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

Tool	Description
library_list_sources	List all 152 sources with descriptions and full-text capabilities
library_ask(query, max_sources?, results_per_source?)	Natural language search — routes your query to the best sources, searches in parallel, returns unified deduplicated results
library_search(query, source, limit?)	Search a specific source by title, author, or keywords
library_read(id, source)	Fetch full text or metadata for an item (200k char limit)
library_index(id, source)	Dry run: chunk and score text quality without writing anything
library_ingest(id, source)	Chunk → embed → store in your vector database. Idempotent.
library_recommend(id, limit?)	Get similar papers via Semantic Scholar's recommendation engine (up to 500)
library_answer(query, max_sources?, results_per_source?, read_top?)	Ask a question and get a synthesized answer with inline [n] citations, fused across sources with reciprocal rank fusion; warnings[] flags an uncited or all-dropped answer
library_research(query, depth?, breadth?, max_minutes?)	Recursive multi-round research: generates queries, answers each, extracts learnings, and writes a final cited report over every source found
library_health_check(source?, cluster?)	Report per-source health (ok, degraded, down, key_missing, unknown), merging this process's live error rate/latency with the last off-process probe run
library_citations(id, source, direction, limit?, format?)	List the works an item cites (direction: "references") or the works that cite it (direction: "citations"), via OpenAlex's citation graph with OpenCitations as a fallback; format: "bibtex" | "ris" | "apa" also returns a formatted bibliography string

library_ask is the primary entry point. library_search is for targeted queries against a known source. library_index / library_ingest are for building a vector knowledge base from retrieved texts. library_answer and library_research synthesize a cited answer or report instead of returning raw results. library_health_check 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.

library_ask, library_search, library_answer, library_research, library_health_check, and library_citations take a response_format: "concise" | "detailed" parameter (default concise); concise trims results and citations to the high-signal fields (title, source, id, year, hasFullText, url; answer/report + citations; name, cluster, status), detailed returns the full payload, including routing reasons, relevance scores, per-stage diagnostics, and per-source error rate/latency/quota usage. In detailed mode, library_search also attaches a resource_link content item for each full-text result, pointing at that item's library://doc/{source}/{id} resource (see below): a client with resource support can read the full text directly instead of a second library_read call.

Prompts

Three ready-made research workflows, surfaced by MCP clients as slash commands (Claude Code's /alexandria:<name>, VS Code's /alexandria.prompt). Each returns a single message naming the tools to call, in order. It does not call any tool itself.

Prompt	Description
literature_review(topic, depth?)	Survey a topic across sources and produce a cited report
fact_check_claim(claim)	Check one claim against the library and report whether it is supported
verify_bibliography(references)	Check that a list of references (one per line) resolves to real, findable items

Resources

library://doc/{source}/{id} reads the same text library_read(id, source) returns (including the open-access fallback below), addressed by the source/id pair library_search or library_ask returned. Clients that support MCP resources (Claude Code's @srv:uri, VS Code's Add Context) can pull an item's full text directly.

Sources (152)

152 sources across 19 clusters (36 hidden pending a key or config not present in this deployment). Full per-source detail, including auth env vars and last-verified dates, is generated in docs/sources.md.

以上为 README 的开头部分。其余内容请阅读原文。 查看完整 README ↗