Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
Search 340M+ academic papers — citation graphs, semantic similarity, and AI literature reviews.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://mcp.nobleblocks.com/mcpRun this in your terminal
claude mcp add --transport http nobleblocks https://mcp.nobleblocks.com/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"nobleblocks": {
"url": "https://mcp.nobleblocks.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"nobleblocks": {
"type": "http",
"url": "https://mcp.nobleblocks.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://mcp.nobleblocks.com/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
We have not read this server’s tool list yet; we check endpoints in rotation.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
The registry name was verified against the domain nobleblocks.com (the registry checks domain ownership)
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Not checked yet; we check endpoints in rotation
Not checked yet; we check endpoints in rotation
Not checked yet; we read the tool list when we check the endpoint
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (2.0.0) reached the registry 5 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Search 340 million deduplicated academic papers from Claude Desktop, Claude Web, ChatGPT, Cursor, VS Code Copilot, or any MCP-compatible tool. Covers 15+ academic databases — all cross-linked through a biomedical knowledge graph with 1.3M+ entities and 109M+ paper connections.
This is a thin authenticated client — all indexing, ranking, vector search, and knowledge graph traversal runs on the NobleBlocks backend. You get fast results without managing any infrastructure.
| Source | Papers | Updates |
|---|---|---|
| OpenAlex | ~250M works | Daily |
| Semantic Scholar | ~220M papers | Weekly |
| PubMed / MEDLINE | ~41M articles | Daily |
| Europe PMC | ~43M articles | Daily |
| Crossref | Incremental | Daily |
| arXiv | ~2.5M preprints | Daily |
| bioRxiv / medRxiv | ~1K/day | Daily |
| ClinicalTrials.gov | ~582K trials | Daily |
| Unpaywall | OA link resolution | Daily |
| DBLP | Computer science | Via OpenAlex |
| CORE | ~37M open access outputs | Coming soon |
| BASE (Bielefeld) | Discovery metadata | Via OpenAlex |
| DOAJ | Open access journals | Via Crossref |
| Papers with Code | ML/AI benchmarks | Weekly |
| Retraction Watch | Retraction status | Weekly |
| USPTO / EPO patents | ~9.3M patent-paper links | Daily |
| …and others |
All sources are cross-deduplicated on DOI, PMID, and arXiv ID. Total unique records after dedup: 340M+ (June 2026).
The search backend also maintains a biomedical knowledge graph (1.3M+ entities, 109M+ paper links) with genes, diseases, drugs, proteins, institutions, researchers, topics, genetic variants, and drug-target-disease relationships sourced from PubTator Central, DisGeNET, ChEMBL, UniProt, ROR, ORCID, Open Targets, and others.
| Tool | What it does |
|---|---|
search_papers | Full-text + semantic hybrid search with year/citation/source filters |
get_paper | Fetch metadata by DOI, PMID, arXiv ID, or OpenAlex ID |
find_similar | Find papers related by meaning, not just keyword matching |
get_citation_graph | Citation network — references and citing papers |
search_by_entity | Find papers linked to a gene, drug, disease, or institution via the KG |
create_literature_review | AI-generated structured lit review with citations (Pro) |
All usage requires a free NobleBlocks account. Sign up takes 30 seconds:
Free plan: 100 searches/day, 5 similar/day, citation graph access. Pro plan: 5,000 searches/day, literature review generation, priority support.
The easiest way to get started is the remote connector — no API keys, no Python install:
https://mcp.nobleblocks.com/mcpuvx nobleblocks-mcp
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": { "nobleblocks": { "command": "nobleblocks-mcp", "env": { "NOBLEBLOCKS_API_KEY": "nb_pk_your_key_here" } } } }
Restart Claude Desktop. The NobleBlocks tools will appear in the tools list.
Add to .vscode/mcp.json in your project:
{
"servers": { "nobleblocks": { "command": "nobleblocks-mcp", "env": { "NOBLEBLOCKS_API_KEY": "nb_pk_your_key_here" } } } }
Point your editor's MCP settings at the nobleblocks-mcp command with stdio transport. Set NOBLEBLOCKS_API_KEY in the environment.
You can also search directly from the terminal:
# Search papers
nobleblocks search "CRISPR base editing" --limit 5 --min-year 2022
nobleblocks get 10.1038/s41586-020-2649-2
nobleblocks similar "Attention Is All You Need"
nobleblocks citations 10.1038/s41586-020-2649-2 --direction both
All CLI commands require NOBLEBLOCKS_API_KEY set in your environment (or pass --key).
| Variable | Default | Description |
|---|---|---|
NOBLEBLOCKS_API_KEY | *(required)* | Your API key from nobleblocks.com |
NOBLEBLOCKS_API_BASE | https://www.nobleblocks.com | API endpoint |
LOG_LEVEL | INFO | Logging verbosity |
Once configured, ask naturally in Claude/Cursor:
"Find the most-cited papers on CRISPR base editing from 2022-2024"
"Show me papers similar to 'Attention Is All You Need' by Vaswani"
"What papers cite DOI 10.1038/s41586-020-2649-2?"
"Find papers linking BRCA1 to drug resistance"
"Generate a literature review on CAR-T cell therapy in solid tumors"
git clone https://github.com/nobleblocks/nobleblocks-mcp.git
cd nobleblocks-mcp pip install -e .
npx @modelcontextprotocol/inspector nobleblocks-mcp
MIT — see LICENSE.
Built by NobleBlocks — the academic research platform for the AI era.