AgentGraph Trust

io.github.agentgraph-coPublished by GitHub account agentgraph-cov0.3.0Updated Oct 24, 2026

Security scanning and trust verification for AI agent tools.

VerifiedSTDIODesktop onlySecurity & Monitoring

Overview

AI-generated overview

A local MCP server that provides security scanning and trust verification for AI agent tools, letting an assistant check tools before relying on them.

What you can do
Scan AI agent tools for security issues and verify their trustworthiness. The manifest lists no individual tools, so the exact operations are not documented here. It runs as a local process on the user's machine over stdio. No description, instructions or README detail its inputs, outputs or scanning method.
When to use it
Consider it when you want an assistant to vet third-party AI agent tools or MCP servers for security and trust before installing or using them. Because its behavior is undocumented beyond one line, evaluate it carefully first.
Requirements
Runs as a local process on the user's machine, installed from the PyPI package agentgraph-trust over stdio. Desktop only; no web execution. No authentication, environment variables or headers are declared.
Before you install
The manifest declares no credentials, but the server's actual behavior, data handling and any third-party services it contacts are undocumented. Since it is a security tool, confirm what it scans and where results or scanned content are sent before trusting it.

Installation

In SourceWeft

  1. Open AgentGraph Trust in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.3.0LatestSep 16, 2026

Score

25% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.