Aplica el alcance de las pruebas de penetración para agentes de IA validando las llamadas a herramientas MCP contra objetivos, técnicas y ventanas de tiempo aprobadas.
También conocido como IntegSec/agentic-pentest-proxy, @integsec/agentic-pentest-proxy
- Stars
- 9
- Herramientas
- —
- Descargas, 30 días
- 6447
- Última versión
- —
- Último commit
- 10 nov 2026
- Licencia
- Apache-2.0
¿Qué es agentic-pentest-proxy MCP?
agentic-pentest-proxy es un MCP server. Aplica el alcance de las pruebas de penetración para agentes de IA validando las llamadas a herramientas MCP contra objetivos, técnicas y ventanas de tiempo aprobadas.
Resumen generado a partir del README del proyecto
Acerca del MCP server de agentic-pentest-proxy
Este proxy MCP actúa como un gateway de seguridad para proyectos de pruebas de penetración que involucran agentes de IA. Se sitúa entre un cliente MCP, como Claude Desktop o Claude Code, y tus herramientas actuales para garantizar que cada llamada a una herramienta cumpla con un manifiesto de alcance predefinido. Al validar los argumentos frente a objetivos aprobados, técnicas específicas y ventanas de tiempo autorizadas, el proxy evita que los agentes realicen acciones no autorizadas durante una prueba.
Los desarrolladores pueden implementar esto usando Node.js 22 o superior a través de npm, Docker o imágenes de GHCR. El sistema admite varios tipos de conexión, incluyendo stdio para comandos locales, SSE para upstreams como Burp Suite y servicios HTTP. Incluye un gateway gestionado con una interfaz de navegador para la administración de equipos y un workbench de MCP que permite a los usuarios interceptar, editar o descartar solicitudes en tiempo real. Todas las decisiones se registran en un log de auditoría local, que puede monitorearse a través de una interfaz de usuario de terminal dedicada.
Qué puedes hacer con él
- 1Imponer límites de ejecuciónEvita que un agente de IA ataque objetivos o utilice técnicas que queden fuera del alcance aprobado de la prueba de penetración.
- 2Inspeccionar y modificar solicitudes manualmenteUtiliza un workbench para interceptar llamadas a herramientas y cambiar sus argumentos antes de que lleguen al MCP server de origen.
Escrito a partir del README del proyecto. Cada caso de uso se verifica con una cita del mismo.
Cómo instalar agentic-pentest-proxy MCP
Formatos verificados el 10 nov 2026Añadir a CursorAñadir a GooseInstalar agentic-pentest-proxy MCP en Claude Code
$ claude mcp add agentic-pentest-proxy -- npx -y @integsec/agentic-pentest-proxyInstalar agentic-pentest-proxy MCP en Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agentic-pentest-proxy": {
"command": "npx",
"args": [
"-y",
"@integsec/agentic-pentest-proxy"
]
}
}
}Instalar agentic-pentest-proxy MCP en VS Code
.vscode/mcp.json
{
"servers": {
"agentic-pentest-proxy": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@integsec/agentic-pentest-proxy"
]
}
}
}Instalar agentic-pentest-proxy MCP en VS Code CLI
$ code --add-mcp '{"name":"agentic-pentest-proxy","type":"stdio","command":"npx","args":["-y","@integsec/agentic-pentest-proxy"]}'Instalar agentic-pentest-proxy MCP en Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"agentic-pentest-proxy": {
"command": "npx",
"args": [
"-y",
"@integsec/agentic-pentest-proxy"
]
}
}
}Instalar agentic-pentest-proxy MCP en Codex
$ codex mcp add agentic-pentest-proxy -- npx -y @integsec/agentic-pentest-proxyInstalar agentic-pentest-proxy MCP en Codex config.toml
~/.codex/config.toml
[mcp_servers.agentic-pentest-proxy] command = "npx" args = ["-y", "@integsec/agentic-pentest-proxy"]
Instalar agentic-pentest-proxy MCP en Gemini CLI
$ gemini mcp add -s user agentic-pentest-proxy npx -- -y @integsec/agentic-pentest-proxyInstalar agentic-pentest-proxy MCP en Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agentic-pentest-proxy": {
"command": "npx",
"args": [
"-y",
"@integsec/agentic-pentest-proxy"
]
}
}
}Configuración
AUDIT_LOG_PATHMCP_TRANSPORTSCOPE_MANIFEST_PATHUPSTREAM_MCP_ARGS_JSONUPSTREAM_MCP_COMMAND
| Nombre | Descripción | Tipo |
|---|---|---|
| AUDIT_LOG_PATH | — | |
| MCP_TRANSPORT | — | |
| SCOPE_MANIFEST_PATH | — | |
| UPSTREAM_MCP_ARGS_JSON | — | |
| UPSTREAM_MCP_COMMAND | — |
Verificaciones automáticas
Ejecutado 13 nov 2026Informe completo →Pasó nuestras verificaciones automáticas. Esto no es una auditoría de seguridad: lee el código y dale al servidor el acceso más limitado que necesite. Cómo funcionan las verificaciones
- Repositorio de origen vinculado y accesibleintegsec/agentic-pentest-proxy is public and reachablegithub.com/integsec/agentic-pentest-proxy ↗Aprobado
- El paquete indica este repositorio como su origen@integsec/agentic-pentest-proxy names integsec/agentic-pentest-proxy as sourcenpmjs.com/package/@integsec/agentic-pentest-proxy ↗Aprobado
- Procedencia de la compilación (atestación de Sigstore)Sigstore attestation for @integsec/agentic-pentest-proxynpmjs.com/package/@integsec/agentic-pentest-proxy/v/0.4.12#p ↗Aprobado
- Licencia de código abierto (OSI)Apache-2.0spdx.org/licenses/Apache-2.0.html ↗Aprobado
- Commit o lanzamiento en el último añoLast commit or release 2026-11-10github.com/integsec/agentic-pentest-proxy ↗Aprobado
- OpenSSF ScorecardNo verificado
- El nombre del paquete no es similar a un paquete popularNo popular package one edit away from @integsec/agentic-pentest-proxyAprobado
- No hay avisos críticos en el paquete ni en sus dependenciasNo verificado
- Sin instrucciones ocultas para el modelo0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersAprobado
- Las herramientas destructivas están etiquetadasNo verificado
- El endpoint remoto responde al handshake de MCPNo verificado
README
Ver en 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.
Preguntas sobre agentic-pentest-proxy MCP
¿Cómo agrego agentic-pentest-proxy MCP a Claude Code?
Ejecuta claude mcp add agentic-pentest-proxy -- npx -y @integsec/agentic-pentest-proxy en tu terminal. Añade --scope user para que esté disponible en todos los proyectos.
¿Cómo agrego agentic-pentest-proxy MCP a Cursor?
Abre ~/.cursor/mcp.json y añade el servidor en mcpServers, usando la configuración de Cursor que se muestra en la sección de instalación de arriba.
¿Qué es lo que realmente verifica el proxy?
Inspecciona los argumentos de las llamadas a herramientas MCP para bloquear argumentos con objetivos desconocidos, objetivos fuera de alcance, técnicas restringidas y ventanas de tiempo de ejecución expiradas.
¿Puede el proxy evitar que un agente evada las comprobaciones mediante una shell independiente?
No, el gateway no puede evitar que un agente con una shell o ruta de red independiente evada las comprobaciones de MCP.
¿Qué tipos de conexiones de herramientas MCP son compatibles?
El proxy es compatible con herramientas stdio, upstreams SSE (como Burp Suite) y upstreams HTTP.