Redthread
AI app security platform: attack paths, scan findings, shadow AI and MCP server vetting
- Pricing
- Freemium
- Platforms
- Web, API, CLI
- Runs
- Remotely
- Version
- 0.7.469
- Listing updated
- today
About Redthread
Redthread is a freemium MCP server for security. It runs as a hosted remote server, so there is nothing to install locally.
Redthread is an AI-native application protection platform that builds one graph of agents, applications, code, cloud accounts, identities and the data they can reach, then ranks risk by whether a path can actually be reached. The MCP server surfaces attack paths, scan findings and shadow AI from that platform, and can vet MCP servers.
Its docs describe modules a workspace switches on: a free agentless AI risk assessment mapped to the OWASP Top 10 for LLM and agentic apps, exploit validation by autonomous agents against chatbots and RAG endpoints with a reproducible proof for each finding, shadow-AI discovery, cloud posture, CI/CD gating, reports for frameworks such as SOC 2 and ISO 27001, and agent identities with signed trust events.
The docs also report a daily scan of 53,270 MCP registry servers with signed claims, listing-swap and rug-pull checks on tool definitions, and hooks for Claude Code and Cursor that check each MCP call before it runs. The estate scan and one black-box pentest are free; paid modules are quoted to the size of the estate.
Install
Run in a terminal
claude mcp add --transport http redthread https://app.redthreadsec.com/mcpAdd to Settings → Connectors → Add custom connector
https://app.redthreadsec.com/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"redthread": {
"url": "https://app.redthreadsec.com/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"redthread": {
"type": "http",
"url": "https://app.redthreadsec.com/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"redthread": {
"serverUrl": "https://app.redthreadsec.com/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"redthread": {
"type": "http",
"url": "https://app.redthreadsec.com/mcp"
}
}
}What it does
- AI risk assessment
- Maps every AI in use and ranks toxic combinations.
- Exploit validation
- Autonomous agents test AI apps and give reproducible proofs.
- Shadow AI discovery
- Inventories AI features nobody registered.
- MCP server vetting
- Checks servers with signed claims and tool-definition fingerprints.
- CI/CD gating
- Blocks merges that would add a proven attack path.
- Compliance reports
- Evidence packs for SOC 2, ISO 27001, EU AI Act and others.
Good for
- Find the AI agents and models running across an estate
- Prove whether a chatbot or RAG endpoint is exploitable
- Vet an MCP server before connecting it
- Gate pull requests on proven attack paths
Pricing
Freemium
Free estate assessment; paid modules quoted to your estate
Prices change. Check redthreadsec.com before you buy.
Redthread FAQ
Is there a free tier?
The estate assessment is free, with one black-box website scan and one compliance report; other modules are paid and quoted.
Does it need agents installed?
Its core is agentless; an optional detect-only endpoint sensor exists.
Are reports certifications?
No, the docs say the views support an audit but are never a certification.
Which frameworks are mapped?
OWASP LLM Top 10, MITRE ATLAS and reports for SOC 2, ISO 27001, ISO 42001, PCI DSS, GDPR, HIPAA, NIST and the EU AI Act.
Is Redthread free?
Redthread has a free plan, with paid plans for more usage or features.
How do I add Redthread to Claude Code?
Run this command in your terminal: claude mcp add --transport http redthread https://app.redthreadsec.com/mcp
What are the best alternatives to Redthread?
The closest alternatives to Redthread are REA, Agent Roast, Midplane, Leash and Tinplate Edge AI Safety, Security & EU Compliance.
Alternatives to Redthread

REA
MCP serverCLI and MCP server that lets coding agents reverse engineer apps and binaries
Runs locally- Open source
- 464K GitHub stars
- Developer tools
Agent Roast
MCP serverOffline review that flags agent changes which weaken tests, assertions or CI
Runs locally- Open source
- 4 Hacker News points
- Developer tools

Midplane
MCP serverPostgres gateway for AI agents with table grants, column masking and approval for writes
Runs locally- Open source
- 5 GitHub stars
- Databases

Leash
MCP serverReview what your AI touched, approve risky actions and undo supported changes
- 1 tool
- Remote
- Free
- 1 GitHub star
- Security
Zero-log MCP server with 49 tools for AI guardrails, secret scanning and EU compliance
- 49 tools
- Remote
- Freemium
- Security

SecureCloud
MCP serverSentinelOne and IT security catalog, prices, quotes and checkout links for Israel
- 7 tools
- Remote
- Free
- Security