agentwit

agentwit

Debug and audit AI agent ↔ MCP server tool calls.

pip install agentwit
agentwit proxy --target http://localhost:3000 --port 8765

[agentwit] 14:32:01  tools/call  bash       HIGH ⚠  shell_exec
[agentwit] 14:32:03  tools/call  read_file  LOW  ✓
[agentwit] 14:32:05  tools/call  bash       CRITICAL 🚨 privilege_escalation  LLM06

Change one URL. No MCP server modification needed.

日本語版 · PyPI · Releases

---

The problem

When an AI agent calls MCP server tools, you can't see what's happening.

AI Agent
↓  (black box)
MCP Server  →  bash / read_file / fetch / ...

agentwit sits between them as a transparent proxy and records everything.

AI Agent
↓
agentwit  ←  logs every call · detects risks · verifies integrity
↓
MCP Server  (zero modification)

---

5-minute quickstart

pip install agentwit

# 1. Start the proxy
agentwit proxy --target http://localhost:3000 --port 8765

# 2. Point your agent to port 8765 instead of 3000
#    That's it. Recording starts immediately.

# 3. Generate an audit report
agentwit report --session ./witness_logs/SESSION_ID --format html

# 4. Verify log integrity
agentwit verify --session ./witness_logs/SESSION_ID
# Chain integrity:  VALID ✓
# Signature check:  VALID ✓

→ Full guide: docs/quickstart.md

---

Features

Log recording

• Tamper-proof SHA-256 chain — detect any modification
• ed25519 signatures — prove who recorded the log
• HTML / Markdown / JSON report generation
• Auto-backup to ~/.agentwit/backups/ on session end

Risk detection

• 15+ built-in patterns: shell_exec, privilege_escalation, data_exfiltration, jailbreak, ...
• Prompt injection detection (CRITICAL/HIGH/MEDIUM/LOW)
• Tool schema change detection
• Agent thought & reasoning recording (LangChain)

OWASP LLM Top 10 mapping (v1.0.0)

Every detected risk is automatically tagged with the corresponding OWASP LLM category:

from agentwit.analyzer.owasp_mapper import OWASPMapper
mapper = OWASPMapper()
mapper.map("privilege_escalation")  # → "LLM06"
mapper.map_events(events)           # → adds owasp_category to each event

Plugin API (v1.0.0)

Add custom detection rules as external packages — no fork needed:

# my_package/plugin.py
from agentwit.plugins.base import PluginBase

class MyPlugin(PluginBase):
    def scan(self, event: dict) -> list[dict]:
        if "dangerous_pattern" in str(event):
            return [{"pattern": "my_pattern", "severity": "HIGH",
                     "description": "Custom detection"}]
        return []

# pyproject.toml of your plugin package
[project.entry-points."agentwit.plugins"]
my_plugin = "my_package:MyPlugin"

pip install agentwit-plugin-myname
agentwit proxy --target http://localhost:3000 --port 8765
# → plugin auto-loaded on startup

→ Full guide: docs/plugin-guide.md

SIEM integration (v1.0.0)

Forward audit logs to Splunk, Elasticsearch, or Grafana Loki via Fluent Bit:

# docker/docker-compose.siem.yml
SPLUNK_HEC_TOKEN=your-token docker compose -f docker/docker-compose.siem.yml up

Supports: Splunk HEC · Elasticsearch · Grafana Loki

MCP Inspector GUI

Desktop app for real-time MCP server debugging.

Download: GitHub Releases

• Linux: .deb / .rpm / .AppImage
• Windows: .msi (via GitHub Actions)

GUI features

• 3-pane layout: Server info + Tool list / Parameter editor + Response / History + Metrics + Compare
• Export Report button — generate HTML audit report from History tab with one click
• EN/JP language support
• Real-time risk score display

┌─────────────────┬──────────────────────┬─────────────────────┐
│  Server Info    │  Parameter Editor    │  History            │
│  ─────────────  │  ──────────────────  │  ─────────────────  │
│  Tools          │  {                   │  [Export Report]    │
│  ✓ bash   EXEC  │    "command": "ls"   │                     │
│  ✓ read   READ  │  }                   │  14:32 bash  HIGH   │
│  ✓ fetch  READ  │                      │  14:33 read  LOW    │
│                 │  [Execute]           │  14:34 bash  CRIT   │
└─────────────────┴──────────────────────┴─────────────────────┘

---

Transports

---

LangChain integration

pip install agentwit[full]

from agentwit import AgentwitCallback

callbacks = [AgentwitCallback(output="./audit.jsonl")]

# Agent thoughts and reasoning are also recorded:
# {"type": "agent_thought", "thought": "...", "tool_selected": "bash",
#  "reasoning": "...", "timestamp": "..."}

---

CLI reference

# Proxy
agentwit proxy --target http://localhost:3000 --port 8765
agentwit proxy --target http://localhost:3000 --port 8765 --timeout 60
agentwit proxy --stdio -- python mcp_server.py
agentwit proxy --target http://localhost:3000 \
  --webhook https://hooks.slack.com/xxx \
  --webhook-on HIGH,CRITICAL

# Reports
agentwit report --session ./witness_logs/SESSION_ID --format json
agentwit report --session ./witness_logs/SESSION_ID --format markdown
agentwit report --session ./witness_logs/SESSION_ID --format html --output ./report.html

# Verification
agentwit verify --session ./witness_logs/SESSION_ID
agentwit replay --session ./witness_logs/SESSION_ID
agentwit diff --session-a ./witness_logs/A --session-b ./witness_logs/B

→ Full reference: docs/api-reference.md

---

Guard vs. Witness

agentwit does not block. It witnesses.
A blocked call leaves no trace. A witnessed call leaves evidence.

---

Version history

---

Documentation

---

License

MIT — see LICENSE