mcp-server-ads
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| ADS_API_URL | No | API base URL (override for SciX) | https://api.adsabs.harvard.edu |
| ADS_API_TOKEN | Yes | API token from ADS |
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": true
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| ads_citation_helperA | Suggest papers that should be cited alongside the given set. Given a set of bibcodes (e.g. from a paper's bibliography), the citation helper returns papers that are frequently co-cited with the input set but are not yet included. |
| ads_exportA | Export paper records in various citation formats. Supports 18+ formats including BibTeX, AASTeX, RIS, EndNote, CSL-JSON, Dublin Core XML, VOTable, and more. Returns formatted citation text. |
| ads_libraryA | Manage ADS libraries (saved paper collections). Actions:
|
| ads_library_documentsA | Manage documents and notes within an ADS library. Document actions:
Note actions:
|
| ads_metricsA | Compute citation metrics for a set of papers. Returns h-index, g-index, i10-index, citation counts, read counts, and time-series histograms. Works for 1 to ~2000 bibcodes. |
| ads_networkA | Generate a collaboration or citation network from a set of papers.
|
| ads_object_searchA | Translate astronomical object names to ADS search queries via SIMBAD/NED. Provide object identifiers (e.g. 'M31', 'Crab Nebula', 'NGC 1234') and get back an ADS query that matches papers about those objects. |
| ads_resolve_referenceA | Resolve free-text reference strings to ADS bibcodes. Accepts human-readable reference strings and attempts to match them to records in ADS. Useful for identifying papers from partial citations. |
| ads_resolve_linksB | Resolve available links for a paper (full text, data, citations, etc.). |
| ads_searchA | Search the NASA ADS database. Supports the full ADS query syntax including field-qualified searches, boolean operators, and functional operators. Common query patterns:
To find citations and references of a paper:
Other functional operators:
|
| ads_bigqueryA | Search within a specific set of bibcodes (big-query). Useful for filtering, sorting, or retrieving metadata for a known set of papers. Provide up to 2000 bibcodes at once. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| literature_review | Multi-step literature review workflow for a research topic. |
| citation_analysis | Citation network analysis workflow for a set of papers. |
| generate_bibliography | Generate a formatted bibliography from a search or bibcode list. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| get_fields | Complete reference of ADS searchable and returnable fields. |
| get_rate_limits | Current ADS API rate-limit status from tracked headers. |
| get_syntax | ADS query syntax quick-reference with examples. |
TDQS
Scored across 11 tools
Each tool has a clearly distinct purpose with no significant overlap. The tools cover different aspects of the ADS ecosystem: searching (ads_search, ads_bigquery), citation analysis (ads_citation_helper, ads_metrics), library management (ads_library, ads_library_documents), network analysis (ads_network), reference resolution (ads_resolve_reference, ads_resolve_links), object translation (ads_object_search), and export (ads_export). An agent can easily distinguish between them based on their specific functions.
All tool names follow a consistent 'ads_' prefix with descriptive snake_case suffixes (e.g., ads_search, ads_metrics, ads_library). This pattern is maintained across all 11 tools, making them predictable and easy to understand. The naming convention clearly indicates they belong to the same server and domain.
With 11 tools, this server is well-scoped for interacting with the NASA ADS database. The count is appropriate as it covers a comprehensive range of operations from basic searching to advanced analysis and management, without being overwhelming. Each tool serves a distinct and necessary function in the domain of academic paper discovery and analysis.
The tool set provides complete coverage for the ADS domain, including search (ads_search, ads_bigquery), citation management (ads_citation_helper, ads_metrics, ads_resolve_reference), library CRUD operations (ads_library, ads_library_documents), network analysis (ads_network), object translation (ads_object_search), link resolution (ads_resolve_links), and export (ads_export). There are no obvious gaps; agents can perform end-to-end workflows from discovery to analysis and organization.