Fast single-binary security scanner for MCP (Model Context Protocol) servers — config audit, live capability enumeration, tool-poisoning detection & risk grading. Zero deps, fully offline — trivy for
Vet MCP servers before your AI trusts them.
mcprism is a security scanner for Model Context Protocol servers. It finds the servers you have configured, connects to list what each one can do, and checks them against a built-in rule set and a policy you control. Every server gets a list of findings, a 0–100 score and an A–F grade.
It ships as one Go binary with no runtime dependencies, runs fully offline, and only enumerates servers. It never calls a tool, so a scan has no side effects.
MCP connects your AI agent to outside servers for tools, files and data. The protocol is built into Claude Desktop and Claude Code, Cursor, VS Code, Windsurf and others, so a typical setup reaches several servers before long. Those servers run commands, read the filesystem and see your prompts. A malicious or over-privileged server can steal credentials, run commands, or steer the agent through the text it returns. mcprism gives you a per-server report and a score before you let an agent use them, the way you would run trivy against an image.
- Changelog - Attack surface writeup - Launch kit - What it does - When to use it - Report - Install - Quick start - Example output - Policy as code - What it detects - Output formats - Supported clients & transports - CI/CD - How it works - Comparison - FAQ - Roadmap - Contributing
- One binary. No Python or Node setup, no LLM API key, no account. - Static and live checks. It reads the config and performs the MCP handshake to list tools, resources and prompts. It never calls a tool. - Policy as code. Turn rules on/off, change severity, allow or deny
From the project README.
Add the radar badge to your README — it shows your project was picked up by MCP Radar and links to this page:
[](https://mcp.liqiwa.com/s/HUA503--mcprism.html)
MCP security scanner — vet a Model Context Protocol server before you add it to Claude Code, Cursor, or Windsurf. Grades it A–F, catching credential theft, tool-poisoning, and install-script payloads
chawdamrunal/assayMCP & Claude Code security scanner — threat-models plugins, MCP servers, hooks, skills & connectors with an LLM before you trust them. Catches prompt injection, tool poisoning & credential exfiltratio
graygnatconsole/mcp-audit-tool🛡️ Security audit CLI for Model Context Protocol (MCP) servers — scan AI agent configs for tool poisoning, rug pulls, hardcoded secrets, command injection & supply-chain risks. Pure Python, SARIF + CI
agent-chaperone/agent-chaperoneScreens an AI agent's tool calls before they run and tool results before the agent reads them. An MCP proxy plus a hooks adapter for a client's built-in tools.
jiawei686/jev-ultrafast-mcpHand a whole browser task off in one call: a decision model drives the page server-side, so a flow costs one call, not a turn per click. Ref-based element tables, code-checked assertions, zero-model m
00200200/usagetrimKeep the signal. Cut the noise. Local CLI + MCP — fold verbose tool output for Claude Code, Codex, Cursor & Desktop.
The top new MCP servers of the week, every Monday. No spam, unsubscribe anytime.