mcp-confidence
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MCP_CONFIDENCE_MODEL | Yes | The model name to use on the worker (e.g., 'Qwen/Qwen3-30B-A3B'). Required. | |
| MCP_CONFIDENCE_TOP_K | No | Number of top logprobs to request (default 5). Optional. | 5 |
| MCP_CONFIDENCE_API_KEY | No | API key for the local worker (default 'not-needed' if not required). | not-needed |
| MCP_CONFIDENCE_BASE_URL | Yes | The base URL of the OpenAI-compatible local worker (e.g., vLLM, Ollama). Required. | |
| MCP_CONFIDENCE_LOW_THRESHOLD | No | Override the low confidence threshold (in nats). Optional, from calibration. | |
| MCP_CONFIDENCE_HIGH_THRESHOLD | No | Override the high confidence threshold (in nats). Optional, from calibration. |
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/shaxzodbek-uzb/mcp-confidence'
If you have feedback or need assistance with the MCP directory API, please join our Discord server