Tripitaka MCP Server

An MCP Server for searching and citing content from the Pāli Tipiṭaka. Gives AI agents (such as Claude or Cursor) the ability to look up suttas

Remote serverstreamable-httpPython

What is the Tripitaka MCP MCP server?

An MCP Server for searching and citing content from the Pāli Tipiṭaka. Gives AI agents (such as Claude or Cursor) the ability to look up suttas, quote the teachings, and compare translations across languages. Exposed over MCP by the tripitaka mcp mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

Its toolset

Everything the assistant can do here goes through one of these:

  • search_hybrid(Recommended for concept search) Combined keyword + semantic via RRF — best when looking for "discourses about X"
  • search_by_keyword — Trigram keyword search — best for the top few matches of an exact word (appamāda, ānāpānassati)
  • survey_corpusExhaustive corpus survey — exact total + per-pitaka breakdown + the matched word-forms, for "how many times / every place X appears" (coverage
  • search_semantic — Pure vector similarity — usually you want search_hybrid instead
  • get_sutta — Fetch a sutta by ID (e.g. mn1, dn22, dhp1-20) with cross-reference URLs. Whole sutta by default; for long ones use mode="outline" (table of contents
  • open_sutta_viewerInteractive sutta viewer (MCP Apps) — renders the sutta inline in the chat as Pāli + English side by side, with the cited segment highlighted
  • get_reference — Generate a properly formatted academic citation with all source URLs
  • compare_translations — Compare renderings of a single segment across editions
  • list_structure — Show the Tipiṭaka structure with segment-count coverage per nikāya
  • list_editions — List Thai/English translation editions currently loaded
  • get_word_definition — Pāli dictionary lookup (PTS, DPPN, and the Payutto Thai dictionary)
  • parse_pali_word — Strip Pāli suffixes to recover the root form when get_word_definition misses (bhikkhūnaṁ → bhikkhu)

Adding it to your client

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Configuration

You will need one environment variable: YOUR_NPX_PATH. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

When to reach for it

Among the knowledge and memory options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Tripitaka MCP's toolset — search_hybrid, search_by_keyword, survey_corpus and 9 more — is a fair guide to whether it matches your workflow. It is maintained by dhamma-seeker; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Tripitaka MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Caveats

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 12 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Tripitaka MCP.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the tripitaka mcp mcp server does with a few real requests.

Available tools

ToolWhat it does
search_hybrid**(Recommended for concept search)** Combined keyword + semantic via RRF — best when looking for "discourses about X".
search_by_keywordTrigram keyword search — best for the top few matches of an exact word (appamāda, ānāpānassati).
survey_corpus**Exhaustive** corpus survey — exact total + per-pitaka breakdown + the matched word-forms, for "how many times / every place X appears" (coverage, not just best matches). mode=thorough adds concept-level semantic recall
search_semanticPure vector similarity — usually you want search_hybrid instead.
get_suttaFetch a sutta by ID (e.g. mn1, dn22, dhp1-20) with cross-reference URLs. Whole sutta by default; for long ones use mode="outline" (table of contents, no text), around="<segment_id>"+window (context around a hit), or segm
open_sutta_viewer**Interactive sutta viewer (MCP Apps)** — renders the sutta inline in the chat as Pāli + English side by side, with the cited segment highlighted. The calling model can attach an AI translation of the displayed segments
get_referenceGenerate a properly formatted academic citation with all source URLs.
compare_translationsCompare renderings of a single segment across editions.
list_structureShow the Tipiṭaka structure with segment-count coverage per nikāya.
list_editionsList Thai/English translation editions currently loaded.
get_word_definitionPāli dictionary lookup (PTS, DPPN, and the Payutto Thai dictionary).
parse_pali_wordStrip Pāli suffixes to recover the root form when get_word_definition misses (bhikkhūnaṁ → bhikkhu).

How to install the Tripitaka MCP MCP server

{
  "mcpServers": {
    "tripitaka": {
      "command": "npx",
      "args": ["-y", "bridge"],
      "env": {
        "YOUR_NPX_PATH": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
YOUR_NPX_PATHFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Tripitaka MCP to search hybrid.
  • Use Tripitaka MCP to search by keyword.
  • Use Tripitaka MCP to survey corpus.

Frequently asked questions

It connects Tripitaka MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 12 tools (search_hybrid, search_by_keyword, survey_corpus, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Tripitaka MCP directly.