
This is a keyless gateway to Jisho.org's Japanese-English dictionary data, hosted by Pipeworx. The source doesn't list specific tools, but it's built for querying Japanese word definitions, kanji lookups, and translations without managing API keys yourself. You can call tools directly or use the ask_pipeworx interface to query in plain English and let the gateway route to the right endpoint. It's part of a larger gateway offering 780+ data sources, so you can add just the Jisho endpoint or connect to the full Pipeworx hub. Useful when you're building language learning tools, translation features, or anything that needs programmatic access to Japanese dictionary data without the authentication overhead.
Jisho.org Japanese-English dictionary MCP (keyless).
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
| Tool | Description |
|---|---|
search_words | Search the Jisho.org Japanese<->English dictionary. The keyword can be English (translate to Japanese), Japanese kanji/kana, or romaji. Returns up to limit matching dictionary entries, each with the headword (slug), whether it is a common word, JLPT level, all readings/spellings, and English meanings grouped into senses with parts of speech. Use this to translate, look up a kanji/kana word, or find Japanese words for an English concept. |
lookup | Look up a single Japanese or English word in the Jisho.org dictionary and return only the single best/first matching entry in a compact form: headword (slug), common-ness, JLPT level, all readings, a flat list of English meanings, and the unique parts of speech. Best for quick "what does this word mean / how is it read" questions. Accepts kanji, kana, romaji, or English. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"jisho": {
"url": "https://gateway.pipeworx.io/jisho/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/jisho/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Jisho data" })
The gateway picks the right tool and fills the arguments automatically.
MIT
curl -X POST https://gateway.pipeworx.io/v1/tools/search_words \
-H 'Content-Type: application/json' \
-d '{"keyword":"house"}'
No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/search_words. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.