MCP server de Agent Runtime Proof
Commit 13 sept 2026Verifica que un proceso de un agente de IA o un MCP server en ejecución coincida con un artefacto aprobado para prevenir ataques de runtime por reemplazo o procesos obsoletos.
También conocido como fantasyce/agent-runtime-proof, agent-runtime-proof
- Stars
- 1
- Herramientas
- —
- Descargas, 30 días
- —
- Última versión
- 1.1.0
- Último commit
- 13 sept 2026
- Licencia
- Apache-2.0
¿Qué es Agent Runtime Proof MCP?
Agent Runtime Proof es un MCP server. Verifica que un proceso de un agente de IA o un MCP server en ejecución coincida con un artefacto aprobado para prevenir ataques de runtime por reemplazo o procesos obsoletos.
Resumen generado a partir del README del proyecto
Acerca del MCP server de Agent Runtime Proof
Agent Runtime Proof proporciona un mecanismo local de solo lectura para verificar que un proceso de un agente de IA o un MCP server en ejecución coincida con un artefacto aprobado específico. Resuelve el problema de seguridad que ocurre cuando un archivo en el disco se actualiza mientras un proceso antiguo, potencialmente obsoleto o reemplazado, continúa ejecutándose. Al vincular la identidad del proceso en vivo con una expectativa explícita, garantiza que el código que realmente está realizando el trabajo sea la versión exacta que pretendías ejecutar.
Esta herramienta funciona localmente en macOS, Linux y Windows. Puede utilizarse a través de una interfaz de línea de comandos o como un MCP server local vía stdio. Cuando se usa como MCP server, expone tres herramientas específicas: list_local_runtime_candidates, inspect_local_runtimes y verify_local_runtime. Está diseñada para ser respetuosa con la privacidad, omitiendo datos sensibles como valores de entorno, credenciales o líneas de comandos en sus respuestas. Funciona con varios hosts, incluyendo Claude Code, Cursor y VS Code a través de los perfiles de host proporcionados.
Qué puedes hacer con él
- 1Detectar runtimes de procesos obsoletosVerifica si un proceso en ejecución es realmente la versión que se encuentra actualmente en tu disco para prevenir ataques de runtime por reemplazo.
- 2Ejecución segura de comandosLanza un comando a través de un testigo que registra la identidad del proceso y proporciona un recibo de lanzamiento basado en contenido.
Escrito a partir del README del proyecto. Cada caso de uso se verifica con una cita del mismo.
Verificaciones automáticas
Ejecutado 15 nov 2026Informe completo →Aún no verificado. Un servidor necesita una puntuación de 80, ningún hallazgo grave y suficientes datos para que podamos revisarlo. Cómo funcionan las verificaciones · Qué corregir para obtener más puntos
- Repositorio de origen vinculado y accesiblefantasyce/agent-runtime-proof is public and reachablegithub.com/fantasyce/agent-runtime-proof ↗Aprobado
- El paquete indica este repositorio como su origenNo verificado
- Procedencia de la compilación (atestación de Sigstore)No verificado
- 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 2026-09-13github.com/fantasyce/agent-runtime-proof ↗Aprobado
- OpenSSF ScorecardNo verificado
- El nombre del paquete no es similar a un paquete popularNo verificado
- 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 GitHubAgent Runtime Proof
Prove the agent runtime you launched is the artifact you approved.
Agent Runtime Proof (ARP) is a local, read-only runtime identity verifier for AI agents and MCP servers. It detects stale, replaced, mismatched, or unverifiable runtimes without uploading code, secrets, process arguments, or process data.
The failure ARP is built for is simple: you replace an Agent or MCP executable, but yesterday's process keeps doing the work. The file on disk is new; the loaded runtime is not. ARP binds live process identity to an explicit artifact expectation and reports the uncertainty instead of treating the file on disk as proof of what is running.
See the reproducible stale-runtime demonstration, or start with the five-minute quickstart.
Quickstart
The current release is
v1.1.0
for macOS arm64, Linux amd64, and Windows amd64. Download the archive and
SHA256SUMS from that release, verify the bytes, then install the single binary
in a user-owned directory. Full commands for each platform are in
docs/quickstart.md; lifecycle and rollback details are in
docs/install.md.
After installation:
agent-runtime-proof --version
agent-runtime-proof doctor --format json
agent-runtime-proof inspect --all --limit 20
Verify a process against an explicit expectation:
agent-runtime-proof verify \
--expectation /absolute/path/to/expectation.json \
--pid 1234 \
--format json
ARP returns MATCHED only when the evidence supports that conclusion.
UNKNOWN, STALE, LEAKED, CONFLICT, and NOT_RUNNING are domain verdicts,
not transport errors.
Local stdio MCP
ARP can run as a local MCP server:
{
"mcpServers": {
"agent-runtime-proof": {
"command": "/absolute/path/to/agent-runtime-proof",
"args": ["mcp"]
}
}
}
It exposes exactly three read-only tools:
list_local_runtime_candidatesinspect_local_runtimesverify_local_runtime
Host profiles are available for Codex, Claude Code, Cursor, OpenCode, DeepSeek Harness, VS Code/GitHub Copilot, and generic hosts. See the host configuration guide. ARP does not edit the host's configuration.
The v1.1.0 Release also includes
agent-runtime-proof_1.1.0.mcpb for compatible MCP clients. Its Registry
metadata binds the bundle URL to its SHA-256 digest; the same three native
binaries remain available as ordinary platform archives.
The same release is published in the
official MCP Registry
as io.github.fantasyce/agent-runtime-proof.
What ARP proves
These controls answer different questions and work best together:
| Evidence | Question it answers |
|---|---|
| SBOM | What dependencies were declared in this build? |
| Signature or build attestation | Who produced these artifact bytes, and through which build? |
| Checksum | Did the downloaded bytes change? |
| Agent Runtime Proof | Is the live local process bound to the artifact expectation I approved? |
ARP does not replace signing, provenance, SBOMs, sandboxing, or host policy. It closes the gap between an approved file and the process that is actually doing the work.
Privacy and safety boundary
ARP is intentionally narrow:
- local processes and local files only;
- CLI, local
stdioMCP, and an optional launch Witness; - read-only observation of Agent and host state;
- no daemon, network listener, repair action, or configuration write;
- no dependency on Across Agents Assistant, Across Context, Across Orchestrator, or Across Autopilot.
MCP responses omit raw argv, environment values, command lines, file contents, credentials, and transcripts. Read the exact guarantees and limitations in docs/data-handling.md, docs/privacy-model.md, and docs/threat-model.md.
CLI and Witness
Inspect one process or a bounded current-user inventory:
agent-runtime-proof inspect --pid 1234 --format json
agent-runtime-proof inspect --all --limit 100
Run a local command through the byte-transparent launch Witness:
agent-runtime-proof witness --expectation expectation.json -- command arg
The Witness records process identity and a content-addressed launch receipt,
then proxies stdin/stdout without rewriting protocol bytes. Hosts that own
process creation can embed the same contract through sdk/witness.
Exit codes are 0 for inspection, doctor, or MATCHED; 2 for a determinate
negative verdict; 3 for UNKNOWN; 64 for invalid input; and 70 for an
internal failure. JSON mode writes one JSON value to stdout; sanitized
diagnostics use stderr.
Supported platforms and limits
Release archives are built for macOS 14+ arm64, Linux amd64, and Windows 11 amd64. Passive inspection of interpreter and declared-tree runtimes remains conservative when the active entrypoint cannot be observed. An on-disk digest alone is never reported as a loaded-runtime match.
Remote attestation, a daemon, network listeners, repair actions, and Agent configuration writes remain outside v1.
Architecture and acceptance
The same contracts and application layer drive the CLI, MCP server, Witness, and data-only Host Profiles. Technical design is documented in architecture-development-acceptance.md.
Acceptance records:
- Phase 0 contracts
- Phase 1 macOS core
- Phase 1 Windows core
- Phase 2 MCP
- Phase 3 Witness
- Phase 4 host matrix
- Phase 5 open-source release
Maintainers can run the complete source gate with:
bash scripts/check.sh
Release assets include CycloneDX SBOMs, SHA-256 checksums, and GitHub artifact attestations. Publication state is determined by the public GitHub Release, not by a local acceptance record.
Agent Reliability Toolkit
ARP is one independent part of a small, local-first reliability toolkit:
- Agent Recall Trail keeps private Agent memory separate from reviewed shared knowledge.
- Agent Runtime Proof verifies that a live Agent or MCP runtime matches the artifact you approved.
- Agent Residue Evidence records task-scoped files, processes, and listening ports left by tests and builds.
Each project remains separately installable and keeps its own trust boundary.
Community
Contributions and independent host/runtime cases are welcome. For a sanitized Codex or DSH integration, share the host, version, launch relationship, and observed proof boundary in the design-partner issue. DSH users can also join the official community discussion. Read CONTRIBUTING.md, CODE_OF_CONDUCT.md, and SUPPORT.md. Report vulnerabilities privately as described in SECURITY.md; do not put secrets or sensitive process data in a public issue.
Apache-2.0 licensed. See LICENSE.
Preguntas sobre Agent Runtime Proof MCP
¿Qué es lo que realmente verifica Agent Runtime Proof?
Verifica si el proceso local en vivo está vinculado a la expectativa específica del artefacto que aprobaste, cerrando la brecha entre un archivo aprobado y el proceso que realmente se está ejecutando.
¿Esta herramienta sube mi código o secretos?
No, es un verificador local de solo lectura que detecta desajustes en el runtime sin subir código, secretos, argumentos de proceso o datos del proceso.
¿Qué plataformas son compatibles?
La herramienta está disponible para macOS 14+ (arm64), Linux (amd64) y Windows 11 (amd64).