MCP Security Index
Before you install an MCP server, see what it can do. AxioRank enumerates the tools each server declares (read-only, it never calls one) and grades the blast radius of what it can do: write, delete, execute, credential, and wildcard-scope capabilities. Scan a server not listed here.
Scan a server that is not listed
Scans a remote MCP server or agent card by URL. For a local stdio server, run npx @axiorank/mcpaudit.
30 servers in Cloud
- –Azure MCP Server MicrosoftCloud · scan pending
- –Terraform HashiCorpCloud · scan pending
- –AWS Core (AWS Labs) AWS (awslabs)Cloud · scan pending
- –Cloudflare Documentation CloudflareCloud · scan pending
- –Vercel VercelCloud · scan pending
- –Cloudflare Workers Bindings CloudflareCloud · scan pending
- –Cloudflare Observability CloudflareCloud · scan pending
- –AWS Cost Explorer AWS LabsCloud · scan pending
- –Cloudflare API CloudflareCloud · scan pending
- –Heroku Heroku (Salesforce)Cloud · scan pending
- –Amazon CloudWatch AWS LabsCloud · scan pending
- –AWS Pricing AWS LabsCloud · scan pending
- –Netlify NetlifyCloud · scan pending
- –AWS IAM AWS LabsCloud · scan pending
- –AWS Lambda Tool AWS LabsCloud · scan pending
- –DigitalOcean DigitalOceanCloud · scan pending
- –Amazon EKS AWS LabsCloud · scan pending
- –Pulumi PulumiCloud · scan pending
- –Amazon ECS AWS LabsCloud · scan pending
- –Railway RailwayCloud · scan pending
- –AWS Serverless AWS LabsCloud · scan pending
- –Render RenderCloud · scan pending
- –Upstash UpstashCloud · scan pending
- –BorealHost alainsvrdCloud · scan pending
- –CalendarMCP Full-VibeCloud · scan pending
- –dataecho mohocpCloud · scan pending
- –Arcane RMCP jmagarCloud · scan pending
- –Cortex RMCP jmagarCloud · scan pending
- –Synapse RMCP jmagarCloud · scan pending
- –Unraid RMCP jmagarCloud · scan pending
How the grades work
A grade measures blast radius: how much a server could do if it were compromised or misinstructed, based on the capabilities it declares (write, delete, execute, credential access, wildcard scope). It is not a vulnerability assessment and not a judgment of the vendor. Lower is better: A is 0 to 19, up to F at 80 and above. The scan is read-only. It lists tools and never calls one.
Run a server? You can scan it yourself and embed your grade. See something off? Every server page links a re-scan.
Govern the MCP servers your agents use
AxioRank is the security gateway for AI agents: allowlist servers, block risky tool calls, and get an audit trail of every action.
Start free