Azure, Voyage)
API 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)
One of: 'debug', 'info', 'warning', 'error' (Used by: Azure, Cerebras, Deepseek, Fireworks, Github, Groq, Heroku, Moonshot, Ollama, Openai, Openrouter, Perplexity, Together, Vercel, X Ai)
Path to the SSL certificate file for requests (Used by: Azure, Azure, Voyage)
API key for Vercel service
AWS Account ID for Bedrock service
AWS region for Bedrock service
AWS Secret Access Key for Bedrock service
API key for Azure Cohere service (cohere models on Azure)
Endpoint for Azure Cohere service (cohere models on Azure)
Region for Azure Cohere service
API key for Azure OpenAI service (OpenAI models on Azure)
Endpoint for Azure OpenAI service (OpenAI models on Azure)
Region for Azure OpenAI service (OpenAI models on Azure)
Your Cohere API Key
Host URL for Cohere service
API key for DeepSeek service
Your Google Gemini API Key
Your Google API Key
Log level for Hugging Face Hub client
API key/token for Hugging Face service
HTTP proxy for requests
API key for Heroku service
Host URL for Heroku service
Your Mistral API Key
API 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.
One of: 'debug', 'info', 'warning', 'error'
Log level for Qdrant service
API key for Qdrant service
Enable TLS for Qdrant service, expects truthy or false value (e.g. 1 for on, 0 for off).
Hostname of the Qdrant service; do not use for URLs with schemes (e.g. 'http://')
Port number for the Qdrant service
Path to the TLS certificate file for Qdrant service. Only needed if using a self-signed certificate. If you're using qdrant-cloud, you don't need this.
Path to the SSL certificate file for requests
Your Tavily API Key
API key for Together service
OIDC token for Vercel service
API key for Voyage service
Specify a custom config file path for CodeWeaver. Only needed if not using the default locations.
Enable debug mode for CodeWeaver.
Specify the API key for the embedding provider, if required. Note: {', '.join([p for p in _providers_for_kind('embedding') if p.])}
Specify the embedding model to use.
Specify the embedding provider to use.
Set the server host for CodeWeaver.
Set the log level for CodeWeaver (e.g., DEBUG, INFO, WARNING, ERROR).
Set the MCP server port for CodeWeaver if using http transport for mcp. Not required if using the default port (9328), or stdio transport.
Set the port for the codeweaver management server (information and management endpoints).
Use a premade provider settings profile for CodeWeaver.
Set the project name for CodeWeaver.
Set the project path for CodeWeaver.
Specify the API key for the reranking provider, if required.
Specify the reranking model to use.
Specify the reranking provider to use.
Specify the sparse embedding model to use.
Specify the sparse embedding provider to use.
Specify the API key for the vector store, if required.
Specify the port for the vector store.
Specify the vector store provider to use.
Specify the URL for the vector store.
Disable telemetry data collection.
Opt-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.
HTTP proxy for requests (Used by: Azure, Azure, Voyage)
API 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)
One of: 'debug', 'info', 'warning', 'error' (Used by: Azure, Cerebras, Deepseek, Fireworks, Github, Groq, Heroku, Moonshot, Ollama, Openai, Openrouter, Perplexity, Together, Vercel, X Ai)
Path to the SSL certificate file for requests (Used by: Azure, Azure, Voyage)
API key for Vercel service
AWS Account ID for Bedrock service
AWS region for Bedrock service
AWS Secret Access Key for Bedrock service
API key for Azure Cohere service (cohere models on Azure)
Endpoint for Azure Cohere service (cohere models on Azure)
Region for Azure Cohere service
API key for Azure OpenAI service (OpenAI models on Azure)
Endpoint for Azure OpenAI service (OpenAI models on Azure)
Region for Azure OpenAI service (OpenAI models on Azure)
Your Cohere API Key
Host URL for Cohere service
API key for DeepSeek service
Your Google Gemini API Key
Your Google API Key
Log level for Hugging Face Hub client
API key/token for Hugging Face service
HTTP proxy for requests
API key for Heroku service
Host URL for Heroku service
Your Mistral API Key
API 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.
One of: 'debug', 'info', 'warning', 'error'
Log level for Qdrant service
API key for Qdrant service
Enable TLS for Qdrant service, expects truthy or false value (e.g. 1 for on, 0 for off).
Hostname of the Qdrant service; do not use for URLs with schemes (e.g. 'http://')
Port number for the Qdrant service
Path to the TLS certificate file for Qdrant service. Only needed if using a self-signed certificate. If you're using qdrant-cloud, you don't need this.
Path to the SSL certificate file for requests
Your Tavily API Key
API key for Together service
OIDC token for Vercel service
API key for Voyage service
Where to find authoritative docs and source for codeweaver.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 30+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioPublicData Oracle
Public data API with ML enrichment — SEC EDGAR, FRED, NOAA, EPA, USGS. 404 endpoints.
1stDibs
MCP server for browsing and searching items on 1stDibs marketplace.
mcp-v1
Sub-cent factual claim verification against live data sources.
ads
Manage Google, Meta, TikTok & LinkedIn ads. 91 tools for campaigns, analytics & optimization.