Context7
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Description from the maker (original English)
Read-only access to Bunpro profile, reviews, study statistics, vocabulary, and search.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
BUNPRO_API_TOKENValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"bunpro": {
"command": "npx",
"args": [
"-y",
"bunpro-mcp-server"
],
"env": {
"BUNPRO_API_TOKEN": "your-value"
}
}
}
}Run this in your terminal
claude mcp add bunpro --env BUNPRO_API_TOKEN=your-value -- npx -y bunpro-mcp-serverFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"bunpro": {
"command": "npx",
"args": [
"-y",
"bunpro-mcp-server"
],
"env": {
"BUNPRO_API_TOKEN": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"bunpro": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"bunpro-mcp-server"
],
"env": {
"BUNPRO_API_TOKEN": "your-value"
}
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account Alexxanddr, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
You need to fill in: BUNPRO_API_TOKEN
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.3.0) reached the registry 16 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Node.js on your computer.
In the same category: Context7, Codebase Memory, Exa
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Connect AI agents to Exa for web search, content fetching, and multi-step research.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
A read-only Model Context Protocol server that lets MCP clients work with your Bunpro profile, review queue, forecasts, SRS progress, vocabulary, learning content, and search.
[!WARNING]
This project uses Bunpro's unofficial, reverse-engineered frontend API. It may change without notice. This project is not affiliated with or endorsed by Bunpro.
The server exposes no account-changing, review-submission, or deletion tools.
npx.https://api.bunpro.jp/api/frontend/....Authorization request header value without the Bearer prefix.Treat this token like a password. Do not commit it, paste it into issues, or expose it in screenshots.
Install and launch the published package directly from your MCP client:
{
"mcpServers": { "bunpro": { "command": "npx", "args": ["-y", "bunpro-mcp-server"], "env": { "BUNPRO_API_TOKEN": "your-token" } } } }
For local development, build the repository and configure the client with an absolute path:
{
"mcpServers": { "bunpro": { "command": "node", "args": ["/absolute/path/to/bunpro-mcp-server/dist/index.js"], "env": { "BUNPRO_API_TOKEN": "your-token" } } } }
Restart the MCP client after changing its configuration or rebuilding the server.
npm ci
npm run build BUNPRO_API_TOKEN='your-token' node dist/index.js
The last command starts an MCP stdio process and waits for protocol messages; it has no interactive prompt. Prefer the MCP client's environment configuration so the token does not enter shell history.
| Tool | Purpose |
|---|---|
get_user | Get the current user profile. |
get_user_furigana | Get furigana settings. |
get_due | Get items currently due. |
get_queue | Get the current review queue. |
get_quiz_questions | Get the current read-only quiz queue. |
get_base_stats | Get base study statistics. |
get_jlpt_progress | Get mixed JLPT progress. |
get_daily_forecast | Get the daily review forecast. |
get_hourly_forecast | Get the hourly review forecast. |
get_srs_overview | Get the SRS level overview. |
get_review_activity | Get daily or hourly review activity. |
get_last_session | Get last-session accuracy. |
get_weak_items | Rank weak grammar and vocabulary using study count and accuracy. |
get_vocab | Get vocabulary by slug or ID. |
get_vocab_notes | Get notes for vocabulary. |
get_vocab_neighbors | Get adjacent vocabulary in a deck. |
get_learning_content | Get learning content for a deck. |
get_topic_replies | Get replies for a Bunpro discussion topic. |
get_srs_level_details | Get paginated SRS-level details. |
get_self_study_srs_details | Get paginated self-study SRS details. |
get_ghost_srs_details | Get ghost-review SRS details. |
search | Search grammar and vocabulary with compact results. |
Exact inputs, outputs, defaults, and errors are in MCP contracts.
| Variable | Required | Description |
|---|---|---|
BUNPRO_API_TOKEN | Yes | Frontend bearer token without the Bearer prefix. |
BUNPRO_API_BASE_URL | No | API override mainly for tests. It receives the token; use only a trusted URL. |
npm ci
npm run check
Authenticated live checks are separate:
cp .env.example .env
npm run test:live
The live suite is read-only and .env is ignored. See Testing and Contributing.
Bearer prefix.The server is a local stdio package using the official TypeScript MCP SDK. Most outputs pass through Bunpro's JSON, so upstream shape changes are possible. It currently provides tools only—no resources, prompts, hosted HTTP endpoint, browser login, or OAuth flow.
Read Architecture, Technical security, and the community API reference.
The npm package is published as bunpro-mcp-server and can be launched with npx -y bunpro-mcp-server. Release metadata is also prepared for the official MCP Registry through server.json.
Releases use Semantic Versioning and GitHub Releases. The release tag must match v ; GitHub Actions then tests, publishes through tokenless npm Trusted Publishing, and registers the same version in the official MCP Registry. See Publishing.
A future hosted streamable-HTTP server could reduce installation friction, but it first needs secure per-user authentication and token storage. Local stdio keeps the current bearer token on the user's machine.
Read SECURITY.md before reporting a vulnerability. Contributions follow CONTRIBUTING.md. Never include credentials or personal Bunpro responses in a report.
Licensed under the existing MIT License. Downstream users must also comply with Bunpro's applicable terms and policies.