Harvester
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HARVESTER_HOME | No | Directory under which the launcher installs the versioned Harvester binary. | |
| PLUGIN_LOG_DIR | No | When set, Harvester writes its activity log under $PLUGIN_LOG_DIR/harvester/ instead of the default state log directory. | |
| XDG_STATE_HOME | No | Base directory for Harvester state, including the daemon socket, lock, logs, cache, ask state, and OAuth state. | |
| XDG_CONFIG_HOME | No | Base directory used to determine the default Harvester config path. | |
| HARVESTER_CONFIG | No | Path to the Harvester config file. Defaults to ${XDG_CONFIG_HOME:-$HOME/.config}/harvester/harvester.config.json when unset. | |
| HARVESTER_LOG_LEVEL | No | Selects which Harvester log records are written. | |
| HARVESTER_LOG_COMPONENTS | No | Selects which Harvester log components are written. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Read a web page → read with it in urls; a paper or book by DOI, arXiv id, PMID, PMCID, ISBN, landing URL or search_literature handle → read with it in publications; a local document → read with its path in files; find papers or books by title → search_literature; save a file's bytes unparsed → download_file. Answers are text, one "=== [n/N]" block per item: "No … found" is nothing found, an error is a failed lookup. Web search is not configured on this server — set search.searxngURL or search.braveApiKey in harvester.config.json to enable web search.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| download_fileA | Downloads any file as bytes — 1–50, unparsed: a PDF, zip, image, audio, dataset. Call download_file{urls:["https://…/data.zip"]}. Returns a |
| readA | Reads pages, files and papers — web pages, local documents and scholarly works, as Markdown. Call read{urls:["https://…"], files:["/path/to/file.pdf"], publications:["10.1038/nature14539"]}: 1–50 items, at most 20 publications. A title goes to search_literature first; a file wanted as bytes to download_file. Returns one text block per item, input order: |
| search_literatureA | Finds papers and books — by TITLE or bibliographic query: "find the paper about X", "is there a PDF of ". Call search_literature{query:"Attention Is All You Need", type:"paper"}. Returns a |
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
The three tools map to distinct stages: discover (search_literature), extract as Markdown (read), and fetch raw bytes (download_file). The only real overlap is that both read and download_file can target the same PDF/URL, but the descriptions explicitly split on intent (read for content, download for bytes), so confusion is limited to edge cases.
All names are lowercase snake_case, and search_literature/download_file follow a verb_noun pattern. 'read' is a bare verb rather than verb_noun, a minor deviation but still predictable and readable in context.
Three tools form a tight, well-scoped pipeline (search → read → download) with no redundant entries. Each tool clearly earns its place for a content-harvesting server.
Core lifecycle is covered: discovering scholarly works, reading pages/files/papers, and downloading raw artifacts. The notable gap is discovery of non-scholarly web content — there is no general web search, only literature search — though agents can still read known URLs.