WaniKani for AI agents

WaniKani teaches Japanese kanji and vocabulary through spaced repetition, used by learners tracking review progress and study material. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

EducationAPI keyMCP + RESTwanikani.com
AUDIT LOG · WANIKANIPOLICY: acme-support
09:41:07 · claude · u_8f2read
wanikani.get_user
Get User✓ allowed · 212ms
09:41:08 · claude · u_8f2read
wanikani.get_resets
Get Resets✓ allowed · 164ms
09:41:09 · claude · u_8f2write
wanikani.create_study_material
Create Study Material✓ approved · approved by user
EVERY WANIKANI CALL, ON THE RECORD
01 · USE CASES

What agents do in WaniKani.

01

Get pending reviews

Pull items due for review as a read-only check before a study session.

02

Submit a review result

Record whether a review answer was correct, updating that item's progress.

03

Get study summary

Read the current lesson and review counts as a read-only progress check.

02 · ACTIONS

16 WaniKani actions, graded by risk.

Every WaniKani action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

11

Look things up. Allowed by default.

  • wanikani.get_user
    Get User
  • wanikani.get_resets
    Get Resets
  • wanikani.get_reviews
    Get Reviews
  • wanikani.get_subjects
    Get Subjects
  • wanikani.get_assignments
    Get Assignments
  • wanikani.get_voice_actors
    Get Voice Actors
  • wanikani.get_study_summary
    Get Study Summary
  • wanikani.get_study_materials
    Get Study Materials
  • wanikani.get_review_statistics
    Get Review Statistics
  • wanikani.get_level_progressions
    Get Level Progressions
  • wanikani.get_spaced_repetition_systems
    Get Spaced Repetition Systems

write

5

Create and change things. Allow, or ask the user first.

  • wanikani.create_study_material
    Create Study Material
  • wanikani.update_study_material
    Update Study Material
  • wanikani.update_user_preferences
    Update User Preferences
  • wanikani.submit_review
    Submit Review
  • wanikani.start_assignment
    Start Assignment

destructive

0

Delete, cancel or archive. Ask first, or deny outright.

  • No destructive actions.
03 · HOW IT WORKS

WaniKani in three steps.

  1. 01Your users connect WaniKaniThey add their WaniKani api key on Arc0 Connect, under your brand. It goes straight into the vault.
  2. 02You set the rulesReads run, and writes like “create Study Material” can wait for the user to approve.
  3. 03Any agent can actYour agent calls WaniKani through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
POLICY.TS
await arc0.policies.set('wanikani', {
  read: 'allow',
  write: 'ask',        // create_study_material
  destructive: 'deny',  
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2
04 · AUTH AND DATA

How WaniKani connects.

Users add their WaniKani api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same WaniKani connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH
API key
CREDENTIALS
Per-tenant encrypted vault
MODEL SEES
Results only, never credentials
AUDIT LOG
Every call, on every plan
05 · WORKS WITH

Use WaniKani from any agent.

Claude
ChatGPT
Cursor
Codex
VS Code
OpenAI Agents SDK
Claude Agent SDK
Vercel AI SDK
Mastra
LangGraph
07 · FAQ

WaniKani and Arc0, answered.

Q01

Can I use WaniKani with Claude, ChatGPT or Cursor?

Yes. Connect WaniKani to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the WaniKani actions you allow.

Q02

How do users connect WaniKani?

Users add their WaniKani api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which WaniKani actions can my agent take?

16 in total: 11 read, 5 write and 0 destructive, such as “create Study Material”. Your policies decide which of them each agent may call.

Q04

Can I make my agent read-only in WaniKani?

Yes. Allow read actions and deny writes in the WaniKani policy. Your agent can still look things up, and any write it attempts is blocked and logged.

Q05

Can my own backend call WaniKani too?

Yes. The same WaniKani connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug WaniKani into your agent.

Your users connect WaniKani once, under your brand. Your agent gets 16 actions behind your policies, with every call on the record.

Free to build · MCP + REST · Audit log on every plan