MCTS has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under Apache-2.0.

How do I install MCTS?

MCTS supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What AI clients work with MCTS?

MCTS is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.

Is MCTS actively maintained?

MCTS is actively maintained — last commit was 7 days ago. It has 28 GitHub stars.

MCTS

Name: MCTS
Author: MCP-Audit

mcp-mcts · by MCP-Audit

MCTS (Model Context Threat Scanner) is a local-first security scanner for MCP servers -- static and live tool discovery, multiple analyzers, auditable risk scores, and JSON, SARIF, and HTML output. For authors and platform teams; CI-ready, no cloud API.

28 GitHub PyPI

No known CVEs

Apache-2.0 license

Actively maintained

Last commit 7d ago

Works with most clients

Transport: stdio, sse, http

0 tools

Grade F

Edit this pageView history

Data Security

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcts": {
      "args": [
        "mcp-mcts"
      ],
      "command": "uvx"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/mcts)](https://mcppedia.org/s/mcts)

Read me

What MCTS does

Security scanner for Model Context Protocol (MCP) servers — the programs that give AI assistants access to tools, files, databases, and APIs.

Test This Server

Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.

uvx 'mcp-mcts' 2>&1 | head -1 && echo "✓ Server started successfully"

After testing, let us know if it worked:

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

59/100across 5 weighted dimensions

How we score →

0255075100

−41

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked mcp-mcts against OSV.dev.

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is MCTS safe to use?: MCTS has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under Apache-2.0.
How do I install MCTS?: MCTS supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What AI clients work with MCTS?: MCTS is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is MCTS actively maintained?: MCTS is actively maintained — last commit was 7 days ago. It has 28 GitHub stars.

Similar servers

Others in data / security

View all →

PostgreSQL MCP Server98

Query and manage PostgreSQL databases directly from AI assistants

87.9k 1

Dbhub96

Zero-dependency, token-efficient database MCP server for Postgres, MySQL, SQL Server, MariaDB, SQLite.

3.1k 2

Supabase MCP Server95

Manage Supabase projects — databases, auth, storage, and edge functions

2.8k 4

Firecrawl Mcp Server95

🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

6.8k 4

MCP Security Weekly

Get CVE alerts and security updates for MCTS and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

Edit this pageView history

Data Security

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, sse, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcts": {
      "args": [
        "mcp-mcts"
      ],
      "command": "uvx"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/mcts)](https://mcppedia.org/s/mcts)

Read me

What MCTS does

Security scanner for Model Context Protocol (MCP) servers — the programs that give AI assistants access to tools, files, databases, and APIs.

Test This Server

Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.

uvx 'mcp-mcts' 2>&1 | head -1 && echo "✓ Server started successfully"

After testing, let us know if it worked:

README

MCTS

Model Context Threat Scanner

Security scanner for Model Context Protocol (MCP) servers — the programs that give AI assistants access to tools, files, databases, and APIs.

Run one command to find permission issues, injection risks, attack chains, and more. Works locally, in CI, with no cloud account required.

New to MCP or MCTS? See the documentation index and glossary.

mcts scan ./server.py   # single entrypoint
mcts scan ./            # entire repository

Demo

Scan the included vulnerable MCP server:

uv run mcts scan examples/vulnerable-mcp-server/server.py

Example terminal output

$ mcts scan examples/vulnerable-mcp-server/server.py
==================== MCTS Security Report ====================
Overall Score:   1/100 (CRITICAL)        ← legacy (--min-score)
Risk Index:      100/100
Scoring basis:   5 Critical, 11 High, 1 Medium (17 scorable findings)
Absolute Risk:   2260 (critical)         ← v2 (--max-absolute-risk)
Security Score:  9/100                   ← v2 benchmark

Severity Summary          Top Findings
● Critical    5           [1] CRITICAL Destructive tool: delete_all_users
● High       11           [2] CRITICAL Read → exfiltration attack chain possible
● Medium      1           ...

Two scores on one scan is normal — see the scoring developer guide.

Problem

AI assistants connect to the outside world through MCP servers — small programs that expose callable tools (e.g. "delete user", "read file", "query database"). A misconfigured or malicious server can:

Grant the AI destructive capabilities it shouldn't have
Hide malicious instructions in tool descriptions
Chain innocent tools into data theft or remote code execution
Leak secrets embedded in server source code

Most teams ship MCP servers without dedicated security review. MCTS makes scanning as routine as running a linter.

Features

MCTS is alpha software with a local-first MCP security pipeline — no cloud account required for standard scans. Full reference: Security checks · CLI.

Scanning & discovery

Capability	How
Repository & entrypoint scan	`mcts scan ./repo/` or `mcts scan ./server.py` — Python + TypeScript static discovery
Auto target resolution	`mcts scan . --auto` — pick entrypoint or lone MCP config server
Multi-surface analysis	`--surfaces tool,prompt,resource,instruction`
Repo instruction discovery	Default on static scans — `SKILL.md`, `prompt.md`, `system_prompt.md` → prompt/instruction analyzers
Live stdio probing	`--live --i-understand-live-risk` — merge runtime schemas with static context
Remote HTTP/SSE	`--url` + Bearer/OAuth — streamable HTTP and SSE transports
Air-gapped snapshot	`--snapshot tools.json` or `mcts snapshot` → offline scan
Machine-wide scan	`mcts scan --machine-wide` — all MCP servers in local client configs
Remote manifest probe	`mcts scan-mcp <url>` — pre-connect `tools/list` check
Per-technique mode	`--technique MCTS-T-*` — run one technique pack at a time

Security analysis

Capability	How
Core metadata checks	Permissions, poisoning, FSP, shadowing, line-jumping, jailbreak resistance
Source-aware SAST	Secrets, command execution, path validation in handler code
Behavioral static SAST	Description vs implementation mismatch + taint (Python, TS, Go, Rust)
Semgrep SAST (opt-in)	`--semgrep` — bundled rule

... View full README on GitHub

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

59/100across 5 weighted dimensions

How we score →

0255075100

−41

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked mcp-mcts against OSV.dev.

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is MCTS safe to use?: MCTS has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under Apache-2.0.
How do I install MCTS?: MCTS supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What AI clients work with MCTS?: MCTS is compatible with claude-desktop, cursor, claude-code. It uses stdio and sse and http transport.
Is MCTS actively maintained?: MCTS is actively maintained — last commit was 7 days ago. It has 28 GitHub stars.