MCPSafe
Scans Model Context Protocol servers for security vulnerabilities and maintains a verified registry with quality scores.
≈ 6visits/mo
Emerging · estimate, read 2026-09-19
- For
- AI agent developers and teams securing Model Context Protocol servers
- Price
- Freepricing page, read 2026-09-20
- Activity
- Actively maintainednothing dated on the site
- Company
- founding year not on record
- Runs as
- API
- scan MCP server code for vulnerabilities and unsafe patterns
- integrate security scanning into CI/CD pipelines
- #115
CodeRabbit
Automatically reviews pull requests, prioritizes them by risk, and scans for security vulnerabilities.
24.4knot readFrom $24/user/mo2023 - #148
Hexmos
AI code reviewer that flags logic errors, credential leaks and bugs at commit time before reaching production.
26.2kMaintained— - #153
Mindgard
Discovers, red-teams, and protects AI agents and systems against security vulnerabilities and attacks.
1.2kMaintained— - #195
Greptile
Reviews pull requests and tests code changes using agent swarms to catch bugs and style violations across codebases.
8.5knot readFrom $30/user/mo - #206
Fluid Attacks
Scans applications for vulnerabilities using automated analysis and human penetration testing, prioritizes findings by exploitability, and generates remediation guidance.
4.3knot readFree plan - #219
Hacktron AI
Analyzes pull requests to find exploitable vulnerabilities and generates working proofs of concept before code ships.
68not readFrom $40/user/mo
What is MCPSafe?
Scans Model Context Protocol servers for security vulnerabilities and maintains a verified registry with quality scores.
Who is MCPSafe for?
AI agent developers and teams securing Model Context Protocol servers
How much does MCPSafe cost?
MCPSafe is free, per its pricing page on 2026-09-20.
Do people use MCPSafe?
Emerging: ≈ 6 visits a month · estimate, 2026-09.
Is MCPSafe still maintained?
Actively maintained.
What are alternatives to MCPSafe?
In Developer tools, by use: CodeRabbit, Hexmos, Mindgard, Greptile, Fluid Attacks, Hacktron AI.
How we read a tool
No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.
- Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
- Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
- Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
- The line and the use cases are written by us from the homepage, one row at a time, and refused when they repeat the vendor's marketing.
How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.