Install
$ agentstack add mcp-newioapp-acp-inspector ✓ scanned · ✓ verified — works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README — it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming — see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps — measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
ACP Inspector
A desktop app for testing and debugging Agent Client Protocol (ACP)-compatible agents. ACP is an open protocol that standardizes how client programs (IDEs, chat apps, orchestrators) communicate with agents over JSON-RPC, enabling interoperability across tools and platforms. The ACP inspector is inspired by MCP Inspector.
Features
- Connect to any ACP agent — spawn via command line (e.g.
kiro-cli acp,claude-agent-acp) - Full protocol log — see every JSON-RPC message on the wire with direction indicators, method filtering, and text search
- Interactive prompting — send prompts, observe streaming responses, interrupt with
session/cancel - Session management — create, list, and switch between sessions
- Permission request handling — respond to
session/request_permissioninline - Agent info display — capabilities, supported prompt types, MCP transports, auth methods
- Environment variable management — auto-source from login shell, manual edit, passed to agent process
- Output grouping — concatenates streaming chunks into readable blocks, color-coded by type
Tested With
| Agent | Command | Link | |---|---|---| | Kiro CLI | kiro-cli acp | kiro.dev/docs/cli/acp | | Claude Agent ACP | claude-agent-acp | npmjs.com/package/@agentclientprotocol/claude-agent-acp | | Gemini CLI | gemini --acp | geminicli.com/docs/cli/acp-mode | | Cursor Agent | agent acp | cursor.com/docs/cli/acp |
Install
Download the latest release for your platform from GitHub Releases.
| Platform | Download | |---|---| | macOS (Apple Silicon) | .dmg (arm64) | | macOS (Intel) | .dmg (x64) | | Linux (x64) | .AppImage / .deb | | Linux (arm64) | .AppImage / .deb |
Development
npm install
npm run dev
Build
# Local unsigned build (macOS arm64)
./scripts/build-unsigned.sh
# Local signed build (macOS arm64, requires code signing cert + keychain setup)
./scripts/build-signed.sh
License
[MIT](LICENSE)
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: newioapp
- Source: newioapp/acp-inspector
- License: MIT
- Homepage: https://github.com/newioapp/acp-inspector/releases
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet — be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.