The bridge between Burp Suite and modern AI.
How to install burp-ai-agent?
six2dez/burp-ai-agent
$git clone https://github.com/six2dez/burp-ai-agentInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install burp-ai-agent by running `git clone https://github.com/six2dez/burp-ai-agent`, then use it for the current task and follow its documentation at https://github.com/six2dez/burp-ai-agent.
README.md
| 1 | # Custom AI Agent |
| 2 | |
| 3 | **The bridge between Burp Suite and modern AI.** |
| 4 | |
| 5 | > **A note on the name:** This extension is published as **Custom AI Agent** (formerly *Burp AI Agent*). It was renamed to comply with PortSwigger's BApp Store naming requirements and to avoid confusion with Burp Suite's built-in **Burp AI** provider. The GitHub repository (`github.com/six2dez/burp-ai-agent`), the documentation site (`burp-ai-agent.six2dez.com`), and the configuration directory (`~/.burp-ai-agent/`) keep the `burp-ai-agent` identifier for continuity. |
| 6 | |
| 7 | <!-- screenshot: main extension tab with chat and settings visible --> |
| 8 |  |
| 9 | |
| 10 | Custom AI Agent is an extension for Burp Suite that integrates AI into your security workflow. Use local models or cloud providers, connect external AI agents via MCP, and let passive/active scanners find vulnerabilities while you focus on manual testing. |
| 11 | |
| 12 | ## What's new in v0.9.0 |
| 13 | |
| 14 | - **Native [Anthropic](docs/anthropic-backend.md) backend** (CAP-01) — direct Anthropic Messages API via Burp's HTTP transport; all traffic appears in Proxy history. |
| 15 | - **AES-256-GCM secrets at rest** (SEC-01) — all stored API keys and tokens are encrypted with a per-install key using `javax.crypto`; no plaintext in preferences. |
| 16 | - **Real HKDF host anonymization** (PRIV-01) — STRICT mode now uses genuine HMAC-SHA256 extract/expand (not salted SHA-256) for host anonymization. |
| 17 | - **Request/response body redaction + custom patterns** (PRIV-02) — redaction pipeline covers body fields and user-configurable regex patterns validated against ReDoS. |
| 18 | - **Pre-send secret tripwire** (PRIV-03) — warns before high-entropy values leave Burp; allowlist actions are audit-logged. |
| 19 | - **[External MCP servers](docs/external-mcp-servers.md)** (CAP-02) — connect to external/custom MCP servers (SSE or stdio) so AI agents can call their tools alongside Burp's built-in tools. |
| 20 | - **Per-session token-budget guardrails** (CAP-04) — `BudgetGuard` caps passive-scanner spend with WARN/CAP/OFF states; passive scanner pauses automatically at the hard cap. |
| 21 | |
| 22 | ## Highlights |
| 23 | |
| 24 | - **11 AI Backends** — Burp AI (built-in), Ollama, LM Studio, NVIDIA NIM, Perplexity, Generic OpenAI-compatible, Gemini CLI, Claude CLI, Codex CLI, OpenCode CLI, Copilot CLI. |
| 25 | - **59 MCP Tools** — Let Claude Desktop (or any MCP client) drive Burp autonomously (8 extension-native AI tools in the BApp Store build, all 59 in the full build). |
| 26 | - **Scoped MCP Access** — Optionally confine every MCP tool to your in-scope hosts, so external AI clients can't reach out-of-scope targets through Burp. |
| 27 | - **62 Vulnerability Classes** — Passive and Active AI scanners across injection, auth, crypto, and more. The passive scanner runs as a Burp `PassiveScanCheck` (Burp Pro). |
| 28 | - **Available on the BApp Store** — Install **Custom AI Agent** directly from Burp's BApp Store, or grab the full build from Releases. |
| 29 | - **Theme-Aware UI** — An internal design system styles the settings panel and re-themes automatically with Burp's light/dark switch. |
| 30 | - **Burp Scan Skill** — Use your preferred AI coding assistant (Claude Code, Gemini CLI, Codex, etc.) as a scanner via MCP. |
| 31 | - **3 Privacy Modes** — STRICT / BALANCED / OFF. Redact sensitive data before it leaves Burp. |
| 32 | - **Custom Prompt Library** — Save free-form prompts per context (HTTP request or scanner issue); launch them from the right-click menu or type ad-hoc ones via `Custom…`. |
| 33 | - **Audit Logging** — JSONL with SHA-256 integrity hashing for compliance; every launch stamped with `promptSource` / `contextKind` for reproducibility. |
| 34 | |
| 35 | ## Quick Start |
| 36 | |
| 37 | ### 1. Install |
| 38 | |
| 39 | Install **Custom AI Agent** from Burp's **BApp Store**, download the latest JAR from [Releases](https://github.com/six2dez/burp-ai-agent/releases), or build from source (Java 21): |
| 40 | |
| 41 | ```bash |
| 42 | git clone https://github.com/six2dez/burp-ai-agent.git |
| 43 | cd burp-ai-agent |
| 44 | |
| 45 | # Full build (default, GitHub releases) — all 59 MCP tools |
| 46 | JAVA_HOME=/path/to/jdk-21 ./gradlew clean shadowJar |
| 47 | # Output: buil |
Related
6 picksType
- mcp-scannerA tool to scan MCP servers and tools for security findingsJul 2026
- hol-guardOpen-source antivirus and runtime protection for AI agents, tools, MCP servers, plugins, skills, and package installs.Jul 2026
- agent-scanAgent supply chain security scanner.Jul 2026
- falcon-mcpConnects AI agents with CrowdStrike Falcon for security analysis and automation.Jul 2026
- pythonPlug-and-play auth for Python MCP servers.Aug 2025
- auth0-mcp-serverAuth0 MCP Server: Manage Auth0 applications, APIs, actions, logs, and forms using natural languageJul 2026
