Impri
Impri MCP server — human-in-the-loop approval inbox for AI agents
Topics: Security
Connect
Review any command before running it. Package names and URLs come from the server's own registry entry.
Remote (streamable-http)
https://api.impri.dev/mcp Reachable (checked 2026-11-09)
Claude Code:
claude mcp add --transport http impri https://api.impri.dev/mcp --header "Authorization: <YOUR_VALUE>"
Or add to your MCP client config:
{
"mcpServers": {
"impri": {
"url": "https://api.impri.dev/mcp",
"headers": {
"Authorization": "<YOUR_VALUE>"
}
}
}
}
Authorizationrequired secret — Impri API key as a Bearer token. Get one at impri.dev.
Package (npm 0.1.3)
npx -y @impri/[email protected]
Or add to your MCP client config:
{
"mcpServers": {
"impri": {
"command": "npx",
"args": [
"-y",
"@impri/[email protected]"
],
"env": {
"IMPRI_API_KEY": "<YOUR_VALUE>"
}
}
}
}
IMPRI_API_KEYrequired secret — Impri API key (im_...). Get one at impri.dev or from your self-hosted server's first-run logs.IMPRI_BASE_URL— Base URL of a self-hosted Impri server (e.g. http://localhost:8484). Defaults to the hosted cloud.
Related servers
semgrep
Scan code for security vulnerabilities using Semgrep.
ida-pro-mcp
IDA Pro plugin for binary analysis: decompilation, disassembly and automatic malware analysis reports.
lauriewired/ghidramcp
Autonomous reverse engineering with Ghidra: decompile binaries, rename methods and data, and list methods, classes, imports and exports.
jadx-ai-mcp
JADX decompiler plugin providing live, LLM-assisted reverse engineering.
beelzebub
Honeypot framework for building decoy MCP tools that an agent would never use in normal work, to detect prompt injection and malicious…
SafeDep Vet MCP
Protect your AI agents and IDEs from malicious open-source packages.
Listed in punkpeye/awesome-mcp-servers (MIT)
Data from the Official MCP Registry