Dhamma MCP server

• Registry namegift.dhamma/pali-canonverified in the MCP registry

The registry name sits under dhamma.gift. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-19
• Tools4
• Server calls itselfdg-node
• Server version1.2.0
• Protocol version2025-06-18

On 2026-10-19 the server answered initialize and tools/list without a sign-in. First answer in 509 ms.

• Its tools do read suttas across several Pali editions and translations, but not practise Pali grammar with drills and textbooks.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

• INITE MCP score75 of 100answers 100 · does the job 50 · definitions 83 · context 100 · use 8 · connects 100
• What an agent can do with it1 of 2 use cases
• Use1 GitHub stars
• Answered100% of days9 of 9 daily checks
• Median first answer501 ms
• Space in an agent's context≈ 1,174 tokensthe definitions of all its tools (4), which an agent carries on every turn
• Tool definitionsB · 83 of 100
• Typed results0 of 4 toolsdeclared outputSchema: results come typed, read once

• Not saying whether it only reads or can destroy: 4 of 4

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

• search

  Search the Pali Canon on dhamma.gift by keyword/substring or REGEX (min 3 letters, no semantic search). Patterns like "kata.*dukkha", "vucc.*dukkha", "katha.*dukkha" find the canon's own definitions and expositions of a term. Returns a…

• get_text

  Fetch a sutta by id (e.g. "dn22", "mn1", "sn56.11") — the Pali root text of every segment. Pali only by default; pass langs for translations, translators to name a translator (e.g. ["en_sujato"]). Same data as dhamma.gift/api/text.

• compare_translations

  One segment of the canon in the Pali root and every available translation side by side. Use a segment id from search/get_text, e.g. "mn129:21.3". Sujato (en_sujato) is excluded unless named in translators.

• list_structure

  What texts exist. Without arguments: collections (sutta/vinaya/abhidhamma/khuddaka), books by id prefix with sutta counts, and translation languages with translators. With prefix (e.g. "mn", "sn56", "an4"): the suttas under it with titles.