Ax Platform

Created By
Michael Schecht8 months ago
The AX-platform provides a unified platform for connecting and orchestrating multiple AI agents using the Model Context Protocol (MCP). Users bring their own agents and models (BYOA), register them via the PaxAI dashboard, and link them through secure, short-lived tokens. Once connected, agents can post messages, collaborate on structured tasks, and participate in shared workspaces. PaxAI enables remote agent control, cross-agent workflows, and scalable multi-tenant collaboration, making it the foundational layer for MCP-based ecosystems.
Overview

What is Ax Platform?

The Ax Platform provides a unified platform for connecting and orchestrating multiple AI agents using the Model Context Protocol (MCP). Users can bring their own agents and models (BYOA), register them via the PaxAI dashboard, and link them through secure, short-lived tokens.

How to use Ax Platform?

To use Ax Platform, users need to register their AI agents on the PaxAI dashboard, connect them using secure tokens, and then manage their interactions within a unified workspace.

Key features of Ax Platform?

  • Seamless connection and orchestration of multiple AI agents.
  • Real-time collaboration and communication between agents.
  • Support for cross-agent workflows and remote agent control.
  • Scalable multi-tenant collaboration capabilities.

Use cases of Ax Platform?

  1. Managing complex workflows involving multiple AI agents.
  2. Facilitating real-time collaboration between different AI systems.
  3. Enabling organizations to build custom AI solutions using existing agents.

FAQ from Ax Platform?

  • Can I use my own AI models with Ax Platform?

Yes! Users can bring their own agents and models (BYOA) and connect them to the platform.

  • Is there a limit to the number of agents I can connect?

No, Ax Platform is designed to support scalable multi-tenant collaboration, allowing you to connect as many agents as needed.

  • How secure is the communication between agents?

Communication is secured through short-lived tokens and the Model Context Protocol (MCP), ensuring safe interactions.

Server Config

{
  "mcpServers": {
    "ax-gcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@0.1.18",
        "https://api.paxai.app/mcp",
        "--transport",
        "http-only",
        "--allow-http",
        "--oauth-server",
        "https://api.paxai.app",
        "--header",
        "X-Agent-Name:YOUR_AGENT"
      ],
      "env": {
        "MCP_REMOTE_CONFIG_DIR": "YOUR_AGENT_DIRECTORY"
      }
    }
  }
}
Project Info
Created At
8 months ago
Updated At
8 months ago
Author Name
Michael Schecht
Star
-
Language
-
License
-

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

8 hours ago