CodeCompass
by alvinveroy
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HTTP_PORT | No | Port for the utility HTTP server. Can also be specified via --port CLI argument. | 3001 |
| LOG_LEVEL | No | Logging level (e.g., error, warn, info, verbose, debug, silly). | info |
| OLLAMA_HOST | No | URL for the Ollama server. | http://localhost:11434 |
| QDRANT_HOST | No | URL for the Qdrant vector store server. | http://localhost:6333 |
| LLM_PROVIDER | No | Specifies the primary LLM provider for generating suggestions. Supported values: ollama, deepseek, openai, gemini, claude. | ollama |
| CLAUDE_API_KEY | No | Your API key for Anthropic Claude (required if LLM_PROVIDER=claude). | |
| GEMINI_API_KEY | No | Your API key for Google Gemini (required if LLM_PROVIDER=gemini). | |
| OPENAI_API_KEY | No | Your API key for OpenAI (required if LLM_PROVIDER=openai). | |
| COLLECTION_NAME | No | Name of the Qdrant collection for this repository. | |
| EMBEDDING_MODEL | No | The specific model to use for embeddings via Ollama. | nomic-embed-text:v1.5 |
| DEEPSEEK_API_KEY | No | Your API key for DeepSeek (required if LLM_PROVIDER=deepseek). | |
| DEEPSEEK_API_URL | No | Custom API URL for DeepSeek if not using the default. | https://api.deepseek.com/chat/completions |
| REFINEMENT_MODEL | No | LLM model to use for query refinement. Defaults to SUGGESTION_MODEL if not set. | |
| SUGGESTION_MODEL | No | The specific model to use for suggestions. | llama3.1:8b |
| DEEPSEEK_RPM_LIMIT | No | Requests per minute limit for DeepSeek. | 20 |
| EMBEDDING_PROVIDER | No | Provider for generating embeddings. Currently ollama is supported. | ollama |
| AGENT_QUERY_TIMEOUT | No | Timeout in milliseconds for agent's LLM reasoning steps. | 180000 |
| SUMMARIZATION_MODEL | No | LLM model to use for summarization tasks. Defaults to SUGGESTION_MODEL if not set. | |
| AGENT_DEFAULT_MAX_STEPS | No | Default maximum number of steps the agent will take. | 10 |
| AGENT_ABSOLUTE_MAX_STEPS | No | Absolute maximum number of steps the agent can take. | 15 |
| MAX_REFINEMENT_ITERATIONS | No | Maximum number of iterations for query refinement. | 3 |
| QDRANT_SEARCH_LIMIT_DEFAULT | No | Default number of results to fetch from Qdrant during standard searches. | 10 |
| FILE_INDEXING_CHUNK_SIZE_CHARS | No | Target size for chunks when indexing large files (in characters). | 1000 |
| MAX_DIFF_LENGTH_FOR_CONTEXT_TOOL | No | Maximum length of a git diff to include in context without summarization. | 3000 |
| FILE_INDEXING_CHUNK_OVERLAP_CHARS | No | Overlap between chunks when indexing large files (in characters). | 200 |
| MAX_SNIPPET_LENGTH_FOR_CONTEXT_NO_SUMMARY | No | Maximum length of a code snippet to include in context without summarization. | 1500 |
| MAX_FILES_FOR_SUGGESTION_CONTEXT_NO_SUMMARY | No | Maximum number of files to list directly in the generate_suggestion tool's context before summarizing. | 15 |
| REQUEST_ADDITIONAL_CONTEXT_MAX_SEARCH_RESULTS | No | Number of search results to fetch when agent uses request_additional_context. | 20 |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
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/alvinveroy/CodeCompass'
If you have feedback or need assistance with the MCP directory API, please join our Discord server