What vulnerability types does Mcp Scan detect?
It detects prompt injection risks, tool poisoning patterns, and excessive permissions.
@Chris79OG
Basic information
MCP server security scanner that detects vulnerability patterns in MCP server configurations and outputs SARIF reports. Scans for prompt injection risks, tool poisoning, excessive permissions, and other security issues in Model Context Protocol servers.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"mcp-scan": {
"command": "npx",
"args": [
"@syntrophy/mcp-scan"
]
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Mcp Scan is a security scanner for MCP servers. It detects common vulnerability patterns such as prompt injection and tool poisoning, flags excessive permissions, and outputs its findings as SARIF 2.1.0 reports.
Run it directly via npx without installation: npx @syntrophy/mcp-scan. No other configuration or invocation details are provided in the README.
It detects prompt injection risks, tool poisoning patterns, and excessive permissions.
Installation is not required; run it directly with `npx @syntrophy/mcp-scan`.
It outputs standard SARIF 2.1.0 reports.
Yes, it is executed as a one‑off command via npx; no explicit runtime dependencies are mentioned in the README.
Modelglass turns "which model should I use?" into a lookup instead of a guess. Seven tools give your agent live pricing across image, language, video, and audio models. Sourced and versioned, not scraped once and forgott

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP
MCP server that lets Claude Code, Cursor or Codex ask you for API keys on a local page and write them to .env. The agent only ever sees key names.

Nebelus is an enterprise agentic-AI platform for regulated industries. This MCP server exposes the Nebelus Construction API: ~48 tools that give an MCP client full agent build parity — create/update/probe agents, edit ag
Comments