sota-anchor
by luckmanqasim
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SOTA_ANCHOR_MODEL | No | The judging model. Unset, it is picked from the live catalog. | |
| SOTA_ANCHOR_API_KEY | No | Any OpenAI-compatible key. Set for a headless verdict, where no agent is present to judge (as in CI). | |
| SOTA_ANCHOR_BASE_URL | No | The API base URL. Defaults to OpenRouter; set it to use another provider's key. Must be https://, or http:// for a server on this machine (localhost, 127.0.0.1, ::1). | |
| SOTA_ANCHOR_CACHE_DIR | No | Where the catalog and session block are cached. Default ~/.cache/sota-anchor. | ~/.cache/sota-anchor |
| SOTA_ANCHOR_PROMPT_HOOK | No | 1 turns on the prompt-time nudge in Claude Code. | |
| SOTA_ANCHOR_TTL_MINUTES | No | How old the session block can get before the hook refreshes it. Default 1440. | 1440 |
| SOTA_ANCHOR_GITHUB_TOKEN | No | GitHub token that raises GitHub's search limit from 10 to 30 requests a minute. Give it no scopes: a token that can see your private repositories adds them to the search results your agent reads. | |
| SOTA_ANCHOR_BRAVE_API_KEY | No | Brave Search API key. Adds general web search as an evidence source. Unset, the web is not queried. |
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