AISentinel by BizDNAi MCP server

AISentinel

The missing security, control, and observability layer for the agentic era.

Traditional security tools were built for malware.

AI agents were given legitimate power through tools and APIs.

AISentinel provides the missing security, control, and observability layer.

1. Project Title + Tagline

AISentinel — an open-source MCP server that protects AI agents at runtime. Built by Kabzhanov / BizDNAi, the team behind the AI Trust Index.

2. Why AISentinel Exists

AI agents now have shell, browsers, file systems, and API keys. They are legitimate processes — antivirus cannot see them. A single indirect prompt injection in a PDF or email can pivot into mass data exfiltration through ordinary tools like Bash and Email_send.

AISentinel closes that gap: it runs as an MCP server in front of every tool call, evaluates YAML policies, logs every decision, and ships an audit trail compatible with the AI Trust Index.

See docs/SECURITY_AUDIT.md for the full threat model.

3. Quickstart (3 minutes)

Option A: install the binary

go install github.com/Kabzhanov/AISentinel/cmd/aisentinel@latest
aisentinel --help
aisentinel serve

go install gives you a standalone binary — you do not need to clone this repo or pass --policy to get started. aisentinel serve with no flags loads a built-in default policy (embedded in the binary at build time), balanced for general use: blocks obvious secrets-in-args and destructive commands, requires approval for network calls and bulk reads. To use your own policy instead, pass --policy /path/to/your.yaml or set $AISENTINEL_POLICY (see Policy resolution below).

Option B: install the sidecar (drop-in policy proxy for any MCP server)

go install github.com/Kabzhanov/AISentinel/cmd/aisentinel-sidecar@latest

# Wrap any stdio MCP server with one command — no --policy required:
aisentinel-sidecar ./your-mcp-server [args...]

Option C: clone and build

git clone https://github.com/Kabzhanov/AISentinel.git
cd AISentinel
go build -o bin/aisentinel ./cmd/aisentinel
go build -o bin/aisentinel-sidecar ./cmd/aisentinel-sidecar
./bin/aisentinel serve --policy policies/default.yaml

(--policy policies/default.yaml here is explicit and optional — omitting it works too, and falls back to the same built-in default described above.)

Option D: pre-built binaries from GitHub Releases

Download from . Available for linux/amd64, linux/arm64, darwin/amd64, darwin/arm64, windows/amd64.

Option E: add to Claude Code / Cursor / Cline

{
  "mcpServers": {
    "aisentinel": {
      "command": "aisentinel",
      "args": ["serve"]
    },
    "aisentinel-sidecar": {
      "command": "aisentinel-sidecar",
      "args": ["--policy", "/absolute/path/to/policies/strict.yaml", "/path/to/your-mcp-server"]
    }
  }
}

Then restart your MCP client and ask your agent to call any tool — AISentinel will gate every call and write a JSONL audit trail to ~/.aisentinel/events-YYYY-MM-DD.jsonl.

Policy resolution

Shortened. The full README is on GitHub.