code-rag-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AZURE_API_KEY | No | Azure API key | |
| AZURE_API_BASE | No | Azure API base URL | |
| COHERE_API_KEY | No | Cohere API key | |
| OPENAI_API_KEY | No | OpenAI API key (required if using OpenAI embeddings) | |
| AWS_REGION_NAME | No | AWS region name | |
| AWS_ACCESS_KEY_ID | No | AWS access key ID | |
| AZURE_API_VERSION | No | Azure API version | |
| VERTEX_AI_PROJECT | No | Vertex AI project | |
| VERTEX_AI_LOCATION | No | Vertex AI location | |
| CODE_RAG_BATCH_SIZE | No | Batch size for processing (default: 16) | 16 |
| CODE_RAG_CHUNK_SIZE | No | Chunk size in characters (default: 1024) | 1024 |
| AWS_SECRET_ACCESS_KEY | No | AWS secret access key | |
| CODE_RAG_DATABASE_TYPE | No | Database backend: chroma or qdrant (default: chroma) | chroma |
| CODE_RAG_SHARED_SERVER | No | Share embedding server across instances (default: true) | true |
| CODE_RAG_EMBEDDING_MODEL | No | Embedding model (default: nomic-ai/CodeRankEmbed) | nomic-ai/CodeRankEmbed |
| CODE_RAG_RERANKER_ENABLED | No | Enable result reranking (default: false) | false |
| CODE_RAG_ADDITIONAL_IGNORE_PATTERNS | No | Comma-separated custom ignore patterns |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_codebaseA | Semantic code search with AI reranking. Finds relevant code by meaning, not keywords. CRITICAL: Write Specific QueriesVague queries return noise. Specific queries find exactly what you need. GOOD (specific intent + context): • "retry logic with exponential backoff in HTTP client" • "JWT token validation and refresh flow" • "database connection pooling configuration" • "error handling for file upload timeout" • "how user permissions are checked before API access" BAD (too vague - avoid these): • "authentication" → TOO BROAD. Try: "password hashing during user login" • "error handling" → TOO BROAD. Try: "error handling when payment fails" • "config" → TOO BROAD. Try: "database connection config loading" • "utils" or "helper" → MEANINGLESS. Describe what the util DOES. Query Formula[WHAT] + [WHERE/WHEN/HOW] = Good Query • "caching" → "Redis caching for API response memoization" • "logging" → "structured logging setup for request tracing" Tips• Include the PROBLEM you're solving, not just keywords • Mention specific technologies if relevant (Redis, JWT, WebSocket) • Follow up with file read for full context |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 1 tool
Only one tool exists, so there is no ambiguity between tools. The tool's purpose is clear and distinct.
With a single tool, naming is inherently consistent. The name 'search_codebase' follows a clear verb_noun pattern.
One tool is at the low end of the range. While the tool itself is comprehensive for search, the server seems thin for a general code assistance purpose.
The server only provides semantic search. It lacks tools for reading files, browsing code structure, or other common code interactions, making the surface incomplete.