preprint-fulltext
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_preprintsB | Search preprint full text (Europe PMC relevance or OpenAlex n-gram). field scopes to fulltext|title|abstract|author. |
| get_fulltextC | Retrieve structured full-text sections for a preprint DOI (or URL). Resolves to the latest version by default; pass version for a specific one. |
| get_metadataB | Retrieve bibliographic metadata (abstract only) for a preprint DOI. |
| resolveB | Resolve between a DOI, an OpenAlex id, and a Europe PMC PPR id. |
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 4 tools
Each tool has a clearly distinct purpose: full-text retrieval, metadata/abstract retrieval, identifier resolution, and search. The boundaries between get_fulltext and get_metadata are especially clear despite both taking a DOI, since one returns sections and the other returns bibliographic metadata.
Names are consistently snake_case with a verb_noun pattern (get_fulltext, get_metadata, search_preprints). The bare verb 'resolve' is a minor deviation but remains readable and idiomatic for identifier resolution.
Four tools is well-scoped for a focused preprint full-text server, with each tool covering a necessary operation: search, resolve, metadata, and full text. There is no redundant or filler tool.
The core lifecycle is covered: search, identifier resolution, metadata, and structured full-text retrieval, including version selection. Minor gaps remain, such as listing available versions or batch operations, but agents can work around them via resolve and get_fulltext.