alexandria
Skill3 starsChanged 11 days agoMITView on GitHub
Reach for this when a research question needs cited sources across academic papers, public domain books, legal records, government archives, security advisories, news, or developer documentation. Alexandria is an MCP server backed by 152 public digital libraries; use it whenever an answer should point at real, checkable sources rather than come from memory alone.
- Reads credentials
1 other project uses a version of this.
Adopted by
Most recently taken up by
- agentik-os/claude-code-skillstheir own version, first seen Sep 17, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- agentik-os/claude-code-skills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 0 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 23
Search and read need no credentials.
- Very specific: line 29
Start with library_ask(query) - it routes a natural-language question to the best sources and searches them in parallel.
- Very specific: line 47
If a source looks like it is misbehaving (no results, stale data, repeated errors), call library_health_check(source?, cluster?) before …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Alexandria
Query, read, and ingest texts from 152 public digital libraries through the
@the-40-thieves/alexandria-mcp MCP server.
Install
npx -y @the-40-thieves/alexandria-mcpOr add it to a client directly, for example Claude Code:
claude mcp add alexandria -- npx -y @the-40-thieves/alexandria-mcpSearch and read need no credentials. library_ask, library_answer,
library_research, and library_ingest need OPENAI_API_KEY; see the
README for the full list of optional keys.
Workflow
Start with library_ask(query) - it routes a natural-language question to
the best sources and searches them in parallel. Use library_search(query,
source, limit?) instead when you already know which of the 152 sources to
query.
Once a result names a source/id pair, library_read(id, source) fetches
the full text.
For a synthesized, cited answer instead of raw results, use
library_answer(query) for a single question or library_research(query,
depth?, breadth?, max_minutes?) for a recursive multi-round report that
generates its own follow-up queries.
library_citations(id, source, direction, limit?, format?) walks the
citation graph around an item forward (direction: "citations") or backward
(direction: "references") for snowball searching, and can export the
result as a bibtex, ris, or apa bibliography.
If a source looks like it is misbehaving (no results, stale data, repeated
errors), call library_health_check(source?, cluster?) before trusting or
retrying it.
response_format
library_ask, library_search, library_answer, library_research, and
library_health_check take response_format: "concise" | "detailed"
(default concise). concise returns the high-signal fields only (title,
source, id, year, hasFullText, url; the answer/report plus citations; health
name, cluster, status). detailed adds routing reasons, relevance scores,
per-stage diagnostics, and per-source error rate, latency, and quota usage -
ask for it when you need to explain or debug a result, not by default.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

