fojin — Buddhist Canon Tools by fojin.app

MCP server · indexed, not reviewed

Hostedvendor's ownwidely used

Not reviewed

No score, grade or rank. This listing is facts from the official MCP registry and our own checks, and it stays out of the rankings until the panel reviews it.

How the index works

Buddhist canon tools: search, passages, cross-canon parallels, dictionaries — all URN-cited.

What the official MCP registry says

Facts

MCP registry
app.fojin/fojin-mcp · 0.4.0
Endpoint
https://mcp.fojin.ai/mcp
Website
fojin.app
GitHub stars
345
Registry entry
updated 10 Aug 2026

From the official MCP registry, the package registries and our own checks. JSON · Markdown

Why it's listed

  • It's published in the registry under fojin.app, a namespace the registry only gives to whoever proves they control that domain.
  • It's in real use: 345 GitHub stars.

Being indexed says nothing about quality, and nobody can pay for it. Is this yours? Ask for a review.

Tools it lists 8 · about 1,401 tokens of context · checked 4 hours ago

ToolWhat it doesHint
search_corpusSemantic search across fojin's Buddhist corpus (10K+ texts, 30+ langs). Returns the most relevant passages, each with a `urn`, title, snippet and similarity score. `lang` optionally filters by language code…
read_passageRead the full content of one fascicle (卷) of a text, with its `urn`. Use the `text_id`/`juan_num` from a search_corpus hit. Returns the actual canonical text — quote from this, not from memory.
get_parallelsCross-canon parallel passages aligned to a fascicle. fojin's alignment moat: given a Chinese fascicle, returns the aligned Pali/Tibetan/Sanskrit parallels so you can compare how a passage is rendered across traditions.…
lookup_dictionaryLook up a Buddhist term across fojin's dictionaries (748K+ entries).
lookup_entitySearch fojin's knowledge graph for entities — people, places, works, doctrinal terms — matching `query`.
resolve_urnResolve a fojin URN (e.g. fojin:cbeta/T0001.1) to a reader URL and confirm it exists in the corpus. Use to verify or dereference a citation.
verify_quoteVerify that a Buddhist-canon quote exists VERBATIM in the corpus. Call this before presenting any quoted scripture to a reader: LLMs routinely invent plausible-looking quotes. Returns `verbatim` (bool), where it was…
commentariesWhat the historical commentators said about a passage of Buddhist scripture. Give a line of a sūtra and get back the classical commentaries that gloss it — each with the commentator's own words, the work it comes from,…

What https://mcp.fojin.ai/mcp answered to tools/list, asked without credentials over MCP 2026-07-28. The token figure is the size of the list as sent, divided by four; a model sees about that much before it calls anything. Full definitions, input schemas included, are in the listing's JSON under mcpTools.

How its tools read to an agent 0 errors · 16 warnings · 2 notes

  • warnTC11commentariesnone of its 2 parameters has a description
  • warnTC11get_parallelsnone of its 2 parameters has a description
  • warnTC11lookup_dictionarynone of its 2 parameters has a description
  • warnTC11lookup_entitynone of its 2 parameters has a description
  • warnTC11read_passagenone of its 2 parameters has a description
  • warnTC11resolve_urnits one parameter, urn, has no description
  • warnTC11search_corpusnone of its 3 parameters has a description
  • warnTC11verify_quotenone of its 3 parameters has a description
  • warnTC16commentariesno readOnlyHint or destructiveHint
  • warnTC16get_parallelsno readOnlyHint or destructiveHint
  • warnTC16lookup_dictionaryno readOnlyHint or destructiveHint
  • warnTC16lookup_entityno readOnlyHint or destructiveHint
  • warnTC16read_passageno readOnlyHint or destructiveHint
  • warnTC16resolve_urnno readOnlyHint or destructiveHint
  • warnTC16search_corpusno readOnlyHint or destructiveHint
  • warnTC16verify_quoteno readOnlyHint or destructiveHint
  • noteTC24server8 of 8 tools have no outputSchema
  • noteTC29serverabout 141 tokens (10% of the definitions) are titles that repeat property or function names

The checks from /check and anchor check, run each day on the list above: about 1,401 tokens of definitions. Not part of the score yet. Check your own server.

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.