Skip to content

CapiscIO

The Authority Layer for AI Agents

Like Let's Encrypt revolutionized HTTPS, CapiscIO brings verifiable identity and trust to the agent economy. Cryptographic proof of who your agent is—and who it can trust.

Get Started How It Works

What Do You Want to Do?

  • Validate My Agent Card

    Check if your A2A agent card is compliant and production-ready.

    Start Validating

  • Secure Agent Communication

    Add authentication, signing, and trust enforcement to your agent.

    Add Security

  • Protect MCP Tools

    Add trust-level authorization to your Model Context Protocol servers.

    MCP Guard

  • Add to CI/CD Pipeline

    Automate validation with GitHub Actions, GitLab CI, or Jenkins.

    CI/CD Setup

The CapiscIO Stack

Three products that work together to secure the agent economy:

  • CapiscIO Core

    CLI & validation engine — Validate agent cards, generate keys, issue badges.

    pip install capiscio  # or npm install -g capiscio
capiscio validate agent-card.json

    CLI Reference

  • CapiscIO SDK

    Runtime security — Sign requests, verify badges, enforce trust in your code.

    from capiscio_sdk import SimpleGuard
guard = SimpleGuard(dev_mode=True)

    Python SDK

  • MCP Guard

    Tool authorization — Protect MCP tools with trust-level requirements.

    @guard(min_trust_level=2)
async def read_database(query: str):
    pass

    MCP Guard

See how these fit together

Developers Love CapiscIO

Every feature works in three commands or less.

capiscio validate agent-card.json
# ✅ Validation passed: 95/100 (A+)

from capiscio_sdk import sign_request
signed = sign_request(request, badge)

@guard.protect(min_trust_level=2)
async def handle_task(request):
    pass  # Only trusted agents reach here

@guard(min_trust_level=3)
async def write_file(path: str, content: str):
    pass  # Enterprise agents only