mcp-supply-guard
🧬 mcp-supply-guard
Integridad de la cadena de suministro de definiciones de herramientas MCP. Dato de seguridad 2026: el 43% de los servidores MCP tienen vulnerabilidades de inyección de comandos, y las definiciones de herramientas pueden mutar después de la aprobación, un vector de "rug-pull". Esta biblioteca fija una línea base de hashes de contenido de definiciones de herramientas tras la revisión, luego verifica en cargas posteriores: señalando herramientas añadidas / eliminadas / modificadas, además de un escaneo de riesgo para señales de peligro de ejecución de comandos.
Cero dependencias. Solo stdlib de Python.
Inicio rápido
pip install mcp-supply-guardRelated MCP server: heddle
Uso
from mcp_supply_guard import load_tools, fingerprint, verify, scan_risk
baseline = [fingerprint(t) for t in load_tools("approved.json")] # lock after review
report = verify(load_tools("current.json"), baseline)
print(report.clean) # False if any tool added/modified
for f in report.findings:
print(f.kind, f.tool, f.message)
risks = scan_risk(load_tools("current.json"))CLI
mcp-supply-guard lock approved.json baseline.json
mcp-supply-guard verify current.json baseline.json --json # CI exit 1 on added/modified
mcp-supply-guard risk current.json --jsontools.json
{"tools": [{"name": "search", "description": "Search the index",
"inputSchema": {"type": "object", "properties": {"q": {"type": "string"}}}}]}Hallazgos
Kind | Severity | Meaning |
| error | herramienta añadida después de bloquear la línea base |
| error | el hash de la definición cambió (vector rug-pull) |
| warning | la herramienta de la línea base ahora falta |
| error/warning | señales de peligro de ejecución de comandos en descripción/esquema |
Licencia
MIT © wwb-bill
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- AlicenseCqualityDmaintenanceEnables secure, zero-trust access to MCP tools through short-lived, signed capability leases that bind tool execution to specific sessions, intents, and constraints. Prevents prompt injection attacks and privilege escalation with dynamic risk scoring, policy enforcement, and tamper-evident audit logging.41MIT
- Alicense-qualityAmaintenanceEnables users to define and run MCP tools using declarative YAML configs with built-in trust enforcement, credential brokering, and tamper-evident audit logging.14MIT

commit-check-mcpofficial
AlicenseAqualityAmaintenanceEnables validation of commit messages, branch names, author info, push safety, and repository state using commit-check rules, accessible as MCP tools.8MIT- AlicenseAqualityBmaintenanceVerify-before-act safety tools for AI coding agents, providing MCP tools to check packages, lockfiles, manifests, and CI workflows for supply chain risks.449MIT
Related MCP Connectors
Static MCP manifest and tool-policy security preflight with signed input-redacted receipts
Remote MCP for tool license checks, vendor policy review, alternatives, and license receipts.
Free MCP tools: the only MCP linter, health checks, cost estimation, and trust evaluation.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/wwb-bill/mcp-supply-guard'
If you have feedback or need assistance with the MCP directory API, please join our Discord server