Server Configuration
Describes the environment variables required to run the server.
Name | Required | Description | Default |
---|---|---|---|
SANDBOX_DIR | No | The directory for documents (default: ./sandbox) | ./sandbox |
ENGINE_ORDER | No | Engine order, e.g. searxng,duckduckgo | |
LANG_DEFAULT | No | Default language hint for web search | |
REGION_DEFAULT | No | Default region hint for web search | |
MAX_FETCH_BYTES | No | Maximum bytes to fetch from a page | |
FETCH_TIMEOUT_MS | No | Page fetch timeout in milliseconds | |
SEARXNG_ENDPOINTS | No | List of SearXNG /search endpoints, separated by commas |
Schema
Prompts
Interactive templates invoked by user choice
Name | Description |
---|---|
No prompts |
Resources
Contextual data attached and managed by the client
Name | Description |
---|---|
No resources |
Tools
Functions exposed to the LLM to take actions
Name | Description |
---|---|
calc.eval | Evaluate math expression (no external calls). |
calc_eval | Alias of calc.eval |
web.search | Multi-engine web search (SearXNG + DuckDuckGo HTML). |
web_search | Alias of web.search |
web.fetch | Fetch a URL with size/time limits and anti-SSRF. |
web_fetch | Alias of web.fetch |
web.read | Extract readable content from given HTML (or pass html from web.fetch). |
web_read | Alias of web.read |
doc.find | Search local documents within sandbox directory. Builds index if missing. |
doc_find | Alias of doc.find |
doc.read | Read a file from sandbox directory (text or pdf). |
doc_read | Alias of doc.read |
index.build | Build MiniSearch index for documents in sandbox directory. |
index_build | Alias of index.build |
sch.search | Academic-first search (arXiv + Crossref + Wikipedia). |
sch_search | Alias of sch.search |
sch.get | Get scholarly metadata by DOI/arXivId/URL. |
sch_get | Alias of sch.get |
wiki.search | Wikipedia title search (public API). |
wiki_search | Alias of wiki.search |
wiki.get | Wikipedia summary by title. |
wiki_get | Alias of wiki.get |