Skip to content
Back to search

burp-mcp-agents

Practical setup guides and helpers to connect Burp Suite MCP Server to multiple AI backends (Codex, Gemini, Ollama, ...).

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/six2dez--burp-mcp-agents/badge.svg)](/listings/six2dez--burp-mcp-agents)

HTML

<a href="/listings/six2dez--burp-mcp-agents"><img src="/api/listings/six2dez--burp-mcp-agents/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

All setups require:

1. Burp MCP Server plguin enabled 2. Caddy reverse proxy (see `common/caddy_setup.md`) 3. One backend of your choice

Install the Burp MCP Server extension

1) Download the Burp MCP Server extension (MCP server jar) from: https://portswigger.net/bappstore/9952290f04ed4f628e624d0aa9dccebc 2) In Burp Suite: `Extender` → `Extensions` → `Add` → select the jar or from BApp Store. 3) Start the extension and confirm it listens on `127.0.0.1:9876`.

---

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 171 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Burp MCP Agents
  2. Practical setup guides and helpers to connect Burp Suite MCP Server to multiple AI backends (Codex, Gemini, Ollama, LM Studio).
  3. This repo focuses on wiring, safety-first workflows, and reusable prompts to analyze real Burp traffic.
  4. No fuzzing.
  5. No blind scanning.
  6. Only real traffic + reasoning.
  7. ---
  8. ## What this is
  9. Burp MCP Agents is a collection of:
  10. • Backend setup guides (Codex, Gemini, Ollama, LM Studio)
  11. • Caddy proxy configuration for MCP SSE
  12. • Prompt templates for passive analysis and reporting
  13. ---
  14. ## Architecture
  15. ```yaml
  16. Burp Suite MCP Server
  17. ▲
  18. │
  19. MCP Bridge
  20. │
  21. ┌──────────────────────────────────────────────┐
  22. │ │ │ │
  23. Codex CLI Ollama Agent Gemini CLI LM Studio Agent
  24. ```
  25. ---
  26. ## Supported Backends
  27. | Backend | Mode | Privacy | Difficulty |
  28. |--------|-----|--------|------------|
  29. | Codex CLI | Cloud | Medium | Easy |
  30. | Ollama | Local | Full | Advanced |
  31. | Gemini CLI | Cloud | Medium | Easy |
  32. | LM Studio | Local | Full | Advanced |
  33. ---
  34. ## Quick start
  35. All setups require:
  36. 1. Burp MCP Server plguin enabled
  37. 2. Caddy reverse proxy (see `common/caddy_setup.md`)
  38. 3. One backend of your choice
  39. ### Install the Burp MCP Server extension
  40. 1) Download the Burp MCP Server extension (MCP server jar) from:
  41. https://portswigger.net/bappstore/9952290f04ed4f628e624d0aa9dccebc
  42. 2) In Burp Suite: `Extender` → `Extensions` → `Add` → select the jar or from BApp Store.
  43. 3) Start the extension and confirm it listens on `127.0.0.1:9876`.
  44. ---
  45. ## Codex CLI
  46. See: `codex/README.md`
  47. **Example models**
  48. | Model | Use |
  49. |------|----|
  50. | gpt-5.2-codex | General use |
  51. | gpt-5.1 | Faster |
  52. | gpt-5-mini | Low resource |
  53. ---
  54. ## Ollama (fully local)
  55. See: `ollama/README.md`
  56. **Example models**
  57. | Model | VRAM | Notes |
  58. |------|-----|------|
  59. | llama3.1:8b-instruct | 8GB+ | Small, fast |
  60. | qwen2.5:14b-instruct | 16GB | Mid size |
  61. | llama3.1:70b-instruct | 48GB+ | Large, high VRAM |
  62. ---
  63. ## Gemini CLI
  64. See: `gemini-cli/README.md`
  65. **Example models**
  66. | Model | Notes |
  67. |------|-----|
  68. | gemini-2.0-flash | Fast |
  69. | gemini-2.0-pro | Deeper reasoning |
  70. ---
  71. ## LM Studio (local OpenAI-compatible)
  72. See: `lmstudio/README.md`
  73. **Example models**
  74. | Model | Notes |
  75. |------|-----|
  76. | llama-3.1-8b-instruct | Small, fast |
  77. | qwen2.5-14b-instruct | Mid size |
  78. | llama-3.1-70b-instruct | Large, high VRAM |
  79. ---
  80. ## Prompts
  81. The real power lives in `prompts/`:
  82. | Prompt | Purpose |
  83. |------|--------|
  84. | passive_hunter.md | Broad passive vuln surfacing |
  85. | idor_hunter.md | IDOR/BOLA discovery |
  86. | auth_flow_mapper.md | Auth vs unauth access mapping |
  87. | ssrf_redirect_hunter.md | SSRF/open redirect candidates |
  88. | logic_flaw_hunter.md | Multi-step logic issues |
  89. | session_scope_hunter.md | Token scope/audience misuse |
  90. | rate_limit_abuse_hunter.md | Rate-limit and abuse gaps |
  91. | report_writer.md | Evidence-based reporting |
  92. See `prompts/README.md` for usage guidance.
  93. ---
  94. ## Optional launchers
  95. You can use the backend launchers to auto-start Caddy and shut it down when the
  96. backend exits.
  97. Source them directly:
  98. ```bash
  99. source /path/to/burp-mcp-agents/codex/burpcodex.sh
  100. source /path/to/burp-mcp-agents/gemini-cli/burpgemini.sh
  101. source /path/to/burp-mcp-agents/ollama/burpollama.sh
  102. source /path/to/burp-mcp-agents/lmstudio/burplmstudio.sh
  103. ```
  104. Then run:
  105. ```bash
  106. burpcodex
  107. burpgemini
  108. burpollama deepseek-r1:14b
  109. burplmstudio llama-3.1-8b-instruct
  110. ```
  111. To make these available in every shell, add the `source` lines to your
  112. `~/.zshrc`.
  113. ---
  114. ## What this enables
  115. You are not running a scanner.
  116. You are reviewing real traffic with assisted reasoning.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.