mcp-server-ads is an MCP server for NASA's Astrophysics Data System (ADS), enabling natural language access to astrophysics literature search, citation analysis, and paper management.
Search papers (
ads_search): Query the ADS database using full query syntax including field searches, boolean operators, and functional operators likecitations(),references(),trending(),reviews(), andsimilar()Bulk bibcode search (
ads_bigquery): Filter, sort, or retrieve metadata for a known set of up to 2000 bibcodesExport citations (
ads_export): Export paper records in 18+ formats including BibTeX, AASTeX, RIS, EndNote, CSL-JSON, VOTable, and moreCompute metrics (
ads_metrics): Calculate h-index, g-index, i10-index, citation/read counts, and time-series histograms for a set of papersManage libraries (
ads_library): List, create, edit, delete, and retrieve saved paper collectionsManage library documents (
ads_library_documents): Add/remove papers, perform set operations (union, intersection, difference), and manage notes on individual papersResolve paper links (
ads_resolve_links): Look up available links for a paper including full text, datasets, citations, and referencesAstronomical object search (
ads_object_search): Translate object names (e.g., 'M31', 'Crab Nebula') into ADS search queries via SIMBAD/NEDCitation suggestions (
ads_citation_helper): Discover papers frequently co-cited with a given bibliography that are not yet includedResolve references (
ads_resolve_reference): Match free-text reference strings to ADS bibcodesNetwork visualization (
ads_network): Generate author collaboration or paper citation cluster networks from a set of papers
Provides tools for searching the NASA Astrophysics Data System (ADS) database, traversing citation graphs, computing citation metrics, resolving paper links and references, and managing research libraries and paper collections.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-server-adsFind the most cited papers on dark matter from the last five years."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-server-ads
A powerful MCP server for the NASA Astrophysics Data System (ADS) — the primary database for astrophysics literature. Search papers, traverse citation graphs forward and backward, export BibTeX, compute metrics, and manage reading lists, all through natural language. Works with Claude Desktop/Code, Cursor, OpenAI Codex, and any MCP-compatible client.
Quick Start
Get an ADS API Token
Create a free account at NASA ADS
Log in and go to Settings > API Token
Click Generate a new key and copy the token
Installation
No separate install step needed — the client configurations below use uvx to automatically fetch and run the server. Just pick your client and go. Requires Python 3.11+ and uv.
Claude Code
claude mcp add --scope user mcp-server-ads -e ADS_API_TOKEN=your-api-token-here -- uvx --from git+https://github.com/cbyrohl/mcp-server-ads mcp-server-adsUse --scope project instead to share the configuration via .mcp.json in your repo, or omit --scope for local (current project only).
Claude Desktop
Add to your Claude Desktop config:
{
"mcpServers": {
"ads": {
"command": "uvx",
"args": ["--from", "git+https://github.com/cbyrohl/mcp-server-ads", "mcp-server-ads"],
"env": {
"ADS_API_TOKEN": "your-api-token-here"
}
}
}
}Codex CLI
codex mcp add mcp-server-ads --env ADS_API_TOKEN=your-api-token-here -- uvx --from git+https://github.com/cbyrohl/mcp-server-ads mcp-server-adsThis installs to ~/.codex/config.toml (user-level, available across all projects). For project-scoped config, add the entry to .codex/config.toml in your project root instead.
Standalone / Python API
If you want to install the package directly (e.g. as a Python library or to run the server manually):
# Install with uv
uv tool install git+https://github.com/cbyrohl/mcp-server-ads
# Or with pip
pip install git+https://github.com/cbyrohl/mcp-server-adsRunning from Source
git clone https://github.com/cbyrohl/mcp-server-ads.git
cd mcp-server-ads
uv sync
# Run the server
ADS_API_TOKEN=your-token uv run mcp-server-adsConfiguration
Environment Variable | Required | Default | Description |
| Yes | — | API token from ADS |
| No |
| API base URL (override for SciX) |
Tools (11)
Search
Tool | Description |
| Search the ADS database with full query syntax, including |
| Search within a specific set of bibcodes (up to 2000) |
Export & Metrics
Tool | Description |
| Export records in 18+ formats (BibTeX, AASTeX, RIS, CSL, etc.) |
| Compute citation metrics (h-index, g-index, citation counts, etc.) |
Libraries
Tool | Description |
| Manage libraries: list, get, create, edit, or delete saved paper collections |
| Manage documents and notes within a library: add/remove papers, set operations (union, intersection, difference, copy, empty), and note CRUD |
Discovery & Resolution
Tool | Description |
| Resolve available links for a paper (full text, data, etc.) |
| Translate astronomical object names to ADS queries (SIMBAD/NED) |
| Suggest papers that should be cited alongside a given set |
| Resolve free-text reference strings to ADS bibcodes |
Network Visualization
Tool | Description |
| Generate author collaboration or paper citation networks from a set of papers |
Resources
URI | Description |
| Complete reference of searchable and returnable ADS fields |
| ADS query syntax quick-reference with examples |
| Live API rate-limit status |
Prompts
Prompt | Description |
| Multi-step literature review workflow for a research topic |
| Citation network analysis workflow for a set of papers |
| Generate a formatted bibliography from search or bibcodes |
Similar Projects
prtc/nasa-ads-mcp — ADS search, metrics, and library management
thostetler/scix-mcp — MCP server for the SciX/ADS API
blazickjp/arxiv-mcp-server — MCP server for arXiv paper search and retrieval
This server focuses on broad ADS API coverage, token-efficient output, and integration-tested reliability. Compared to arXiv-based tools, ADS enables forward/backward citation traversal (citations and references of any paper), though it is focused on astrophysics.
Development
# Install dev dependencies
uv sync
# Run tests
uv run pytest
# Lint
uv run ruff check src/ tests/
# Run the server locally
ADS_API_TOKEN=your-token uv run mcp-server-adsLicense
MIT
Resources
Looking for Admin?
Admins can modify the Dockerfile, update the server description, and track usage metrics. If you are the server author, to access the admin panel.