Skip to main content
Glama

philosophy-mcp

CI License: MIT

An MCP server for philosophy texts — both current scholarship and the canon. It folds these into one keyless server:

  • PhilPapers / PhilArchive — the philosophy preprint archive (the field's closest analog to arXiv): search papers, read abstracts, browse recent submissions, pull full text.

  • Books, classics & reference — public-domain originals and translations (Project Gutenberg, Internet Archive, Wikisource), open-access academic books (DOAB), modern editions (Open Library), and the Stanford Encyclopedia of Philosophy — plus a generic fetch_text for any other source (Zeno.org, marxists.org, Standard Ebooks, …).

  • Local documents — open a large local PDF or text file and work it without loading the whole thing into context: outline, in-file search, and paged reading.

No API key required. Everything runs against keyless public endpoints.

Renamed and expanded from philpapers-mcp (which covered only the PhilPapers tools). The philpapers-mcp binary name still works as an alias.

Tools

Philosophy scholarship (PhilPapers / PhilArchive)

Tool

What it does

Backend

search_papers

Keyword search (title/abstract/full text), returns metadata + PhilArchive links + PDF URL

OpenAlex, filtered to the PhilPapers Foundation source

research

One-shot scan: search and pull each hit's verbatim full abstract + subjects in a single call

OpenAlex + OAI-PMH GetRecord

get_paper

Canonical metadata + full abstract for one record id

PhilArchive OAI-PMH GetRecord

list_recent

Records added/updated in a date window

PhilArchive OAI-PMH ListRecords

fetch_pdf

Download a record's open-access PDF to disk, return the path

philpapers.org/archive/<ID>.pdf

get_fulltext

Download the open-access PDF and return its extracted full text

PDF + unpdf text extraction

PhilArchive is the open-access archive built on the PhilPapers database, so a record id such as BROTNO-9 resolves on both philarchive.org and philpapers.org.

Books, classics & reference

Tool

What it does

Source

search_gutenberg / get_gutenberg_text

Find and read public-domain classics + out-of-copyright translations

Project Gutenberg (Gutendex, with a gutenberg.org fallback)

search_internet_archive / get_archive_text

Find scanned, out-of-print works and read their OCR text

Internet Archive

search_wikisource / get_wikisource_text

Find and read primary texts/translations in any language (en, de, ko, …)

Wikisource

search_openlibrary

Modern editions & translations as metadata, with read/borrow links

Open Library

search_doab

Peer-reviewed, fully open-access academic books (readable in full)

DOAB

search_sep / get_sep_entry

Search and read the standard scholarly reference

Stanford Encyclopedia of Philosophy

fetch_text

Readable plain text from any URL — the catch-all for sources without a dedicated tool

any site

All text-returning tools (get_fulltext, the get_*_text readers, get_sep_entry, fetch_text) return one window — max_chars characters (default 15000) starting at offset (default 0). When the body is longer, the footer reports the next offset to continue from, so you page through a long work a window at a time instead of dumping it whole (and re-dumping from the start to read further). Each fetched/extracted body is cached, so paging doesn't re-download or re-parse the source.

Local documents

Tool

What it does

local_doc_info

Overview of a local PDF/text file — pages, characters, ~tokens, and a heuristic outline — without loading the whole file

local_doc_search

Find passages by keyword/regex and return just the matching snippets with page numbers

local_doc_read

Read a bounded page range / chunk, capped at max_chars so it can't flood context, reporting the next page to continue from

These read a large local file the way you'd skim a thick book — get an outline, jump to the relevant pages by searching, then read a chunk at a time — so only the parts that matter reach the context. Only files under $HOME are readable by default; add more roots via PHILOSOPHY_DOC_ROOTS.

Related MCP server: mcp-scholaris

Example

search_papers with { "query": "phenomenal consciousness higher-order", "open_access_only": true, "limit": 2 }:

Found 1,806 match(es) in PhilPapers/PhilArchive; showing 2 (open-access only).

1. The HOROR theory of phenomenal consciousness (2014)
   id: BROTNO-9
   authors: Richard Brown
   philarchive: https://philarchive.org/rec/BROTNO-9
   pdf: https://philpapers.org/archive/BROTNO-9.pdf

Then get_fulltext with { "id": "BROTNO-9" } returns the paper's extracted full text.

For the canon: search_gutenberg with { "query": "kant critique", "languages": "en" } returns book ids, and get_gutenberg_text with { "book_id": 4280 } reads The Critique of Pure Reason directly; search_sep → get_sep_entry reads an encyclopedia entry; fetch_text pulls readable text from German originals on Zeno.org or translations on marxists.org.

20th-century authors still in copyright (Heidegger, Adorno, Gadamer, Habermas) won't have free full texts here — you'll get metadata, SEP coverage, and read/borrow links.

Setup

Run straight with npx (no clone, once published):

npx -y philosophy-mcp

Or from source:

git clone https://github.com/sea9401/philosophy-mcp
cd philosophy-mcp
npm install   # the `prepare` hook builds dist/ automatically

Updating

dist/ is committed, so an existing source checkout updates with a plain pull — no build step:

cd philosophy-mcp
git pull

Then restart the MCP server (reconnect in Claude Code, or restart Claude Desktop) so it loads the new build. Maintainers: rebuild and commit dist/ whenever you change src/ — CI fails if the two drift.

Register with Claude Code

# via npx (no clone)
claude mcp add philosophy -- npx -y philosophy-mcp

# from a local build
claude mcp add philosophy -- node /absolute/path/to/dist/index.js

# optional: identify yourself to OpenAlex's "polite pool" for better rate limits
claude mcp add philosophy -e OPENALEX_MAILTO=you@example.com -- npx -y philosophy-mcp

Then /mcp inside Claude Code lists philosophy with its tools.

Register with Claude Desktop

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "philosophy": {
      "command": "node",
      "args": ["/home/sea9401/philpapers-mcp/dist/index.js"],
      "env": { "OPENALEX_MAILTO": "you@example.com" }
    }
  }
}

Environment variables

Var

Default

Purpose

OPENALEX_MAILTO

mcp@example.com

Your email — joins OpenAlex's polite pool (recommended).

PHILPAPERS_DOWNLOAD_DIR

<tmp>/philpapers-mcp

Where fetch_pdf saves files.

PHILOSOPHY_DOC_ROOTS

$HOME

Extra roots the local_doc_* tools may read (delimiter-separated absolute paths).

Smoke test

npm test   # builds, then runs smoke-test.mjs

smoke-test.mjs spawns the server over stdio, performs the MCP handshake, and verifies every expected tool is registered — no network calls, so it's the regression guard CI runs. (The older node test-client.mjs additionally exercises a couple of live PhilPapers calls.)

Notes & limits

  • The book/reference tools are keyless and read-only. Search tools return compact lists; the get_* / fetch_text tools return one max_chars window from offset and report the next offset to continue — page through long works instead of pulling them whole.

  • Gutendex (the Project Gutenberg API host) is frequently overloaded; search_gutenberg probes it briefly and falls back to gutenberg.org's OPDS feed. get_gutenberg_text reads the text directly from gutenberg.org, so it works even when Gutendex is down.

  • SEP has no keyword API (its on-site search is JavaScript-driven), so search_sep matches against the published entry index (contents.html) — i.e. title/topic matching.

  • list_recent filters on the OAI datestamp, returns only the first OAI page, and not every record has an open-access PDF — get_paper reports availability; fetch_pdf fails clearly.

Publishing (maintainers)

CI (.github/workflows/ci.yml) builds on Node 18/20/22 for every push and PR.

To publish a new version to npm:

  1. Add a repo secret NPM_TOKEN (an npm Automation access token) under Settings → Secrets and variables → Actions.

  2. Bump the version and tag: npm version patch && git push --follow-tags.

  3. Cut a GitHub Release — .github/workflows/publish.yml runs npm publish automatically.

Or publish manually: npm login then npm publish --access public.

License

MIT

Available Tools

17 tools
fetch_pdfDownload paper PDFA

Download the open-access PDF of a PhilArchive record and save it locally, returning the file path so it can be read. Accepts a record id or URL. Fails clearly if the paper has no open-access PDF. To get the text directly instead of a file, use get_fulltext.

Inputs: id (required), dest_dir.

fetch_textFetch readable text from any URLA

Fetch any URL and return its readable text — the catch-all for sources without a dedicated tool: Zeno.org and projekt-gutenberg.org (German originals), marxists.org (German Idealism to Frankfurt School translations), Standard Ebooks, a specific page, etc.

Inputs: url (required), max_chars.

get_archive_textRead Internet Archive OCR textA

Fetch the OCR full text of an Internet Archive item by identifier (from search_internet_archive). Truncated to max_chars.

Inputs: identifier (required), max_chars.

get_fulltextGet paper full textA

Download a PhilArchive record's open-access PDF and extract its full text, returned directly (no file needed). Accepts a record id or URL. Long papers are truncated to max_chars. Fails clearly if the paper has no open-access PDF.

Inputs: id (required), max_chars.

get_gutenberg_textRead a Project Gutenberg bookA

Fetch the plain-text body of a Project Gutenberg book by numeric id (from search_gutenberg). Truncated to max_chars.

Inputs: book_id (required), max_chars.

get_paperGet paper metadataA

Fetch canonical metadata for one PhilArchive/PhilPapers record via OAI-PMH. Accepts a record id (e.g. 'BROTNO-9'), a philarchive.org/philpapers.org /rec/ URL, or an oai: identifier. Returns title, authors, date, subjects, language, full abstract, the landing-page URL, and whether an open-access PDF is available.

Inputs: id (required).

get_sep_entryRead a Stanford Encyclopedia entryB

Fetch the text of a SEP entry. Accepts a slug (e.g. 'hegel'), a /entries/.. path, or a full URL. Truncated to max_chars.

Inputs: entry (required), max_chars.

get_wikisource_textRead a Wikisource pageA

Fetch the plain text of a Wikisource page by title (from search_wikisource). Truncated to max_chars.

Inputs: title (required), lang, max_chars.

list_recentList recent submissionsA

List recently added/updated PhilArchive records in a date window, via OAI-PMH (harvesting, not keyword search). Returns the first page of results (~up to limit). Dates are UTC YYYY-MM-DD; defaults to the last 7 days.

Inputs: from, until, limit.

researchResearch a topic (search + full abstracts)A

One-shot literature scan: runs a keyword search across PhilPapers/PhilArchive and, for each hit, fetches the archive's canonical metadata (verbatim full abstract, subjects, language) via OAI-PMH — so you get a ready-to-read digest in a single call instead of search_papers + get_paper per result. Returns fewer results than search_papers by default because it does more work per item.

Inputs: query (required), limit, year_from, year_to, +1 more.

search_doabSearch DOAB (open-access books)A

Search the Directory of Open Access Books — peer-reviewed, fully open-access academic books, including many modern philosophy monographs readable in full.

Inputs: query (required), limit.

search_gutenbergSearch Project Gutenberg (public-domain classics)A

Search Project Gutenberg for public-domain classics and out-of-copyright translations (Kant, Hegel, Nietzsche, Schopenhauer, Marx, Fichte, ...). Returns title, author, languages, a Gutenberg page link, and download URLs. Use the numeric id with get_gutenberg_text.

Inputs: query, author, topic, languages, +1 more.

search_internet_archiveSearch the Internet ArchiveA

Search the Internet Archive for scanned, out-of-print monographs, journals, and translations. Use the returned identifier with get_archive_text.

Inputs: query (required), limit, mediatype.

search_openlibrarySearch Open LibraryA

Search Open Library for books — strong for modern editions and translations as metadata, with read/borrow links wherever a scan exists.

Inputs: query (required), author, limit.

search_papersSearch philosophy papersA

Keyword search across PhilPapers / PhilArchive (philosophy preprints and published papers indexed by the PhilPapers Foundation), powered by OpenAlex full-text search. Returns title, authors, year, a short abstract, the PhilArchive record id + URL, and an open-access PDF URL when one exists. Use the returned id with get_paper, research, or fetch_pdf. For a richer one-shot digest with full abstracts, use research instead.

Inputs: query (required), limit, year_from, year_to, +1 more.

search_sepSearch the Stanford Encyclopedia of PhilosophyA

Search SEP (the standard scholarly reference) by matching its full entry index. Read an entry with get_sep_entry.

Inputs: query (required), limit.

search_wikisourceSearch WikisourceB

Search Wikisource for primary texts and translations (en, de, ko, ...). Use get_wikisource_text to read.

Inputs: query (required), lang, limit.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 17 tools

    Disambiguation4/5

    Most tools have distinct purposes, but some overlap exists: fetch_pdf and get_fulltext both retrieve PhilArchive PDFs (file vs text), and fetch_text is a catch-all that could be confused with specific source tools. However, descriptions clarify differences.

    Naming Consistency3/5

    Naming conventions are mixed: some use 'get_', some 'fetch_', some 'search_', plus 'list_recent' and 'research'. While readable, the inconsistency in verb choice could cause confusion.

    Tool Count4/5

    With 17 tools, the count is slightly above the typical well-scoped range, but each tool serves a clear purpose for different text sources and operations. No tool feels redundant.

    Completeness4/5

    The tool set covers a wide range of philosophical text sources (PhilArchive, SEP, Gutenberg, Internet Archive, Wikisource, etc.) with search and retrieval capabilities. Minor gaps exist (e.g., no unified multi-source search), but overall coverage is strong for the domain.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Semantic search over 4.6 million text chunks from 20,000+ classical philosophy and humanities works (pre-1928). Covers Aristotle, Plato, Kant, Hegel, Nietzsche and hundreds more. Multilingual: English, German, Latin, French, Italian, Greek, Russian.
      3
      3
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Searches and retrieves academic papers from open access sources like arXiv, Semantic Scholar, and PubMed, with full text access via arXiv PDFs, PubMed Central, and Unpaywall.
      2
      MIT
    • A
      license
      B
      quality
      D
      maintenance
      Enables scholarly search, paper metadata, citation graphs, author and venue resolution, candidate harvesting, API quota visibility, and guarded full-text downloads through the OpenAlex API.
      9
      4
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Provides free, no-key open-access lookup for scholarly papers via Unpaywall. Enables querying article metadata and open-access status through natural language.
      281 npm
      1
      MIT