searxng-rank-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_HOST | No | MCP bind address host | 0.0.0.0 |
| MCP_PORT | No | MCP bind address port | 8000 |
| LLM_MODEL | No | LLM model for the orchestrator | llama3.1:8b |
| QDRANT_URL | No | Vector store URL | http://localhost:6333 |
| LLM_API_KEY | No | LLM API key for the orchestrator | |
| LLM_API_BASE | No | LLM API base for the orchestrator (OpenAI-compatible) | |
| MAX_ITERATIONS | No | Orchestrator loop budget | 3 |
| FLASHRANK_MODEL | No | Cross-encoder model | ms-marco-TinyBERT-L-2-v2 |
| SEARXNG_BASE_URL | No | Explicit SearXNG endpoint (highest precedence) | |
| QUALITY_THRESHOLD | No | Rerank pass threshold | 0.7 |
| SEARXNG_SECRET_KEY | No | SearXNG instance secret (compose only) | |
| SEARXNG_SERVICE_HOST | No | Same-network service host to probe | searxng |
| SEARXNG_SERVICE_PORT | No | Same-network service port to probe | 8080 |
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
ActivityMaintained
ResponsivenessNo issues