bathys
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BATHYS_SEARXNG_HOME | No | Optional path to the SearXNG home directory used by Bathys. If not set, Bathys will use its default runtime location. |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| deep_researchA | Search the web AND read the top sources in one shot. Runs SearXNG metasearch, dives into the top max_sources pages with a real
browser, distills each page down to passages relevant to |
| web_searchA | Search the web via SearXNG metasearch; return a compact ranked link list. Returns title, URL and a short snippet per hit — no page content. Empty or blocked results are retried automatically with other engine sets. To actually read pages, call read_url; to do both at once, call deep_research. Args: query: search query (natural language or keywords) max_results: 1-20 time_range: "day" | "week" | "month" | "year" category: e.g. "general", "news", "science", "it", "files" engines: comma-separated engine names, e.g. "google,bing,duckduckgo" language: e.g. "ru", "en", "ru-RU" refresh: ignore cache and re-run the search as_json: return pure machine-readable JSON {query, count, hits[], answer?} instead of the human-friendly list (no footer line) |
| read_urlA | Read one web page; return its main content as clean, budgeted markdown. JS-rendered pages are handled by a real headless browser. Boilerplate
(nav, footer, ads) is stripped; if |
| read_urlsA | Read several known web pages in one call under one shared character budget. Pages are fetched in parallel (JS-rendered, boilerplate-stripped) and the combined total_chars budget is split evenly between the pages that came back. Prefer this over N read_url calls when you already hold the URLs: one round-trip, one budget, and a failed page costs one line instead of a failed call. Args: urls: 1-10 absolute http(s) URLs; duplicates (after utm/fragment cleanup) are merged, extras beyond 10 are reported in a Skipped line query: optional focus; each page is distilled to passages relevant to it total_chars: combined output budget across all sections (300-30000) refresh: ignore cache and re-fetch every page |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| bathys_deep_research | Глубокое исследование одного вопроса за 1–3 итерации: заход, разбор, уточнение терминами источников, верификация, синтез. |
| bathys_source_audit | Аудит утверждения по списку URL: чтение под тезис, кросс-поиск опровержений, вердикты по каждому пункту. |
| bathys_fresh_scan | Свежий срез по теме за окно времени: отбор значимых событий, пакетное чтение, сводка с датами и URL. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
Each tool has a clearly distinct role: web_search returns links only, read_url reads a single page, read_urls batches page reads, and deep_research combines search and reading. The descriptions explicitly cross-reference each other, eliminating ambiguity between the overlapping search/read behaviors.
read_url and read_urls follow a verb_noun pattern, but deep_research and web_search are noun-style phrases rather than commands. The naming is readable and all tools use lowercase with underscores, but the verb/noun mix is inconsistent.
Four tools form a tight, purposeful set for a web research server: search, read single, read batch, and search+read combined. There is no bloat, and each tool earns its place.
The domain of web research is fully covered: discover URLs, fetch one page, fetch many pages, and run a combined research workflow. No critical lifecycle step is missing, and the tools compose naturally.