Memastikan batasan scope penetration testing untuk AI agent dengan memvalidasi tool call MCP terhadap target, teknik, dan jendela waktu yang telah disetujui.
Juga dikenal sebagai IntegSec/agentic-pentest-proxy, @integsec/agentic-pentest-proxy
- Stars
- 9
- Tools
- —
- Unduhan, 30 hari
- 6.447
- Versi terbaru
- —
- Commit terakhir
- 10 Nov 2026
- Lisensi
- Apache-2.0
Apa itu agentic-pentest-proxy MCP?
agentic-pentest-proxy adalah MCP server. Memastikan batasan scope penetration testing untuk AI agent dengan memvalidasi tool call MCP terhadap target, teknik, dan jendela waktu yang telah disetujui.
Ringkasan dibuat dari README proyek
Tentang agentic-pentest-proxy MCP server
MCP proxy ini berfungsi sebagai security gateway untuk engagement penetration testing yang melibatkan AI agent. Proxy ini berada di antara MCP client, seperti Claude Desktop atau Claude Code, dan tools Anda yang sudah ada untuk memastikan setiap tool call mematuhi manifest scope yang telah ditentukan. Dengan memvalidasi argumen terhadap target yang disetujui, teknik spesifik, dan jendela waktu yang diizinkan, proxy ini mencegah agent melakukan tindakan yang tidak sah selama pengujian.
Developer dapat men-deploy ini menggunakan Node.js 22 atau versi terbaru melalui npm, Docker, atau image GHCR. Sistem ini mendukung berbagai tipe koneksi termasuk stdio untuk perintah lokal, SSE untuk upstreams seperti Burp Suite, dan layanan HTTP. Sistem ini mencakup managed gateway dengan UI browser untuk administrasi tim dan MCP workbench yang memungkinkan pengguna untuk mencegat, mengedit, atau membatalkan request secara real-time. Semua keputusan dicatat dalam audit log lokal, yang dapat dipantau melalui terminal user interface khusus.
Apa yang bisa Anda lakukan dengannya
- 1Menegakkan batasan engagementMencegah AI agent menyerang target atau menggunakan teknik yang berada di luar scope penetration testing yang telah disetujui.
- 2Inspeksi dan modifikasi request secara manualGunakan workbench untuk mencegat tool calls dan mengubah argumennya sebelum mencapai upstream MCP server.
Ditulis berdasarkan README proyek. Setiap use case diperiksa terhadap kutipan dari README tersebut.
Cara menginstal agentic-pentest-proxy MCP
Format diverifikasi 10 Nov 2026Tambahkan ke CursorTambahkan ke GooseInstal agentic-pentest-proxy MCP di Claude Code
$ claude mcp add agentic-pentest-proxy -- npx -y @integsec/agentic-pentest-proxyInstal agentic-pentest-proxy MCP di Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agentic-pentest-proxy": {
"command": "npx",
"args": [
"-y",
"@integsec/agentic-pentest-proxy"
]
}
}
}Instal agentic-pentest-proxy MCP di VS Code
.vscode/mcp.json
{
"servers": {
"agentic-pentest-proxy": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@integsec/agentic-pentest-proxy"
]
}
}
}Instal agentic-pentest-proxy MCP di VS Code CLI
$ code --add-mcp '{"name":"agentic-pentest-proxy","type":"stdio","command":"npx","args":["-y","@integsec/agentic-pentest-proxy"]}'Instal agentic-pentest-proxy MCP di Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"agentic-pentest-proxy": {
"command": "npx",
"args": [
"-y",
"@integsec/agentic-pentest-proxy"
]
}
}
}Instal agentic-pentest-proxy MCP di Codex
$ codex mcp add agentic-pentest-proxy -- npx -y @integsec/agentic-pentest-proxyInstal agentic-pentest-proxy MCP di Codex config.toml
~/.codex/config.toml
[mcp_servers.agentic-pentest-proxy] command = "npx" args = ["-y", "@integsec/agentic-pentest-proxy"]
Instal agentic-pentest-proxy MCP di Gemini CLI
$ gemini mcp add -s user agentic-pentest-proxy npx -- -y @integsec/agentic-pentest-proxyInstal agentic-pentest-proxy MCP di Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agentic-pentest-proxy": {
"command": "npx",
"args": [
"-y",
"@integsec/agentic-pentest-proxy"
]
}
}
}Konfigurasi
AUDIT_LOG_PATHMCP_TRANSPORTSCOPE_MANIFEST_PATHUPSTREAM_MCP_ARGS_JSONUPSTREAM_MCP_COMMAND
| Nama | Deskripsi | Tipe |
|---|---|---|
| AUDIT_LOG_PATH | — | |
| MCP_TRANSPORT | — | |
| SCOPE_MANIFEST_PATH | — | |
| UPSTREAM_MCP_ARGS_JSON | — | |
| UPSTREAM_MCP_COMMAND | — |
Pengecekan otomatis
Berjalan 13 Nov 2026Laporan lengkap →Lolos checks otomatis kami. Ini bukan audit keamanan: baca kodenya dan berikan server akses paling terbatas yang dibutuhkannya. Cara kerja checks
- Source repository terhubung dan dapat dijangkauintegsec/agentic-pentest-proxy is public and reachablegithub.com/integsec/agentic-pentest-proxy ↗Lolos
- Nama paket mencantumkan repositori ini sebagai sumbernya@integsec/agentic-pentest-proxy names integsec/agentic-pentest-proxy as sourcenpmjs.com/package/@integsec/agentic-pentest-proxy ↗Lolos
- Provenance build (atestasi Sigstore)Sigstore attestation for @integsec/agentic-pentest-proxynpmjs.com/package/@integsec/agentic-pentest-proxy/v/0.4.12#p ↗Lolos
- Lisensi open source (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Lolos
- Ada commit atau release dalam satu tahun terakhirLast commit or release 2026-11-10github.com/integsec/agentic-pentest-proxy ↗Lolos
- OpenSSF ScorecardTidak diperiksa
- Nama package tidak mirip dengan package populerNo popular package one edit away from @integsec/agentic-pentest-proxyLolos
- Tidak ada advisory kritis pada paket atau dependensinyaTidak diperiksa
- Tidak ada instruksi tersembunyi untuk model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersLolos
- Tools yang bersifat destruktif telah diberi labelTidak diperiksa
- Endpoint remote merespons handshake MCPTidak diperiksa
README
Lihat di GitHubAgentic Pentesting MCP Gateway
New to the gateway? The documentation site shows the local and hosted paths side by side, including where test traffic comes from. The full guides below are also available there after team sign-in.
An MCP proxy that checks tool calls against a pentest scope manifest before forwarding them to your MCP tools. It blocks calls it can identify as outside the targets, techniques, or time window you approved, and records decisions in a local audit log.
Requires Node.js 22 or newer. The proxy supports stdio tools, SSE upstreams such as Burp Suite, and HTTP upstreams.
Managing several tools? The managed gateway adds a browser UI with local MCP server presets, scope templates and technique checkboxes, JSON policy import and download, administrator approval and assignment, and a separate engagement choice for each user. It exposes scoped tools, an active engagement resource, PlexTrac reference resources, a TurboPentest knowledge-base catalog with search and controlled live reads, and guided pentest prompts. It supports one hosted MCP URL for ChatGPT and Claude and a local Burp route.
The MCP workbench shows your live tool calls and background jobs. Intercept requests, edit arguments before forwarding, or drop a call. Long calls return a job ID that you can inspect or cancel without waiting for one MCP request to stay open. The gateway checks scope again after any edit.
To keep the local gateway running after sign-in, use pentest-gateway service install; use pentest-gateway service remove to undo it. It binds to loopback only. See the local startup guide. The gateway cannot prevent an agent with a separate shell or network path from bypassing MCP checks; see the secure deployment guide.
Quick start: add an MCP tool
-
Install the proxy:
npm install -g @integsec/agentic-pentest-proxy -
Create a scope manifest with the guided wizard:
pentest-manifest new -o scope.jsonSet the real engagement targets and time window. Review the generated file with the engagement owner before using it.
-
Generate a client entry for each MCP tool. Put the tool's normal launch command after
--:pentest-setup --name scanner-scoped --manifest ./scope.json -- npx -y @example/scanner-mcpReplace
npx -y @example/scanner-mcpwith the command from your tool's own setup instructions. The command prints anmcpServersentry. Paste that entry into your MCP client's configuration and restart the client. To add another tool, run setup again with a new--name, then add its entry under the samemcpServersobject.For example, the generated entry has this shape (the setup command fills in your actual manifest and audit paths):
{ "mcpServers": { "scanner-scoped": { "command": "pentest-proxy", "env": { "SCOPE_MANIFEST_PATH": "/path/to/scope.json", "MCP_TRANSPORT": "stdio", "AUDIT_LOG_PATH": "/path/to/audit", "UPSTREAM_MCP_COMMAND": "npx", "UPSTREAM_MCP_ARGS_JSON": "[\"-y\",\"@example/scanner-mcp\"]" } } } }Use the
mcpServersblock in Claude Desktop's MCP configuration or in your Claude Code project's.mcp.json. Other MCP clients may label the server settings differently; use the generated command and environment variables in their equivalent fields. The proxy starts when the client launches the tool. -
Watch decisions in another terminal:
pentest-tui --audit-path ./auditSetup prints the exact audit path to use. If your shell is in another directory, use that printed path. For a one-off TUI without a global install:
npm exec --yes --package=@integsec/agentic-pentest-proxy -- pentest-tui --audit-path ./auditThe TUI reads local audit files; it does not start the proxy. See TUI screenshots.

Other MCP tool types
| Tool connection | What to do |
|---|---|
| stdio tool launched by a command | Use the setup command above with -- <command> [args...]. |
| SSE upstream already listening, such as Burp Suite | Use pentest-setup --name burp-scoped --manifest ./scope.json --sse http://127.0.0.1:9876. |
| HTTP upstream | Run the proxy as an HTTP service and point your MCP client at it. HTTP and Docker guide. |
Use one generated client entry per upstream tool. A single scope manifest can be shared by several entries; each call still gets checked. More client examples.
What gets checked
The proxy checks MCP tools/call arguments it can inspect. It blocks unknown target-bearing arguments, out-of-scope targets, explicit exclusions, restricted techniques, expired engagement windows, and free-form commands by default. DNS names authorized through IP ranges must resolve entirely inside the allowed ranges. Local JSONL auditing is always on; cloud logging is optional.
The proxy cannot control destinations selected inside an upstream tool, HTTP redirects, targets read from files or encoded payloads, DNS changes after validation, or traffic that bypasses MCP. Use network egress controls and review each upstream tool's schema before relying on the proxy for an engagement. Security model.
Install and release options
| Option | Command or image |
|---|---|
| Global npm install | npm install -g @integsec/agentic-pentest-proxy |
| Project install | npm install @integsec/agentic-pentest-proxy |
| GHCR image | ghcr.io/integsec/agentic-pentest-proxy:latest |
| Docker Hub image | integsec/agentic-pentest-mcp-proxy:latest |
The npm package includes the gateway, proxy, manifest builder, setup helper, TUI, bridge, and scanner adapter. Run pentest-gateway version or pentest-gateway --version to check the installed release. The older integsec- command names still work for existing client configurations. To see the optional install welcome banner, add --foreground-scripts; npm hides package install-script output by default. You can always run pentest-gateway --help for the same next steps. The welcome script does not access the network or modify files.
Google Cloud logging and Secret Manager SDKs are opt-in to keep the default install lean and free of their deprecated transitive package. If you use either GCP backend, install the SDKs alongside the proxy:
npm install -g @integsec/agentic-pentest-proxy @google-cloud/logging @google-cloud/secret-manager
AWS and Azure SDKs are included as optional dependencies. See configuration and cloud setup for the required environment variables and Docker notes. If you use GCP and are upgrading from 0.2.6, install the GCP SDKs before restarting the proxy; it now reports a missing Cloud Logging SDK at startup.
Troubleshooting
| Symptom | Check |
|---|---|
| Tool does not appear in your MCP client | Paste the generated entry inside one mcpServers object, restart the client, and confirm the client can run pentest-proxy. |
| TUI shows no decisions | Start a tool call, then use the exact audit path printed by setup. The TUI and client may have different working directories. |
| Call is blocked | Check the decision and reason in the TUI or audit JSONL. Confirm the target, exclusions, technique, and window in your manifest. |
| GCP backend says its SDK is missing | Install the two GCP packages shown above alongside the proxy. |
| Need all CLI options | Run pentest-gateway --help, pentest-proxy --help, pentest-setup --help, pentest-manifest --help, or pentest-tui --help. |
Reference
- Configuration and manifest fields
- Client integrations, HTTP, and Docker
- TUI usage and screenshots
- Security model and limitations
- Contributing and development
License
Apache-2.0. See LICENSE.
Pertanyaan tentang agentic-pentest-proxy MCP
Bagaimana cara menambahkan agentic-pentest-proxy MCP ke Claude Code?
Jalankan claude mcp add agentic-pentest-proxy -- npx -y @integsec/agentic-pentest-proxy di terminal Anda. Tambahkan --scope user agar tersedia di semua proyek.
Bagaimana cara menambahkan agentic-pentest-proxy MCP ke Cursor?
Buka ~/.cursor/mcp.json dan tambahkan server di bawah mcpServers, menggunakan config Cursor yang ditunjukkan di bagian instalasi di atas.
Apa yang sebenarnya diperiksa oleh proxy ini?
Proxy ini memeriksa argumen tool call MCP untuk memblokir argumen yang mengandung target tidak dikenal, target di luar scope, teknik yang dilarang, dan jendela waktu engagement yang sudah kedaluwarsa.
Apakah proxy ini bisa mencegah agent melewati pengecekan melalui shell terpisah?
Tidak, gateway ini tidak dapat mencegah agent yang memiliki shell atau jalur jaringan terpisah untuk melewati pengecekan MCP.
Jenis koneksi MCP tool apa saja yang didukung?
Proxy ini mendukung stdio tools, SSE upstreams (seperti Burp Suite), dan HTTP upstreams.