✦ M I T S U ✦

Your chibi red-team companion

A little personality. A serious toolkit. A full engagement, one evidence-led step at a time.

• What is Mitsu?
• At a glance
• Pentest process flow
• Demonstration
• Install
• Modes and dialogs
• Red Team Armory
• MCP integrations
• Session Intel
• Providers and search
• Using a session
• Slash commands
• Project layout
• Data storage
• Disclaimer
• License

What is Mitsu?

Mitsu is your chibi red-team companion for authorized penetration tests, built to help carry an engagement from the first look at the attack surface through service enumeration, vulnerability research, validation, and access-path assessment. Her MCP server connects the model to Mitsu’s 165-tool Red Team Armory, custom command wrappers, and external MCP servers, so she can turn a plan into focused tool work and use the returned evidence to choose what to check next. When a requested utility is missing, she can offer to install it and wait for your approval.

The engagement’s Intel grows alongside the work: targets, IPs, domains, ports and services, vulnerability leads, confirmed findings, accounts, evidence, and observations all stay organized in session context. That gives Mitsu a record of what is known, what has been tried, and where a lead stopped fitting, rather than treating each turn as a fresh start. Sessions keep their own history and workspace, and the recorded results can feed summaries and attack-surface maps.

Pick the role you want her to take. Recon keeps work passive and operator-led; Guided pauses for your choices and lets you steer the next phase; AutoPwn can follow evidence-backed paths through an in-scope assessment with fewer interruptions. Mitsu supports multiple model providers, and you can change the provider, working directory, tools, scope, and autonomy to fit each engagement. She brings the chibi energy; you give her the sword to attack.

At a glance

• Model providers: OpenAI, Anthropic, OpenRouter, Ollama, DeepSeek, Moonshot (Kimi), NVIDIA NIM, and Cloudflare Models, plus custom OpenAI- or Anthropic-compatible endpoints.
• Mitsu’s MCP server connects models to a catalog of 165+ Red Team Armory tools across 17 categories, plus custom CLI wrappers and external MCP servers.
• Persistent engagement Intel for targets, findings, services, vulnerabilities, domains, IPs, accounts, people, and working observations.
• Three operating modes: Recon, Guided, and AutoPwn.
• Engagement-scoped sessions keep conversation, Intel, artifacts, and working directory together; resume, search, rewind, or export as needed.
• Vulnerability research that combines session Intel with configured search engines and reference databases.

Mitsu Logic & Pentest Process Flow

flowchart TD
    A[Launch Mitsu] --> B{Choose a session}
    B -->|New| C[Create session]
    B -->|Resume| D[Load history and Intel]
    C --> E[Select provider and model]
    D --> E
    E --> F[Set target, scope, mode, and workspace]
    F --> G[Describe the assessment objective]
    G --> H[Model reviews conversation and session Intel]
    H --> I[Choose a focused next step]
    I --> J{Need a tool, a detail, or a final answer?}
    J -->|Question or choice| K[Show an interactive dialog]
    K --> H
    J -->|Final answer| Z[Summarize evidence and remaining gaps]
    J -->|Tool| L{Mode and approval check}
    L -->|Guided| M[Ask operator to choose the next action]
    M -->|Continue| N[Run one focused check]
    M -->|Redirect or stop| H
    L -->|AutoPwn| N
    L -->|Recon| O[Use permitted passive or read-only checks]
    L -->|Approval required| P[Show approval or sudo dialog]
    P -->|Approve| N
    P -->|Decline| H
    N --> Q[Run capability through MCP]
    O --> Q
    Q --> R[Review tool output and evidence]
    R --> S[Update targets, services, IPs, domains, and observations]
    S --> T{Relevant vulnerability lead?}
    T -->|Yes| U[Check product, version, and prerequisites]
    U --> V{Evidence supports applicability?}
    V -->|No or unknown| W[Record uncertainty and choose another check]
    V -->|Yes| X[Validate impact within scope]
    X --> Y{Confirmed?}
    Y -->|No| W
    Y -->|Yes| AA[Record finding, severity, evidence, and references]
    T -->|No| AB{Useful in-scope work remains?}
    W --> AB
    AA --> AB
    AB -->|Yes| I
    AB -->|No| Z
    Z --> AC[Save session and review results]
    AC --> AD[Generate report, map attack surface, export, or resume]
    AE[Operator sends a new direction] -. interrupts active turn .-> H

Mitsu runs the selected model in a tool loop: it receives the session history and Intel, requests a tool when useful, and continues from the returned evidence. Recon, Guided, and AutoPwn apply different interaction and approval rules around that loop. A new operator message can redirect an active turn; recorded Intel keeps confirmed assets and findings alongside unresolved observations.

Demonstration

Install

Mitsu requires Python 3.10 or newer. The GitHub installer uses uv to set up and manage its environment.

By pip

Install Mitsu with:

pip install mitsu
mitsu

Install from GitHub

git clone https://github.com/ARCANGEL0/Mitsu.git
cd Mitsu
./scripts/install.sh

Mitsu can identify missing tools or the local SearXNG container needed for a task and offer to install them with your approval.

Install a local checkout

From the Mitsu source directory:

uv tool install .
mitsu

To run directly from the checkout instead:

./mitsu

First launch

The first-run setup walks you through the essentials:

1. Configure a model provider and its connection details.
2. Choose a model.
3. Configure web-search providers.
4. Select the Red Team Armory tools Mitsu can use; approve installation if a selected tool is missing.
5. Choose Mitsu’s companion.

After that, you’re ready to start a session.

You can return to provider and model setup from the command center at any time. In a session, use /connect to change provider settings or /model to switch models. For a local Ollama server, make sure it is running and has a model available before connecting.

Choose how Mitsu works

Switch modes with /mode. The mode controls how Mitsu interacts with targets and when she asks you to decide.