Nobleblocks Mcp

nobleblocks/nobleblocks-mcp

A remote-first MCP server that connects Claude, Cursor, and other tools to 340 million deduplicated academic papers from OpenAlex, PubMed, Semantic Scholar, arXiv, and 15+ other sources. It exposes six tools: hybrid full-text and semantic search with citation filters, paper metadata lookup by DOI or PMID, similarity search, bidirectional citation graph traversal, knowledge graph queries linking papers to 1.3 million biomedical entities (genes, drugs, diseases), and AI-generated literature reviews on Pro plans. The backend handles all indexing and vector search, so you just need an API key. Useful when you're doing research, writing grants, validating claims, or need citation networks without leaving your editor.

GitHub stars: 1
tools: 11
transport: HTTP
last updated: Jun 5, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://mcp.nobleblocks.com/mcp --name nobleblocks-mcp

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

$ claude mcp add --transport http nobleblocks-mcp https://mcp.nobleblocks.com/mcp

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 11 tools

Verified live against the running server on Nov 6, 2026.

search_papersSearch the NobleBlocks index of scholarly papers by keyword relevance, with filters. Each result has title, authors, year, journal, DOI, citation count, an abstract excerpt, a NobleBlocks link and `best_link` (free full text when known, else the DOI/ARK). Use get_paper with a...9 params

Search the NobleBlocks index of scholarly papers by keyword relevance, with filters. Each result has title, authors, year, journal, DOI, citation count, an abstract excerpt, a NobleBlocks link and `best_link` (free full text when known, else the DOI/ARK). Use get_paper with a...

Parameters* required

languagevalue

Two-letter language code, e.g. 'en'.

limitinteger

Number of results (1-50; your access tier may cap it lower).default: 10

min_citationsvalue

Only papers cited at least this many times.

offsetinteger

Skip this many results (paging).default: 0

query*string

Topic, question, title words or author name. Supports AND / OR / NOT and "quoted phrases".

sortstring

relevance (default), date (newest first) or citations.one of relevance · date · citationsdefault: relevance

sourcevalue

Only records from this source.

year_fromvalue

Only records published in or after this year.

year_tovalue

Only records published in or before this year.

search_trialsSearch clinical trial registrations (ClinicalTrials.gov or WHO ICTRP) held in the NobleBlocks index. Each result carries its registry id (`trial_id`, e.g. NCT01234567). Use get_paper with that id for the full record.6 params

Search clinical trial registrations (ClinicalTrials.gov or WHO ICTRP) held in the NobleBlocks index. Each result carries its registry id (`trial_id`, e.g. NCT01234567). Use get_paper with that id for the full record.

Parameters* required

limitinteger

Number of results (1-50; your access tier may cap it lower).default: 10

offsetinteger

Skip this many results (paging).default: 0

query*string

Condition, intervention, sponsor or title words.

registrystring

clinicaltrials (ClinicalTrials.gov, default) or ictrp (WHO ICTRP registries).one of clinicaltrials · ictrpdefault: clinicaltrials

year_fromvalue

Only records published in or after this year.

year_tovalue

Only records published in or before this year.

get_paperFull metadata for one paper or trial: authors, journal, volume/issue/pages, identifiers (DOI, PMID, arXiv, OpenAlex, trial id, NobleID ARK when confirmed), retraction status, open access link, citation count, abstract and links (`links.best` is open access first).1 params

Full metadata for one paper or trial: authors, journal, volume/issue/pages, identifiers (DOI, PMID, arXiv, OpenAlex, trial id, NobleID ARK when confirmed), retraction status, open access link, citation count, abstract and links (`links.best` is open access first).

Parameters* required

identifier*value

A NobleBlocks paper id (the `id` from a search), a DOI (10.xxxx/...), a NobleID ARK (ark:/48914/...), an OpenAlex id (W...), 'pmid:<number>', 'arxiv:<id>' or a trial registry id (NCT...).

get_citing_papersPapers in the NobleBlocks index that cite this paper, most cited first. Citation links are still being loaded, so an empty answer is reported as such, not as 'never cited'.3 params

Papers in the NobleBlocks index that cite this paper, most cited first. Citation links are still being loaded, so an empty answer is reported as such, not as 'never cited'.

Parameters* required

identifier*value

A NobleBlocks paper id (the `id` from a search), a DOI (10.xxxx/...), a NobleID ARK (ark:/48914/...), an OpenAlex id (W...), 'pmid:<number>', 'arxiv:<id>' or a trial registry id (NCT...).

limitinteger

Number of results (1-50; your access tier may cap it lower).default: 10

offsetinteger

Skip this many results (paging).default: 0

get_referencesPapers this paper cites (its reference list) that are in the NobleBlocks index, most cited first.3 params

Papers this paper cites (its reference list) that are in the NobleBlocks index, most cited first.

Parameters* required

identifier*value

A NobleBlocks paper id (the `id` from a search), a DOI (10.xxxx/...), a NobleID ARK (ark:/48914/...), an OpenAlex id (W...), 'pmid:<number>', 'arxiv:<id>' or a trial registry id (NCT...).

limitinteger

Number of results (1-50; your access tier may cap it lower).default: 10

offsetinteger

Skip this many results (paging).default: 0

search_authorsFind researchers by name. Returns name, ORCID iD, OpenAlex id, affiliation and reported counts. Use get_author with an ORCID iD for the profile and top papers.3 params

Find researchers by name. Returns name, ORCID iD, OpenAlex id, affiliation and reported counts. Use get_author with an ORCID iD for the profile and top papers.

Parameters* required

limitinteger

Number of results (1-50; your access tier may cap it lower).default: 10

name*string

Author name or part of it.

offsetinteger

Skip this many results (paging).default: 0

get_authorOne researcher's public profile by ORCID iD: name, affiliation, topics, reported metrics, NobleID when recorded, and their most cited papers in the index.2 params

One researcher's public profile by ORCID iD: name, affiliation, topics, reported metrics, NobleID when recorded, and their most cited papers in the index.

Parameters* required

orcid*string

ORCID iD, bare (0000-0002-1825-0097) or as an orcid.org URL.

papersinteger

How many of the author's most cited papers to include (0-50).default: 10

get_citationFormat a citation for one paper as BibTeX, RIS or APA 7. The URL is the paper's NobleID ARK when it has a confirmed one, else its DOI. DOIs known to be unreliable are left out rather than guessed.2 params

Format a citation for one paper as BibTeX, RIS or APA 7. The URL is the paper's NobleID ARK when it has a confirmed one, else its DOI. DOIs known to be unreliable are left out rather than guessed.

Parameters* required

formatstring

bibtex, ris or apa (APA 7, plain text).one of bibtex · ris · apadefault: bibtex

identifier*value

A NobleBlocks paper id (the `id` from a search), a DOI (10.xxxx/...), a NobleID ARK (ark:/48914/...), an OpenAlex id (W...), 'pmid:<number>', 'arxiv:<id>' or a trial registry id (NCT...).

citeCitations for several papers at once, in one format, in the order given. Each entry links to the ARK or DOI; failures are listed per identifier instead of failing the whole call.2 params

Citations for several papers at once, in one format, in the order given. Each entry links to the ARK or DOI; failures are listed per identifier instead of failing the whole call.

Parameters* required

formatstring

bibtex, ris or apa.one of bibtex · ris · apadefault: bibtex

identifiers*array

1-50 paper identifiers (same forms as get_paper). Your access tier may allow fewer.

searchSearch scholarly papers and return citable results as {results: [{id, title, url}]}. `url` is open access first. Pass an `id` to fetch for the full text record.1 params

Search scholarly papers and return citable results as {results: [{id, title, url}]}. `url` is open access first. Pass an `id` to fetch for the full text record.

Parameters* required

query*string

What to look for.

fetchFetch one paper as {id, title, text, url, metadata}. `text` is the abstract plus a formatted citation; `url` is open access first.1 params

Fetch one paper as {id, title, text, url, metadata}. `text` is the abstract plus a formatted citation; `url` is open access first.

Parameters* required

id*string

An id from search, or any identifier get_paper accepts.

Readme

NobleBlocks MCP Server

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.

What's in the index

View the full README on GitHub

Details

Repository: github.com/nobleblocks/nobleblocks-mcp
Category: Search & Web Crawling
Transport: HTTP
Registry: MCP registry, active
Tools verified: Nov 6, 2026

Related Search & Web Crawling MCP servers

View all

GitLab Documentation MCP Servernunolima/gitlab-docs-mcpSearchable access to GitLab documentation from multiple repositories with full-text search.1stars

Claude Memory Managernyxtoolsdev/claude-memory-managerCross-session memory for Claude Code — context capture, semantic search, recall1stars

Tender MCPojaskord/tender-mcpGovernment tender search for AI agents. UK, EU and US procurement opportunities.1stars

Spresh Mcpprashantbtkl/spresh-mcpSearch Facebook ads, decode competitor creative strategy, and track brand ad history.1stars

Quotewisequotewise/mcpSemantic quote search with 600K quotes. Find quotes by meaning, verify attributions.0stars

Murphys Lawsravidorr/murphys-lawsAccess thousands of Murphy's Laws: search, browse by category, random, daily, submit.1stars