Practical setup guides and helpers to connect Burp Suite MCP Server to multiple AI backends (Codex, Gemini, Ollama, ...).
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"burp-mcp-agents": {
"command": "<see-readme>",
"args": []
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
Practical setup guides and helpers to connect Burp Suite MCP Server to multiple AI backends (Codex, Gemini, Ollama, LM Studio).
No automated test available for this server. Check the GitHub README for setup instructions.
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
No package registry to scan.
passive_hunterBroad passive vuln surfacing
idor_hunterIDOR/BOLA discovery
auth_flow_mapperAuth vs unauth access mapping
ssrf_redirect_hunterSSRF/open redirect candidates
logic_flaw_hunterMulti-step logic issues
session_scope_hunterToken scope/audience misuse
rate_limit_abuse_hunterRate-limit and abuse gaps
report_writerEvidence-based reporting
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in security
An evil MCP server used for redteam testing
AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.
Proof primitive for AI agents on MultiversX. Anchor file hashes on-chain as verifiable proofs.
mcpki-server is the backend infrastructure for https://www.mcpki.org, enabling secure public key management and autonomous certificate handling for large language models (LLMs).
MCP Security Weekly
Get CVE alerts and security updates for Burp Mcp Agents and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
Practical setup guides and helpers to connect Burp Suite MCP Server to multiple AI backends (Codex, Gemini, Ollama, LM Studio).
This repo focuses on wiring, safety-first workflows, and reusable prompts to analyze real Burp traffic.
No fuzzing. No blind scanning. Only real traffic + reasoning.
Burp MCP Agents is a collection of:
• Backend setup guides (Codex, Gemini, Ollama, LM Studio) • Caddy proxy configuration for MCP SSE • Prompt templates for passive analysis and reporting
Burp Suite MCP Server
▲
│
MCP Bridge
│
┌──────────────────────────────────────────────┐
│ │ │ │
Codex CLI Ollama Agent Gemini CLI LM Studio Agent
| Backend | Mode | Privacy | Difficulty |
|---|---|---|---|
| Codex CLI | Cloud | Medium | Easy |
| Ollama | Local | Full | Advanced |
| Gemini CLI | Cloud | Medium | Easy |
| LM Studio | Local | Full | Advanced |
All setups require:
common/caddy_setup.md)Extender → Extensions → Add → select the jar or from BApp Store.127.0.0.1:9876.See: codex/README.md
Example models
| Model | Use |
|---|---|
| gpt-5.2-codex | General use |
| gpt-5.1 | Faster |
| gpt-5-mini | Low resource |
See: ollama/README.md
Example models
| Model | VRAM | Notes |
|---|---|---|
| llama3.1:8b-instruct | 8GB+ | Small, fast |
| qwen2.5:14b-instruct | 16GB | Mid size |
| llama3.1:70b-instruct | 48GB+ | Large, high VRAM |
See: gemini-cli/README.md
Example models
| Model | Notes |
|---|---|
| gemini-2.0-flash | Fast |
| gemini-2.0-pro | Deeper reasoning |
See: lmstudio/README.md
Example models
| Model | Notes |
|---|---|
| llama-3.1-8b-instruct | Small, fast |
| qwen2.5-14b-instruct | Mid size |
| llama-3.1-70b-instruct | Large, high VRAM |
The real power lives in prompts/:
| Prompt | Purpose |
|---|---|
| passive_hunter.md | Broad passive vuln surfacing |
| idor_hunter.md | IDOR/BOLA discovery |
| auth_flow_mapper.md | Auth vs unauth access mapping |
| ssrf_redirect_hunter.md | SSRF/open redirect candidates |
| logic_flaw_hunter.md | Multi-step logic issues |
| session_scope_hunter.md | Token scope/audience misuse |
| rate_limit_abuse_hunter.md | Rate-limit and abuse gaps |
| report_writer.md | Evidence-based reporting |
See prompts/README.md for usage guidance.
You can use the backend launchers to auto-start Caddy and shut it down when the backend exits.
Source them directly:
source /path/to/burp-mcp-agents/codex/burpcodex.sh
source /path/to/burp-mcp-agents/gemini-cli/burpgemini.sh
source /path/to/burp-mcp-agents/ollama/burpollama.sh
source /path/to/burp-mcp-agents/lmstudio/burplmstudio.sh
Then run:
burpcodex
burpgemini
burpollama deepseek-r1:14b
burplmstudio llama-3.1-8b-instruct
To make these available in every shell, add the source lines to your
~/.zshrc.
You are not running a scanner. You are reviewing real traffic with assisted reasoning.