← Index

com.knitli/codeweaver

com.knitli/codeweaverv0.1.0-alpha.3Search

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

In-path gate · all MCP tools

Using com.knitli/codeweaver in Claude, Cursor, Gemini CLI, Cline, or Zed?

MCP tool contracts can change remotely with no version bump. The mcpindex gate pins each contract and HOLDs the call when it drifts-before your agent acts. Zero credentials. This is not the package install for this server itself (use Install this server for that).

Install the mcpindex gate (one command)

Rewrites your MCP host config so each server launches behind the gate. Inspect first: curl -fsSL https://mcpindex.ai/install.sh | less

uv tool install mcpindex-gate && mcpindex-config-wire
Trust verdict · v1 advisory · method
REVIEWstatus: PARTIALfresh until 2026-08-04 05:05 UTC
screened 2026-07-05tier: scannedgranularity: description-levelsource: registry

Semantic screen found no manipulation pattern in the description. Conformance probe not yet run.

mcpindex.integrity.descriptionpassINFO

evidenceNo malicious instructions foundvia static_description

Limits of this verdict
  • - Semantic screen only - the deterministic conformance probe has not run on this server
  • - Confidence is reported but not yet calibrated (v1)
  • - Screen reads the tool description, not the live behavior
  • - advisory
  • - registry description only no input schema
  • - screen model 8b

Semantic screen: an LLM judge reads the tool description for hidden instructions (status PARTIAL). A pass means the description is not lying, not that the tool is safe: a high-capability tool with an honest description still warrants caution. The deterministic conformance probe has not been run on this server yet, so the screen here is semantic-only. Posture: advisory. Confidences are reported but not yet calibrated (calibrated=false at v1). Full verdict history is not shown on this page.

Own this server? Screen its description →

That verdict was true at screening time (snapshot 2026-07-31).

Contracts can change after screening, with no version bump. The gate pins com.knitli/codeweaver’s tool contracts on first sight and holds any silent change before your agent acts - the check that keeps being true on Tuesday.

See your first HOLD in 2 minutes →

Related: how to trust an MCP server · screen before install · silent contract drift

Embed this badge

A live verdict badge for your README or listing. It reflects the current screen, links back here, and updates when the verdict does.

Markdown
[![mcpindex](https://mcpindex.ai/api/v1/badge/com-knitli-codeweaver)](https://mcpindex.ai/server/com-knitli-codeweaver)
HTML
<a href="https://mcpindex.ai/server/com-knitli-codeweaver"><img src="https://mcpindex.ai/api/v1/badge/com-knitli-codeweaver" alt="mcpindex verdict" height="20" /></a>
Environment variables
CODEWEAVER_CONFIG_FILE

Specify a custom config file path for CodeWeaver. Only needed if not using the default locations.

CODEWEAVER_DEBUG

Enable debug mode for CodeWeaver.

CODEWEAVER_EMBEDDING_API_KEY
secret

Specify the API key for the embedding provider, if required. Note: {', '.join([p for p in _providers_for_kind('embedding') if p.])}

CODEWEAVER_EMBEDDING_MODEL

Specify the embedding model to use.

CODEWEAVER_EMBEDDING_PROVIDER

Specify the embedding provider to use.

CODEWEAVER_HOST

Set the server host for CodeWeaver.

CODEWEAVER_LOG_LEVEL

Set the log level for CodeWeaver (e.g., DEBUG, INFO, WARNING, ERROR).

CODEWEAVER_MCP_PORT

Set the MCP server port for CodeWeaver if using http transport for mcp. Not required if using the default port (9328), or stdio transport.

CODEWEAVER_PORT

Set the port for the codeweaver management server (information and management endpoints).

CODEWEAVER_PROFILE

Use a premade provider settings profile for CodeWeaver.

CODEWEAVER_PROJECT_NAME

Set the project name for CodeWeaver.

CODEWEAVER_PROJECT_PATH

Set the project path for CodeWeaver.

CODEWEAVER_RERANKING_API_KEY
secret

Specify the API key for the reranking provider, if required.

CODEWEAVER_RERANKING_MODEL

Specify the reranking model to use.

CODEWEAVER_RERANKING_PROVIDER

Specify the reranking provider to use.

CODEWEAVER_SPARSE_EMBEDDING_MODEL

Specify the sparse embedding model to use.

CODEWEAVER_SPARSE_EMBEDDING_PROVIDER

Specify the sparse embedding provider to use.

CODEWEAVER_VECTOR_STORE_API_KEY
secret

Specify the API key for the vector store, if required.

CODEWEAVER_VECTOR_STORE_PORT

Specify the port for the vector store.

CODEWEAVER_VECTOR_STORE_PROVIDER

Specify the vector store provider to use.

CODEWEAVER_VECTOR_STORE_URL

Specify the URL for the vector store.

CODEWEAVER__TELEMETRY__DISABLE_TELEMETRY

Disable telemetry data collection.

CODEWEAVER__TELEMETRY__TOOLS_OVER_PRIVACY

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.

HTTPS_PROXY

HTTP proxy for requests (Used by: Azure, Azure, Voyage)

OPENAI_API_KEY
secret

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)

OPENAI_LOG

One of: 'debug', 'info', 'warning', 'error' (Used by: Azure, Cerebras, Deepseek, Fireworks, Github, Groq, Heroku, Moonshot, Ollama, Openai, Openrouter, Perplexity, Together, Vercel, X Ai)

SSL_CERT_FILE

Path to the SSL certificate file for requests (Used by: Azure, Azure, Voyage)

AI_GATEWAY_API_KEY
secret

API key for Vercel service

AWS_ACCOUNT_ID

AWS Account ID for Bedrock service

AWS_REGION

AWS region for Bedrock service

AWS_SECRET_ACCESS_KEY
secret

AWS Secret Access Key for Bedrock service

AZURE_COHERE_API_KEY
secret

API key for Azure Cohere service (cohere models on Azure)

AZURE_COHERE_ENDPOINT

Endpoint for Azure Cohere service (cohere models on Azure)

AZURE_COHERE_REGION

Region for Azure Cohere service

AZURE_OPENAI_API_KEY
secret

API key for Azure OpenAI service (OpenAI models on Azure)

AZURE_OPENAI_ENDPOINT

Endpoint for Azure OpenAI service (OpenAI models on Azure)

AZURE_OPENAI_REGION

Region for Azure OpenAI service (OpenAI models on Azure)

COHERE_API_KEY

Your Cohere API Key

CO_API_URL

Host URL for Cohere service

DEEPSEEK_API_KEY
secret

API key for DeepSeek service

GEMINI_API_KEY

Your Google Gemini API Key

GOOGLE_API_KEY

Your Google API Key

HF_HUB_VERBOSITY

Log level for Hugging Face Hub client

HF_TOKEN

API key/token for Hugging Face service

HTTPS_PROXY

HTTP proxy for requests

INFERENCE_KEY
secret

API key for Heroku service

INFERENCE_URL

Host URL for Heroku service

MISTRAL_API_KEY

Your Mistral API Key

OPENAI_API_KEY
secret

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.

OPENAI_LOG

One of: 'debug', 'info', 'warning', 'error'

QDRANT__LOG_LEVEL

Log level for Qdrant service

QDRANT__SERVICE__API_KEY
secret

API key for Qdrant service

QDRANT__SERVICE__ENABLE_TLS

Enable TLS for Qdrant service, expects truthy or false value (e.g. 1 for on, 0 for off).

QDRANT__SERVICE__HOST

Hostname of the Qdrant service; do not use for URLs with schemes (e.g. 'http://')

QDRANT__SERVICE__HTTP_PORT

Port number for the Qdrant service

QDRANT__TLS__CERT

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.

SSL_CERT_FILE

Path to the SSL certificate file for requests

TAVILY_API_KEY

Your Tavily API Key

TOGETHER_API_KEY
secret

API key for Together service

VERCEL_OIDC_TOKEN
secret

OIDC token for Vercel service

VOYAGE_API_KEY
secret

API key for Voyage service

CODEWEAVER_CONFIG_FILE

Specify a custom config file path for CodeWeaver. Only needed if not using the default locations.

CODEWEAVER_DEBUG

Enable debug mode for CodeWeaver.

CODEWEAVER_EMBEDDING_API_KEY
secret

Specify the API key for the embedding provider, if required. Note: {', '.join([p for p in _providers_for_kind('embedding') if p.])}

CODEWEAVER_EMBEDDING_MODEL

Specify the embedding model to use.

CODEWEAVER_EMBEDDING_PROVIDER

Specify the embedding provider to use.

CODEWEAVER_HOST

Set the server host for CodeWeaver.

CODEWEAVER_LOG_LEVEL

Set the log level for CodeWeaver (e.g., DEBUG, INFO, WARNING, ERROR).

CODEWEAVER_MCP_PORT

Set the MCP server port for CodeWeaver if using http transport for mcp. Not required if using the default port (9328), or stdio transport.

CODEWEAVER_PORT

Set the port for the codeweaver management server (information and management endpoints).

CODEWEAVER_PROFILE

Use a premade provider settings profile for CodeWeaver.

CODEWEAVER_PROJECT_NAME

Set the project name for CodeWeaver.

CODEWEAVER_PROJECT_PATH

Set the project path for CodeWeaver.

CODEWEAVER_RERANKING_API_KEY
secret

Specify the API key for the reranking provider, if required.

CODEWEAVER_RERANKING_MODEL

Specify the reranking model to use.

CODEWEAVER_RERANKING_PROVIDER

Specify the reranking provider to use.

CODEWEAVER_SPARSE_EMBEDDING_MODEL

Specify the sparse embedding model to use.

CODEWEAVER_SPARSE_EMBEDDING_PROVIDER

Specify the sparse embedding provider to use.

CODEWEAVER_VECTOR_STORE_API_KEY
secret

Specify the API key for the vector store, if required.

CODEWEAVER_VECTOR_STORE_PORT

Specify the port for the vector store.

CODEWEAVER_VECTOR_STORE_PROVIDER

Specify the vector store provider to use.

CODEWEAVER_VECTOR_STORE_URL

Specify the URL for the vector store.

CODEWEAVER__TELEMETRY__DISABLE_TELEMETRY

Disable telemetry data collection.

CODEWEAVER__TELEMETRY__TOOLS_OVER_PRIVACY

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.

HTTPS_PROXY

HTTP proxy for requests (Used by: Azure, Azure, Voyage)

OPENAI_API_KEY
secret

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)

OPENAI_LOG

One of: 'debug', 'info', 'warning', 'error' (Used by: Azure, Cerebras, Deepseek, Fireworks, Github, Groq, Heroku, Moonshot, Ollama, Openai, Openrouter, Perplexity, Together, Vercel, X Ai)

SSL_CERT_FILE

Path to the SSL certificate file for requests (Used by: Azure, Azure, Voyage)

AI_GATEWAY_API_KEY
secret

API key for Vercel service

AWS_ACCOUNT_ID

AWS Account ID for Bedrock service

AWS_REGION

AWS region for Bedrock service

AWS_SECRET_ACCESS_KEY
secret

AWS Secret Access Key for Bedrock service

AZURE_COHERE_API_KEY
secret

API key for Azure Cohere service (cohere models on Azure)

AZURE_COHERE_ENDPOINT

Endpoint for Azure Cohere service (cohere models on Azure)

AZURE_COHERE_REGION

Region for Azure Cohere service

AZURE_OPENAI_API_KEY
secret

API key for Azure OpenAI service (OpenAI models on Azure)

AZURE_OPENAI_ENDPOINT

Endpoint for Azure OpenAI service (OpenAI models on Azure)

AZURE_OPENAI_REGION

Region for Azure OpenAI service (OpenAI models on Azure)

COHERE_API_KEY

Your Cohere API Key

CO_API_URL

Host URL for Cohere service

DEEPSEEK_API_KEY
secret

API key for DeepSeek service

GEMINI_API_KEY

Your Google Gemini API Key

GOOGLE_API_KEY

Your Google API Key

HF_HUB_VERBOSITY

Log level for Hugging Face Hub client

HF_TOKEN

API key/token for Hugging Face service

HTTPS_PROXY

HTTP proxy for requests

INFERENCE_KEY
secret

API key for Heroku service

INFERENCE_URL

Host URL for Heroku service

MISTRAL_API_KEY

Your Mistral API Key

OPENAI_API_KEY
secret

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.

OPENAI_LOG

One of: 'debug', 'info', 'warning', 'error'

QDRANT__LOG_LEVEL

Log level for Qdrant service

QDRANT__SERVICE__API_KEY
secret

API key for Qdrant service

QDRANT__SERVICE__ENABLE_TLS

Enable TLS for Qdrant service, expects truthy or false value (e.g. 1 for on, 0 for off).

QDRANT__SERVICE__HOST

Hostname of the Qdrant service; do not use for URLs with schemes (e.g. 'http://')

QDRANT__SERVICE__HTTP_PORT

Port number for the Qdrant service

QDRANT__TLS__CERT

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.

SSL_CERT_FILE

Path to the SSL certificate file for requests

TAVILY_API_KEY

Your Tavily API Key

TOGETHER_API_KEY
secret

API key for Together service

VERCEL_OIDC_TOKEN
secret

OIDC token for Vercel service

VOYAGE_API_KEY
secret

API key for Voyage service

MCP quality score · maturity, not trust · methodology
freshness
9
completeness
15
installability
25
documentation
15
stability
5
Alternatives in Search