AgentGraph Trust
AgentGraph Trust is a MCP server that performs security scanning and trust verification on AI agent tools.
About
AgentGraph Trust is an MCP server from AgentGraph Co. that provides security scanning and trust verification for AI agent tools—skills, MCP servers, and related packages you might paste into Claude Code or Cursor. developers face a growing supply chain problem: every new skill is arbitrary code with repository access. This server exposes verification workflows through stdio MCP (PyPI package agentgraph-trust, version 0.3.0) so you can check trust signals before install rather than after an incident. It complements manual README review and community reputation, not replaces formal penetration tests or organizational vendor review. Use it when you discover tools on marketplaces or GitHub and need a structured security-oriented second opinion aligned with agent tooling rather than generic npm audit alone.
- Security scanning and trust verification focused on AI agent tools
- Published as AgentGraph Trust MCP server v0.3.0 on PyPI (agentgraph-trust)
- Stdio transport for integration with MCP-capable coding agents
- Helps reduce supply-chain risk from unvetted skills and servers
- From agentgraph-co with MCP schema 2025-12-11 metadata
AgentGraph Trust by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add agentgraph-trust -- uvx agentgraph-trustAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | agentgraph-trust |
|---|---|
| Transport | STDIO |
| Auth | None |
What it does
Scan and verify trust for MCP servers, skills, and agent tools before you add them to Claude Code or Cursor.
Who is it for?
Best when you're curating skills and MCP servers from the open ecosystem and want a dedicated agent-tool trust scan.
Skip if: Skip if you have mandated enterprise SCA/SAST pipelines that already gate every dependency with legal and infra sign-off.
What you get
You run trust and security checks through MCP before installing third-party agent tooling.
- Trust and security assessment outputs for agent tools via MCP
- Clearer install/no-install decisions for third-party skills and servers
- Reduced blind trust when expanding agent capability surface
By the numbers
- MCP server version 0.3.0
- Product title: AgentGraph Trust
- Transport: stdio
Recommended MCP Servers
1Claw VaultHSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.2
1passwordMCP server for 1Password service accounts — tools and resources for vaults and credentials18
402sentinel McpAssess an x402 counterparty's risk BEFORE paying: allow/review/block, scored on-chain (Base).1
A2adependencyinspector McpRemote MCP for A2A dependency inspector MCP, structured receipts, audit logs, and reviewer-ready eviA2a Governance Bridge McpA2A Governance Bridge MCP server.A2aidentitytoll McpRemote MCP for A2A caller identity, scope policy, verdict receipts, and audit history.How it compares
Agent-tool trust MCP scanner, not a runtime WAF or a generic dependency-only npm audit skill.
FAQ
Who is agentgraph-trust for?
Developers and agent power users evaluating MCP servers and skills before adding them to local agent configs.
When should I use agentgraph-trust?
Use it during ship/security review whenever you install or update third-party agent tools from GitHub, registries, or marketplaces.
How do I add agentgraph-trust to my agent?
Install the PyPI package agentgraph-trust, register it as a stdio MCP server in Claude Code or Cursor, and invoke trust verification tools on candidates before install.