Arca MCP
by m0nochr0me
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ARCA_DEBUG | No | Enable debug mode | false |
| ARCA_APP_HOST | No | Server bind address | 0.0.0.0 |
| ARCA_APP_PORT | No | Server port | 4201 |
| ARCA_CACHE_TTL | No | Default cache TTL in seconds (1 hour) | 3600 |
| ARCA_TRANSPORT | No | MCP transport (stdio, http, sse, streamable-http) | streamable-http |
| ARCA_REDIS_HOST | No | Redis host | localhost |
| ARCA_REDIS_PORT | No | Redis port | 6379 |
| ARCA_APP_WORKERS | No | Uvicorn worker count | 1 |
| ARCA_APP_AUTH_KEY | Yes | Bearer token for MCP authentication | |
| ARCA_CACHE_TTL_LONG | No | Long cache TTL in seconds (7 days, used for embeddings) | 604800 |
| ARCA_GOOGLE_API_KEY | Yes | Google API key for Gemini embeddings | |
| ARCA_REDIS_DB_CACHE | No | Redis database number for cache | 4 |
| ARCA_REDIS_PASSWORD | No | Redis password (optional) | null |
| ARCA_EMBEDDING_MODEL | No | Gemini embedding model name | gemini-embedding-001 |
| ARCA_VECTOR_STORE_PATH | No | LanceDB storage directory | ./lancedb |
| ARCA_EMBEDDING_DIMENSION | No | Embedding vector dimensionality | 3072 |
| ARCA_LOG_MESSAGE_MAX_LEN | No | Maximum log message length | 2000 |
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