
Agent-driven bug bounty / pentest framework: one gated chain over five systems (Caido, HexStrike
Agent-driven bug bounty / pentest framework: one gated chain over five systems (Caido, HexStrike, Jev, Memgraph, TencentDB, Prometheus)
·
MCP toolkit for agent-driven pentesting. The agent harness (Claude Code, or any MCP-capable LLM) is the reasoning loop. Jcyber provides scope-gated scanning tools, an evidence graph, a finding lifecycle, and long-term memory through an MCP server.
Agent Harness (Claude Code / any MCP client)
|
| MCP protocol (stdio)
v
Jcyber MCP Server ---- scope gate (pre-hook, every call)
| | | |
v v v v
HexStrike Memgraph TencentDB Caido
(:8899) (:7687) (memory) (:8889)
| |
+----------> Target <----------------+The agent decides what to scan, when to create hypotheses, and when to promote findings. Jcyber enforces safety in code: the scope gate runs before every tool call, exploit tools require operator confirmation, and all evidence is normalized into the engagement graph.
| Component | Role |
|---|---|
| HexStrike | Hands - 150+ security scanning tools via REST |
| Memgraph | Session brain - engagement graph (evidence, hypotheses, findings) |
| TencentDB | Long-term memory - cross-engagement recall and learning |
| Caido | Traffic substrate - proxy, request logging, passive plugins |
nmap_scan, nuclei_scan, sqlmap_scan, ffuf_scan, httpx_probe, etc. Each scope-gated.confirm_difference - 3-gate confirmation: baseline vs attack request, mechanical response diff (status, body, timing). Absorbed from CyberStrike.create_hypothesis, promote_finding (endpoint-aware duplicate triage), score_finding, retire_hypothesis, create_attack_chain, get_attack_chainsintake_target, get_state, render_findings_report, get_decision_tracerecall_lessons, commit_learningssuggest_severity, check_duplicateuv:8899:8889 (API on :8080).env: TYPESAFE_API_KEY, CAIDO_API_TOKEN (auto-loaded by python-dotenv)| Service | Port | Notes |
|---|---|---|
| HexStrike | 8899 | REST API for security tools |
| Caido | 8889 | HTTP proxy, passive plugins |
| Memgraph | 7687 | Bolt protocol (graph DB) |
| Memgraph Lab | 3000 | Web UI for graph inspection |
1. Install.
uv sync2. Start the session brain (Memgraph).
docker compose -f deploy/docker-compose.memgraph.yml up -d3. Start the MCP server.
Option A - standalone server (connect your agent separately):
python -m jcyber serveOption B - intake a target and start serving:
python -m jcyber run https://example.com4. Connect your agent. Add the MCP server to your agent's config. For Claude Code / OMP, add to your MCP config:
{
"jcyber": {
"type": "stdio",
"command": "python",
"args": ["-m", "jcyber", "serve"]
}
}The agent reads the SKILL.md methodology and drives the engagement through MCP tool calls.
| Variable | Default | Purpose |
|---|---|---|
HEXSTRIKE_URL | http://127.0.0.1:8899 | HexStrike REST endpoint |
MEMGRAPH_URI | bolt://127.0.0.1:7687 | Memgraph Bolt endpoint |
JCYBER_MEMORY_URL | (none) | TencentDB memory-core endpoint |
CAIDO_PROXY | 127.0.0.1:8889 | Caido proxy listener (TCP health-checked) |
CAIDO_API_URL | http://127.0.0.1:8080 | Caido instance GraphQL API |
CAIDO_API_TOKEN | (none) | Caido access token (in .env) |
TYPESAFE_API_KEY | (none) | TypeSafe API key for Jev classifiers (in .env) |
Secrets live in .env (auto-loaded by python-dotenv at startup).
metasploit_run, hydra_attack, etc.) return a confirmation prompt instead of executing. Operator must approve.python -m jcyber serve # start MCP server (stdio)
python -m jcyber run <url> # intake target + start MCP server
python -m jcyber intake <link> # create engagement directory
python -m jcyber report <dir> # render engagement report
python -m jcyber trace <dir> # render decision tracejcyber/
mcp_server.py MCP server with all 57 tools
SKILL.md Agent methodology (the pentesting ladder)
scope.py Deterministic scope gate
normalize.py Evidence normalization (sha256, summary)
config.py Engagement + scope config parsing
intake.py Bare-link intake (URL -> engagement)
report.py Report renderer (graph -> Markdown)
trace.py Decision trace renderer
learn.py Distiller (findings -> long-term memory)
ports.py Protocol interfaces
types.py Domain types (Evidence, Scope, Severity)
clients/
hexstrike.py HexStrike REST adapter
memgraph.py Memgraph Bolt adapter
tencentdb.py TencentDB HTTP adapter
caido.py Caido GraphQL adapter
toon.py TOON codec (CLI wrapper)
schema/
memgraph/ Engagement graph DDL + indexes
storage-layout.md TOON config shapes
tencentdb/ Memory interface spec
tests/ pytest suite (no external deps needed)
deploy/ Docker Compose for Memgraphuv run pytest -q
uv run ruff check . && uv run ruff format --check .
uv run pyrightSee CONTRIBUTING.md.
Jcyber assumes in-scope targets only. The scope gate is load-bearing, not decorative: it is deterministic string matching enforced in code as a pre-hook on every MCP tool call. Out-of-scope targets are rejected before reaching any scanner. Nothing in this repo grants permission to test any system. Authorization is the operator's responsibility.
MIT - see LICENSE.
This repo does not document an install step we could read. Check the README on GitHub.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/jcyber to learn what the "Jcyber" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
This server doesn't publish a machine-readable tool manifest, and it doesn't expose a public endpoint we could ask. Connect the server locally to see what it exposes.
We could not run this server: it ships no npx package for our sandbox and no public endpoint. The four checks that need a live server are left out, and the grade tops out at B until one exists.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/jcyber)Nothing comparable is listed yet.
No tagged releases on record.
Connect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "jcyber" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.