Alexandria MCP server
Search, read, and cite across 152 libraries: 11 tools, 3 prompts, and a full-text resource.
2 stars28 downloads/wk
Reviews
Write oneNobody has reviewed Alexandria yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Alexandria tools (13)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
library_answerAsk a question in plain English and get a synthesized answer with inline [n] citations, fused across sources with reciprocal rank fusion. Use this instead of library_ask when you want a cited answer rather than raw results. Every factual sentence is cited or dropped; an uncited or all-dropped answer is flagged in warnings[]. Requires OPENAI_API_KEY (or ALEXANDRIA_SYNTH_API_KEY). Set response_forma
library_askAsk for content in plain English; automatically selects the best sources from all … libraries, generates optimized per-source queries, and searches in parallel. Use this as the default entry point for any natural-language request. Use library_search instead when you already know which source to query. Requires OPENAI_API_KEY (already set for embeddings). Set response_format: "detailed" for routing
library_citationsList the works a scholarly item cites (direction: "references") or the works that cite it (direction: "citations"), resolved through OpenAlex's citation graph with OpenCitations as a fallback when OpenAlex has no record. Accepts an id/source from library_search or library_ask, or a bare DOI/arXiv id. Set format: "bibtex" | "ris" | "apa" to also return a `formatted` bibliography string; BibTeX pref
library_health_checkReport per-source health: 'ok', 'degraded', 'down', 'key_missing', or 'unknown', merging this process's live error rate and latency with the last off-process probe run. The probe layer reads eval/probe-latest.json, which published installs do not ship, so on a published install a source's status stays 'unknown' until this process itself calls it. Use before relying on a source that has been errori
library_indexDry run: fetch text, chunk semantically, score OCR quality. No writes. Full-text sources only.
library_ingestChunk, embed, and store a text. Idempotent. Full-text sources only. Requires OPENAI_API_KEY + SUPABASE_URL + SUPABASE_SERVICE_ROLE_KEY.
library_list_sourcesList all … library sources (count computed from the live registry at startup) with descriptions and capabilities.
library_readFetch text from a library source. Full-text sources return cleaned text (truncated at 200k chars). Metadata sources return item details and an external URL.
library_recommendGet papers similar to a given paper using Semantic Scholar's recommendation engine. Pass a paperId from a semanticscholar search result. Returns up to 500 similar papers.
library_researchDeep research on a topic: outlines 3 to 7 coverage objectives, generates search queries, answers each with library_answer, extracts learnings and follow-up questions, then recurses with half the breadth. Stops once every objective is covered by a learning, at the given depth, at the time budget, or once a round finds no new sources. Requires OPENAI_API_KEY (or ALEXANDRIA_RESEARCH_API_KEY / ALEXAND
library_searchSearch a specific library source by name. Use library_ask instead for natural language queries across multiple sources. Sources marked [full text] support library_read and library_ingest. Sources marked [metadata] return discovery info and external URLs only.
readfake read
searchfake search
Public scan report
scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it
- Code scan393 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 40 days ago12/15
- Maintainer identityregistry namespace matches repository owner7/10
How Alexandria compares
Against every graded Web search MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 77/100
- higher than 55% of 3,470 Web search servers
- Tools
- 13
- the typical Web search server has 5
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 2
- more than 70% of 1,786 Web search servers
- Downloads a week
- 28
- more than 14% of 827 Web search servers with a package
What its tools let an agent do: 13 read
Install Alexandria in Claude Code, Cursor or VS Code
Runs npx -y @the-40-thieves/alexandria-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add alexandria-mcp -- npx -y @the-40-thieves/alexandria-mcp
What the publisher says
From the Alexandria repository's README, as published. We do not edit it. Read it on GitHub
Alexandria
Install in Goose
A Model Context Protocol (MCP) server for querying, reading, and ingesting texts from 152 public digital libraries. Works with any MCP-compatible client (Claude Desktop, Cursor, VS Code Copilot, etc.).
Tools
libraryask is the primary entry point. librarysearch is for targeted queries against a known source. libraryindex / libraryingest are for building a vector knowledge base from retrieved texts. libraryanswer and libraryresearch synthesize a cited answer or report instead of returning raw results. libraryhealthcheck tells you whether a source is worth calling before you call it. library_citations walks the citation graph around an item and can export it as a bibliography.
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Alexandria: common questions
- Is Alexandria MCP server safe?
- Mostly: it is graded B (77/100). Read the Alexandria safety report
- How do I install Alexandria?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Alexandria need an API key?
- Yes. The registry entry asks for
OPENAI_API_KEY,ALEXANDRIA_API_KEY,CORE_API_KEY,COURTLISTENER_API_KEYand 6 more. - Is Alexandria maintained?
- The last commit was 58 days ago (2026-09-07). The latest release is v11.0.0.
- What can I use instead of Alexandria?
- Servers from other publishers that do the same job: Arxiv MCP server, Pubmed MCP server and Jshookmcp MCP server.
- How does Alexandria compare with other Web search MCP servers?
- safety score 77/100 (higher than 55% of 3,470 Web search servers); tools 13 (the typical Web search server has 5); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Alexandria
Same job from other publishers: the closest match first, then the best rated.
- ArxivSearch arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP.not reviewedWidely usedA
- PubmedSearch PubMed/Europe PMC, fetch articles and full text (PMC/EPMC/Unpaywall), citations, MeSH terms.not reviewedEstablishedA
- JshookmcpSearch-first MCP server for JavaScript reverse engineering: 735 tools across 36 domains.not reviewedEstablishedC
- Sui Knowledge Base (kapa.ai)Semantic search across Sui documentation and knowledge sources, powered by kapa.ainot reviewedEstablishedA
Free SearchNo-API-key web search, page fetching and document reading across many engines. Local-first.not reviewedEstablishedB