NOEMA-AI MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| API_KEY | No | Leave blank to run the API in open dev mode. Set a value to require a matching X-API-Key header | |
| PERSIST_DIR | No | Where the BM25 corpus and ingested-document manifest are saved | ./storage |
| GROQ_API_KEY | No | Key for Groq-hosted LLaMA 3.3 70B calls (leave blank to use the built-in mock LLM for local testing) | |
| HYBRID_RRF_K | No | Reciprocal Rank Fusion constant for /query/hybrid; higher values reduce how much rank position 1 vs 2 matters | 60 |
| VECTOR_DB_PATH | No | Local path for the persistent Chroma store | ./chroma_db |
| EMBEDDING_PROVIDER | No | Embedding provider: hash (default), sentence-transformers, or remote | hash |
| EMBEDDING_MODEL_NAME | No | Model name used when EMBEDDING_PROVIDER=sentence-transformers | all-MiniLM-L6-v2 |
| CHAT_HISTORY_MAX_TURNS | No | How many turns of conversation /chat keeps per session | 10 |
| QUERY_CACHE_MAX_ENTRIES | No | How many entries the cache holds before evicting | 500 |
| QUERY_CACHE_TTL_SECONDS | No | How long identical (mode, query, top_k) requests are served from cache | 300 |
| CHAT_SESSION_TTL_SECONDS | No | How long an idle session is kept before being swept | 3600 |
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
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 | |
This server cannot be deployed
Maintenance
ActivityStale
ResponsivenessNo issues