Quick Start
Add RecourseOS to your agent's MCP config:
{
"mcpServers": {
"recourseos": {
"command": "npx",
"args": ["-y", "recourse-cli@latest", "mcp", "serve"]
}
}
}Then tell the agent to check before destructive commands:
Use RecourseOS to check before running: rm -rf /tmp/testAgent Setup Guides
Shell Wrapper
Wrap dangerous shell commands so they automatically check RecourseOS before executing. Add to your shell profile:
eval "$(recourse wrap)"Or with npx:
eval "$(npx -y recourse-cli@latest wrap)"Available Tools
| Tool | Purpose |
|---|---|
recourse_evaluate_terraform | Evaluate Terraform plan JSON before apply |
recourse_evaluate_shell | Evaluate a shell command before execution |
recourse_evaluate_mcp_call | Evaluate another MCP tool call before invoking it |
recourse_evaluate_with_evidence | Re-evaluate with verification evidence |
recourse_supported_resources | List deterministic resource handler coverage |
Attestation
Every evaluation response includes a cryptographic attestation (Ed25519 signature). Always enabled.
Verify attestations:
recourse verify attestation.json— CLI verificationGET /.well-known/recourse-keys.json— public key registryGET /.well-known/attestations/{id}.json— individual attestations
Agent Behavior
Agents should treat RecourseOS as a pre-action consequence check:
- allowSafe to proceed
- warnProceed with caution, inform user
- escalateStop and ask user for explicit approval
- blockDo not proceed without human review