| What it does | Security runtime for autonomous AI agents and multi-agent workflows
| Check your AI coding agent's config before it runs
|
|---|
| Stage | MVP
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | Not given
| GE
|
|---|
| Pricing model | Free trial
| Freemium
|
|---|
| Pricing | Starter: $29/mo with 7-day free trial, 250,000 requests/mo, 1,500 mins sandbox compute, 5 custom Wasm rules. Pro: $79/mo, 1,000,000 requests/mo, 5,000 mins sandbox compute, unlimited custom Wasm policies. Enterprise: Custom pricing. Pay-as-you-go overages: $8 per 100k extra requests and $0.005 per m
| Free browser scan available with no account. Paid plans: Individual $9/month (up to 1 developer), Team $49/month (up to 10 developers), Business $129/month (up to 50 developers). Enterprise plans available with custom quote.
|
|---|
| Key features | - L4/L7 Proxy Interceptor for inline A2A and MCP protocol interception
- Sub-millisecond Wasm guardrails and PII redaction under 1.2ms
- Financial circuit breakers and spend locks with multi-node Redlock consensus
- Firecracker MicroVM sandboxing for untrusted code execution
- Human-in-the-Loop asynchronous state hydration for approval workflows
- Slack integration for approval requests and notifications
- Zero agent refactoring with drop-in integration
- Support for LangGraph, CrewAI, AutoGen, and Claude frameworks
- 99.99% uptime SLA for data plane proxy on Pro and Enterprise tiers
| - Scans CLAUDE.md, .mcp.json, .claude/settings.json and related configuration files
- Detects risky permissions and allow rules such as Bash, * or bypassPermissions
- Flags hook commands that use the network, pipe into a shell or decode and run
- Identifies unpinned MCP packages and auto-confirm flags
- Identifies instructions to exfiltrate secrets
- Detects instructions that override or hide agent actions
- Runs in CLI, GitHub Actions, git hooks and browser
- Outputs findings in text, JSON or SARIF 2.1.0 format
- Compares git revisions with diff mode for pull request checks
|
|---|
| What makes it different | - Infrastructure-level security enforcement outside agent context prevents prompt injection bypasses
- Sub-5ms p99 latency overhead with fail-closed guarantees
- Memory-safe Rust implementation with WebAssembly policy execution
- Zero payload retention and data sovereignty with SAML/OIDC support
| - Never executes code - reads files as text only
- Fixed deterministic rules that always give the same results
- Identifies real vulnerabilities like backdoored postmark-mcp and CVE-2025-6514 in mcp-remote
- Free browser scan requires no installation or account
- Works across multiple AI agent tools: Claude Code, Cursor, Codex and Gemini CLI
|
| Community votes | 0 | 0 |
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | Not checked yet ● no change since last check |
| Trust Flow (Majestic) | 0 | 0 |
| Citation Flow (Majestic) | 0 | 0 |
| Referring domains (Majestic) | 0 | 0 |