AGENZA MCP Server
Enables verifiable AI agent identity and reputation management on ICP via MCP, allowing agents to register, create handshake proofs, and verify credentials.
README
🛡️ AGENZA
Verifiable AI Agent Identity & Reputation Protocol on ICP
Self-sovereign, W3C-compliant identity for AI agents. Register once, build reputation across platforms, take it anywhere.
Quick Facts
| Status | ✅ All 7 phases complete. Deployed on mainnet. |
| Version | v1.5.0 |
| Mainnet canister | dli3j-zaaaa-aaaaa-qhjla-cai |
| Agent registration | Free forever |
| Pricing | Year 1 free for everyone. Platform subscriptions Year 2+. |
| Short link | bit.ly/agenza-icp |
For AI Agents
npm install veritas-agent
import { Agent } from 'veritas-agent';
const agent = new Agent();
agent.generateKeys('principal');
const proof = agent.createHandshakeProof();
Or discover via MCP: /mcp/jsonrpc — works with Claude Desktop, Cline, Goose.
For Platforms
npm install veritas-verify
import { verify } from 'veritas-verify';
const result = verify(credentialJson);
V1 HTTP API (No SDK Required)
# Verify an agent's reputation
curl "https://dli3j-zaaaa-aaaaa-qhjla-cai.raw.icp0.io/v1/verify?did=did:agenza:b54wo..."
# Register as a platform (self-service)
curl -X POST "https://dli3j-zaaaa-aaaaa-qhjla-cai.raw.icp0.io/v1/platforms" \
-H "Content-Type: application/json" \
-d '{"name": "TaskMarket", "endpoint": "https://taskmarket.com/api"}'
Quick Start
- Visit bit.ly/agenza-icp
- Choose a role (Agent / Platform / Verifier)
- Follow the curl examples — no SDK, no account required
- Start verifying agent identities
All Phases Complete
| Phase | What | Cost |
|---|---|---|
| 1 | Credential minting + PoP + W3C VCs | ~$15 |
| 2 | veritas-verify + veritas-agent npm | $0 |
| 3 | Credit scoring (6-factor, 0-850) | ~$5 |
| 4 | Rate limiting + mint queue | ~$3 |
| 5 | Reputation sources + admin dashboard | ~$5 |
| 6 | MCP server on-canister | $0 |
| 7 | Docs + demos + subscription management | ~$5 |
| Total | ~$33 (dev + test on playground) |
Key Links
| Resource | URL |
|---|---|
| Mainnet canister | dli3j-zaaaa-aaaaa-qhjla-cai |
| Short link | bit.ly/agenza-icp |
| Admin dashboard | GET /admin |
| MCP endpoint | GET /mcp/jsonrpc |
| Architecture | ARCHITECTURE.md |
| Full spec | AGENZA-SPEC.md |
| V1 HTTP API | docs/guides/HTTP-API.md |
| Integration guide | docs/guides/INTEGRATION.md |
| npm | veritas-verify · veritas-agent |
| GitHub | kodydpa-hub/veritas |
License
MIT — both npm packages and all canister code are open source.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.