openinputbridge-mcpSAFE
OpenInputBridgeのMCPサーバー実装です。
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
[](https://github.com/Applet-LLC/OpenInputBridge-MCP/actions/workflows/build.yml)
[OpenInputBridge](https://github.com/Applet-LLC/OpenInputBridge)(Interception互換のカーネルレベル キーボード/マウス入力ドライバ)を、MCP (Model Context Protocol) 経由のツールとして公開するサーバーです。
GUI/ネイティブアプリのテスト自動化における SendInput() / UI Automation / 座標ベース自動化ツールの代替・上位互換として、AIエージェント(Claude Codeなど)やテストコードから、カーネルレベルの合成キーボード/マウス入力を送信できます。
⚠️ 本プロジェクトは oblitum/Interception(LGPL/商用デュアルライセンス)のコードには一切依存していません。ヘルパー実行ファイル(helper/oib_bridge.c)は、OpenInputBridge本体の `docs/PROTOCOL.md` に文書化されたワイヤプロトコルのみを根拠に、独自にIOCTLを実装しています。これは何のためのツールか
SendInput() / UI Automation / PyAutoGUI・Selenium等の座標ベース自動化には、テスト自動化の現場でよく遭遇する構造的な限界があります。本ツールはそれらを、ドライバレベルで合成入力を注入することで回避します。
注意: 上記はあくまで技術的な限界の回避策であり、「検知されない」ことを保証するものではありません。カーネルレベルのフィルタドライバ自体が検知され得ることは SECURITY.md に記載しています。自分が権限を持つ/管理しているテスト環境以外(他社のゲーム・アプリのアンチチート回避目的など)での利用は想定しておらず、対象ソフトウェアの利用規約に違反する可能性がある用途には使用しないでください。
アーキテクチャ
flowchart TB Client["MCPクライアント(Claude Desktop / Claude Code など)"] subgraph Server["openinputbridge-mcp (Node.js/TypeScript)"] directio
cf346a43c823OBSERVED · 2026-10-12Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add openinputbridge-mcp -- npx -y [email protected]
{
"mcpServers": {
"openinputbridge-mcp": {
"command": "npx",
"args": [
"-y",
"[email protected]"
]
}
}
}Exposed tools (13)
8 read · 5 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
disable_exclusive_input_mode | write | |
disable_input_control | write | |
enable_exclusive_input_mode | write | |
enable_input_control | write | |
get_driver_status | read | |
get_exclusive_mode_status | read | |
key_down | read | |
key_up | read | |
mouse_click | read | |
mouse_move | write | |
mouse_wheel | read | |
press_key | read | |
type_text | read |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (1)
@modelcontextprotocol/sdk, zod, @types/node, typescript
Gates applied: no_behavioural_pass.
cf346a43c823full audit observations/trust-audit/mcp-server/applet-llc__openinputbridge-mcp.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | cf346a43c823 | SAFE | B | 89 | first audit |
Questions
What is the openinputbridge-mcp MCP server?
OpenInputBridgeのMCPサーバー実装です。
What tools does openinputbridge-mcp expose?
13 in total: 8 read-only, 5 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is openinputbridge-mcp safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does openinputbridge-mcp need?
No credential environment variables were found in its source, so it appears to need none.
How does openinputbridge-mcp run?
It speaks stdio, so it runs as a local process your client starts. It is published on npm as openinputbridge-mcp at 0.1.1.
How current is this page?
The grade is for one exact copy of the source (cf346a43c823), read on 2026-10-12. The repository is watched and re-audited when it changes.