seeker
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SEEKER_DEVICE | No | Device to run models on: `cpu`, `mps`, or `cuda` | auto |
| SEEKER_RERANK | No | Set to `blend` or `pure` to enable cross-encoder reranking in the `auto` search type | off |
| SEEKER_HYDE_MODEL | No | Model used for query rewriting (HyDE), off by default; e.g. `llama3.2:3b` via Ollama | |
| SEEKER_RERANK_DEPTH | No | Number of candidates reranked | 30 |
| SEEKER_RERANK_MODEL | No | The reranker model to use; `BAAI/bge-reranker-base` is slower | cross-encoder/ms-marco-MiniLM-L6-v2 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Semantic web search over a local open index of high-quality web pages. Describe the page you want in natural language for best results. The index is a static snapshot, so it is weak on very recent events.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| web_searchC | Search the web index. Returns title, url, crawl date, relevant highlights and the start of each page. |
| find_similarC | Find pages similar in meaning to the given URL. |
| get_contentsC | Get the full text of a page: from the index if present, otherwise fetched live. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a distinct input shape: find_similar takes a URL, web_search takes a query, and get_contents retrieves full text. There is mild conceptual overlap between find_similar and web_search (both surface related pages), but the URL-vs-query distinction is clear enough to avoid misselection.
All three names follow a clean verb_noun snake_case pattern: find_similar, get_contents, web_search. No mixed conventions or vague verbs.
Three tools is lean but each covers a distinct retrieval mode (search, fetch, similarity), so nothing feels redundant. It sits at the thin edge of the range, with no explicit way to submit or index a page.
The surface covers the core read path — search, retrieve full text, and find similar pages — but there is no tool to add or refresh pages in the index, no result pagination control, and no metadata-only lookup. Agents can work around these gaps but cannot manage the index.