NASA ADS MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ADS_API_TOKEN | Yes | Your NASA ADS API token (get yours at https://ui.adsabs.harvard.edu/user/settings/token) |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_papersA | Search NASA ADS for papers. Each result shows title, authors, year, citations, publication (journal, volume, page), DOI, arXiv ID and bibcode. How ADS queries work:
|
| get_paper_detailsA | Get full details for up to 20 papers in one call: abstract, authors, publication (journal, volume, page), DOI, arXiv ID, keywords and citations. Accepts bibcodes, DOIs and arXiv IDs, and says which ones ADS doesn't have. |
| get_author_papersA | Find papers by an author. Returns titles, years, publication details, citations and bibcodes. Searches the astronomy collection unless told otherwise. Matches names, not people: the result lists the ORCID iDs recorded on this name's first-author papers; confirm one with the user before passing it as orcid. |
| export_bibtexA | Export BibTeX citations for one or more papers, exactly as ADS formats them (journal macros, volume, pages, DOI, eprint). Accepts bibcodes, DOIs and arXiv IDs; the BibTeX key is always ADS's current bibcode, and the result notes any that changed. Useful for adding references to LaTeX/Quarto documents. |
| check_referencesA | Check a list of references, as written in a manuscript's bibliography, against ADS: finds each paper's bibcode and says whether the reference matches the ADS record (first author, year, volume, page). Use it to verify a bibliography or to get bibcodes for export_bibtex. Pass one reference per list item, up to 100 per call; send a whole bibliography in one call, because ADS allows only 100 resolver requests a day. References marked CHECK resolved to a paper that differs from what is written, which can be a typo in the reference or a wrong match: show the user both. For NOT FOUND, try search_papers with the first author and a few title words. |
| get_paper_metricsA | Get detailed metrics for specific papers including citation count, reads, and impact indicators. Accepts bibcodes, DOIs and arXiv IDs. Useful for tracking paper impact over time. |
| get_author_metricsA | Get comprehensive metrics for an author including h-index, total citations, paper count, and citation statistics. Useful for CV preparation and tracking research impact. Matches names, not people: searches the astronomy collection unless told otherwise, and the result states the filter, so numbers can differ from ADS's web page, which counts all collections. For a common name, give the orcid; the result lists the iDs recorded on the name's first-author papers. For a CV, refereed_only and max_authors give a figure for the author's own work, without large collaboration papers. |
| list_librariesA | List all your personal paper libraries/collections in ADS. Shows library names, descriptions, and paper counts. |
| get_library_papersB | Get all papers from a specific library. Returns paper details for papers in the specified collection. |
| create_libraryB | Create a new paper library/collection in the user's ADS account. Useful for organizing papers by topic, project, or reading status. |
| add_to_libraryA | Add papers to an existing library in the user's ADS account. Provide library ID and list of bibcodes to add. Papers already in the library are not duplicated. |
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 11 tools
Most tools have clearly distinct purposes: general search, paper details, author papers, metrics, BibTeX export, reference checking, and library management. There is some overlap because search_papers can also query by author and get_paper_details includes citation counts, but the descriptions generally make the intended use clear.
All tool names use consistent snake_case and follow a predictable verb_noun pattern such as search_papers, get_paper_details, create_library, and add_to_library. The naming is coherent across search, metadata, metrics, export, and library operations.
The server exposes 11 tools, which is a well-scoped set for a literature research and reference-management domain. Each tool maps to a meaningful operation without excessive fragmentation.
The tool set covers core ADS workflows: searching, paper details, author papers, citation/impact metrics, BibTeX export, reference checking, and basic personal library creation and population. The main gap is that library management lacks remove/delete or update operations, which limits full CRUD coverage for personal libraries.