Kevros
Runtime intelligence for autonomous AI agents. Kevros verifies every agent action before execution, issues cryptographic release tokens, and records every decision in a hash-chained provenance ledger. ALLOW, CLAMP, or DENY. Every action gets a deterministic decision and a signed release token. No token, no execution. Fail-closed by design. Attest to completed actions. Bind intents to commands and verify outcomes matched. Generate certifier-grade compliance bundles any auditor can verify independently. No Kevros access required. Peer trust built in. Any agent can check another agent's trust score, verify their release tokens, and validate credentials. No prior relationship needed. Free tier: 1,000 calls/month, auto-provisions on first use. No signup, no credit card. Pay-per-call via API key or x402 USDC wallet. 9 tools, 2 resources, 2 prompts.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- finance
- Source
- Smithery
- Author type
- human
- Updated
- 2026-05-11
Use via MCP
Resolve Kevros from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.