Vigile Mcp

io.github.Vigile-aiPublished by GitHub account Vigile-aiv0.1.2Updated Oct 24, 2026

Query trust scores for MCP servers and agent skills. Check if a tool is safe.

VerifiedSTDIODesktop onlyDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

A local MCP server that lets an assistant look up Vigile trust scores for MCP servers and agent skills and scan skill files for security issues.

What you can do
Look up trust scores for MCP servers by name or package, and for agent skills such as claude.md or .cursorrules files, with a 0-100 rating and risk level. Scan raw content from skill or rules files for security issues such as tool poisoning, data exfiltration, prompt injection and supply chain attacks. Search the Vigile trust registry by keyword. Verify whether a skill uses location data safely and check for location-based attack patterns.
When to use it
Useful when you want your coding assistant to check whether an MCP server or agent skill is safe before installing or using it, or to screen a skill or rules file for security problems.
Requirements
Runs locally via npx or a global npm install; needs Node.js 18+ and an MCP-compatible client. Works without an account on the public, rate-limited registry; an optional VIGILE_API_KEY environment variable raises limits. Network access to the Vigile service is required.
Before you install
Content scanned with the content-scan tool is sent to the Vigile service, and only that tool consumes the scan quota. Free tier is limited to 10 scans per minute and 50 per month; paid tiers cost $30 or $100 per month. Scores are automated and explicitly not a definitive security guarantee, so treat them as one input among others. An API key is optional and should be kept secret.

Installation

In SourceWeft

  1. Open Vigile Mcp 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.

Other MCP clients

Follow the launch instructions in the repository.

README

This repository has no README.

Tools

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

Version history

1
  1. v0.1.2LatestSep 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.