Adsabs Harvard Edu API for Astrophysics Data System (ADS)
Official vendor OpenAPI document · agent-readyEducationLmsbearer97 EndpointsREST
For Agents
Search NASA ADS astronomy and physics literature, manage personal libraries, export citations in many formats, run metrics, and resolve objects, references, and authors through bearer-authenticated endpoints.
Use for: I want to search ADS for papers on exoplanet atmospheres published since 2024, Save my exoplanet atmosphere query so I can rerun it later, Add a list of bibcodes to my 'Thesis-Ch3' library, Export the references in my library as BibTeX
Not supported: Does not handle paper hosting, peer review, or full-text fetching from publishers - use for ADS search, library, citation export, and bibliometric services only.
The NASA Astrophysics Data System (ADS) API provides programmatic access to one of the world's largest digital libraries of astronomy and physics literature, hosted by the Smithsonian Astrophysical Observatory at Harvard. This OpenAPI specification exposes 97 endpoints covering full-text search, stored queries, library management, citation export in many formats, metrics, author affiliation lookups, citation helpers, classic ADS import, object resolution, journal data, recommendations, references, resolvers, and visualisations. Use it to build literature-discovery tools, citation pipelines, and bibliometric analyses against the ADS corpus. Authentication is by bearer token issued by the ADS user portal.
Install Jentic One Beta
Connect the API for Astrophysics Data System (ADS) to your agent
Jentic One is a self-hosted execution layer for AI agents. It lets your agent call the API for Astrophysics Data System (ADS), or any other public or private API you need. You set the rules, the agent never sees your credentials, and every call is logged.
Two steps, two machines. Install the instance in a safe environment, then register your agent from wherever it runs.
1
Step 1: Jentic One Host machine
# On the machine that will host your Jentic One instance:
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fadsabs.harvard.edu%2Fads" | sh2
Step 2: Agent machine
# On the machine where your agent runs (keep this separate from the instance):
curl -fsSL "https://jentic.com/install.sh?src=apis&api=%2Fapis%2Fadsabs.harvard.edu%2Fads" | sh
jentic register # connects your agent to your Jentic One instanceJentic One is in public beta. The setup above keeps your agent separate from the instance, which is what you want before using real credentials: an agent running as the same OS user as Jentic One can read its stored keys directly. Just evaluating? A single local install is fine to start. See the secure deployment guide for the tiers.
Capabilities
What an agent can do with API for Astrophysics Data System (ADS) API.
Run keyword and field-restricted searches across the NASA ADS corpus and return ranked bibcodes
Save and replay queries via the vault stored-search service to support reproducible literature reviews
Manage personal libraries of bibcodes including adding documents, performing set operations, and transferring ownership
Export selected bibcodes in tagged, LaTeX, and XML citation formats for papers and reports
Compute citation and usage metrics for a set of papers including h-index and read counts
Resolve astronomical objects, journals, references, and full-text resolver links from a bibcode
Use Cases
Patterns agents use API for Astrophysics Data System (ADS) API for, with concrete tasks.
★ Programmatic Literature Search
Researchers and bibliometric tools query the ADS corpus using GET /search/query with field-restricted Solr-style queries (e.g., title:exoplanet AND year:2024). The big-query variant POST /search/bigquery accepts batches of bibcodes for retrieval. This replaces UI scraping and produces stable, reproducible result sets for downstream analysis.
Run GET /search/query with q=title:'exoplanet atmosphere' AND year:2024-* and return the top 50 bibcodes
Personal Library Curation
ADS users curate libraries of bibcodes for projects, papers, or courses using the biblib endpoints, including adding documents (POST /biblib/documents/{library_id}), running set operations (POST /biblib/libraries/operations/{library_id}), and transferring ownership when a researcher leaves a group. This builds a programmatic alternative to the ADS web UI for managing reading lists at scale.
Add a list of 30 bibcodes to library 'Thesis-Ch3' via POST /biblib/documents/{library_id}
Citation Export and Reference Pipelines
Authors and reference managers export selected bibcodes in BibTeX, AASTeX, EndNote, RIS, and other formats using the export service endpoints. Combined with the resolver and reference services, this drives end-to-end pipelines from search to formatted bibliography without manual copy-paste.
Export the 30 bibcodes in library 'Thesis-Ch3' as BibTeX via the ADS export service
Bibliometrics and Metrics Reports
Department administrators and tenure committees compute citation metrics for a set of papers using the metrics service, including h-index, total citations, and read counts. These numbers feed into hiring, grant, and tenure assessments and removing the manual lookup step is a meaningful time saver.
Compute the h-index and total citations for the bibcodes in library 'GroupPapers-2026' using the ADS metrics endpoints
Agent-Driven Literature Research via Jentic
AI research assistants chain ADS search, library, export, and metrics calls via Jentic to answer literature questions in natural language. The bearer token is held in your Jentic One instance rather than in the agent's prompt, and intent search resolves to the right ADS service among the 97 endpoints without the agent reading the full ADS API docs.
Search Jentic for 'ads search', load GET /search/query, execute it for 'protoplanetary disk' since 2023, then export the top 20 bibcodes as BibTeX
Key Endpoints
97 endpoints — the nasa astrophysics data system (ads) api provides programmatic access to one of the world's largest digital libraries of astronomy and physics literature, hosted by the smithsonian astrophysical observatory at harvard.
METHOD
PATH
DESCRIPTION
GET
/search/query
Search the ADS corpus
POST
/search/bigquery
Search using bigquery batch
POST
/vault/query
Save a query
GET
/biblib/libraries
List user libraries
POST
/biblib/documents/{library_id}
Add or remove documents in a library
POST
/biblib/libraries/operations/{library_id}
Run set operations on libraries
GET
/search/query
Search the ADS corpus
POST
/search/bigquery
Search using bigquery batch
POST
/vault/query
Save a query
GET
/biblib/libraries
List user libraries
POST
/biblib/documents/{library_id}
Add or remove documents in a library
POST
/biblib/libraries/operations/{library_id}
Run set operations on libraries
Why Jentic?
What agents get from Jentic-routed access to this vendor.
Setup
Wiring the Astrophysics Data System API by hand means handling its bearer token auth and staying within your account's daily quota across a large service surface. Through Jentic you install once, import ADS from the API Directory, store the token once, and your agent calls it.
Permission scoping
ADS puts the library id in the URL path (/biblib/documents/{library_id}), so a rule can pin your agent to one library: it can add documents to and run operations on that library and nothing else. You choose the operations it may call, so search and citation export stay available only if you include them.
Credential isolation
Your ADS bearer token is stored once, encrypted, by your own Jentic One instance and injected at execution time. It never enters the agent's prompt, logs, or context.
Intent-based discovery
Agents search Jentic by intent such as 'run an ads search query' or 'export bibcodes as bibtex', and Jentic returns the matching ADS operation with its input schema so the agent calls the right endpoint without browsing the reference docs.
Related APIs
Alternatives and complements available in the Jentic catalogue.
FAQs
Specific to using API for Astrophysics Data System (ADS) API through Jentic.
What authentication does the NASA ADS API use?
ADS uses HTTP bearer authentication. Tokens are issued from the ADS user portal under Account Settings and sent in the Authorization header as 'Authorization: Bearer <token>'. Through Jentic, the token is stored encrypted in the vault and injected at execution time so the agent never sees the raw secret.
Can I save a search and replay it with the NASA ADS API?
Yes. POST /vault/query saves a query and returns a queryId. You can later retrieve it via GET /vault/query/{queryId} or replay it with GET /vault/execute_query/{queryId}. This is the canonical pattern for reproducible literature reviews.
How do I export bibcodes as BibTeX with the NASA ADS API through Jentic?
Search Jentic for 'ads bibtex export', load the relevant export service endpoint, and execute it with the bibcode list. The export service offers tagged, LaTeX (BibTeX, AASTeX), XML, and other formats so the same flow handles most reference managers.
What are the rate limits for the NASA ADS API?
ADS enforces daily request limits per service (search, bigquery, export, metrics) which are documented at the ADS user portal but not in the OpenAPI spec. Returned headers include the remaining quota. Through Jentic, retries with backoff can be configured in the execution request.
Can I run set operations across two ADS libraries?
Yes. POST /biblib/libraries/operations/{library_id} accepts union, intersection, and difference operations between libraries you have access to. This is useful for combining curated reading lists or finding papers in one list that are absent from another.
Is the NASA ADS API free?
Yes. Access is free for academic and personal research use after creating an ADS account. Heavy usage may require contacting ADS to extend rate limits, but there is no per-call charge. Jentic stores the bearer token once you have one.
Can I limit what my agent is allowed to do with the NASA ADS API?
Yes. Because you run Jentic One yourself, your own rules decide which ADS operations and credentials the agent may use. ADS carries the library id in the URL path (/biblib/documents/{library_id}), so a rule can pin the agent to a single library, letting it add documents to and run set operations on that one library and nothing else. You choose which operations are exposed, so calls like GET /search/query or the citation export service are only reachable if you include them.
GET STARTED