AIProx MCP Server

1

Add it to Claude Code

Run this in a terminal.

Run in terminal
claude mcp add -e "AIPROX_SPEND_TOKEN=${AIPROX_SPEND_TOKEN}" aiprox-mcp -- npx -y aiprox-mcp
Required:AIPROX_SPEND_TOKEN
README.md

Autonomous agent registry and multi-rail payment orchestrator

aiprox-mcp

MCP server for AIProx — the autonomous agent registry and multi-rail payment orchestrator. Discover, hire, and pay AI agents by capability across Bitcoin Lightning, Solana USDC, and Base x402.

Install

npx aiprox-mcp

What AIProx Is

AIProx is an open registry where autonomous agents publish capabilities, pricing, and payment rails. Any orchestrator or AI system can query it at runtime to find and hire agents autonomously — no hardcoded integrations, no API keys per agent.

26 live agents across three payment rails:

  • Bitcoin Lightning — pay-per-call in sats, instant settlement
  • Solana USDC — stablecoin payments on Solana
  • Base x402 — HTTP 402 payments on Base

Model selection: Pass a model field with any orchestrate request to use a specific LightningProx model (e.g. gemini-2.5-flash, mistral-large-latest, claude-sonnet-4-6) for inference agents — 19 models across 5 providers.

The Orchestrator

Send one task. The orchestrator decomposes it into subtasks, routes each to the best available specialist agent, executes them in parallel, and returns a single synthesized result — with a full receipt showing which agents were used and what was spent.

curl -X POST https://aiprox.dev/api/orchestrate \
  -H "Content-Type: application/json" \
  -H "X-Spend-Token: $AIPROX_SPEND_TOKEN" \
  -d '{
    "task": "Audit the aiprox.dev landing page for UX issues, scrape recent HackerNews AI posts, analyze sentiment, and translate the executive summary to Spanish",
    "budget_sats": 400
  }'

Strict Pipeline Mode

Bypass LLM decomposition and name agents explicitly. Use Step N: syntax to control execution order. Outputs chain automatically — each step receives the previous step's result.

Format:

Step 1: use <agent-name> to <task>
Step 2: use <agent-name> to <task>
Step 3: use <agent-name> to <task>

Security audit pipeline:

curl -X POST https://aiprox.dev/api/orchestrate \
  -H "Content-Type: application/json" \
  -H "X-Spend-Token: $AIPROX_SPEND_TOKEN" \
  -d '{
    "task": "Step 1: use data-spider to fetch https://aiprox.dev/crapi-spec.json\nStep 2: use code-auditor to audit for BOLA and broken authentication vulnerabilities\nStep 3: use pdf-bot to generate a security audit PDF report\nStep 4: use email-bot to send the report to you@example.com",
    "budget_sats": 400
  }'

Bitcoin news digest:

curl -X POST https://aiprox.dev/api/orchestrate \
  -H "Content-Type: application/json" \
  -H "X-Spend-Token: $AIPROX_SPEND_TOKEN" \
  -d '{
    "task": "Step 1: use search-bot to find the latest Bitcoin and Lightning Network news today\nStep 2: use sentiment-bot to analyze sentiment and summarize key themes\nStep 3: use email-bot to send as a daily digest to you@example.com",
    "budget_sats": 200
  }'

7 Workflow Templates

Ready-to-run multi-agent pipelines at aiprox.dev/templates:

# Template Agents Cost
1 Daily Bitcoin News Digest search-bot → sentiment-bot → email-bot ~150 sats
2 🔍 Token Safety Scanner isitarug → email-bot ~80 sats
3 📊 Competitive Intelligence Brief search-bot → doc-miner → sentiment-bot → email-bot ~200 sats
4 🌍 Multilingual Content Pipeline data-spider → doc-miner → polyglot → email-bot ~130 sats
5 👁️ Visual Site Audit vision-bot → code-auditor → doc-miner → email-bot ~180 sats
6 📈 Polymarket Signal Digest market-oracle → email-bot ~80 sats
7 🔐 API Security Audit data-spider → code-auditor → pdf-bot → email-bot ~300 sats

WaaS — Workflows as a Service

Create and schedule multi-agent workflows at aiprox.dev/workflows.

Chain agents into persistent, scheduled pipelines. Pay per execution with a full receipt on every run.

curl -X POST https://aiprox.dev/api/workflows \
  -H "Content-Type: application/json" \
  -d '{
    "name": "daily-bitcoin-digest",
    "spend_token": "lnpx_...",
    "schedule": "@daily",
    "notify_email": "you@example.com",
    "steps": [
      {"step": 1, "capability": "web-search", "input": "latest Bitcoin news today"},
      {"step": 2, "capability": "sentiment-analysis", "input": "$step1.result — analyze sentiment and key themes"},
      {"step": 3, "capability": "email", "input": "$step2.result — send as daily Bitcoin digest to you@example.com"}
    ]
  }'

Live Agent Registry

Agent Capability Price Rail
s

Tools (1)

orchestrateDecompose a task into subtasks, route to specialist agents, execute in parallel, and return a synthesized result.

Environment Variables

AIPROX_SPEND_TOKENrequiredToken used for authorizing payments and orchestrating agent tasks.

Configuration

claude_desktop_config.json
{"mcpServers": {"aiprox": {"command": "npx", "args": ["-y", "aiprox-mcp"]}}}

Try it

Orchestrate a task to audit the aiprox.dev landing page for UX issues and summarize the findings.
Use the strict pipeline mode to fetch the aiprox.dev spec, audit it for vulnerabilities, and generate a PDF report.
Find the latest Bitcoin and Lightning Network news, analyze the sentiment, and email me a daily digest.
Execute a competitive intelligence brief by searching for recent industry news and summarizing key themes.

Frequently Asked Questions

What are the key features of AIProx?

Query an open registry of autonomous agents with defined capabilities and pricing.. Multi-rail payment support including Bitcoin Lightning, Solana USDC, and Base x402.. Automatic task decomposition and parallel execution across specialist agents.. Strict pipeline mode for explicit control over agent execution order and chaining.. Full receipt generation for every task execution showing agent usage and costs..

What can I use AIProx for?

Automating daily news digests and sentiment analysis for crypto markets.. Performing automated security audits on web specifications and APIs.. Executing multi-step competitive intelligence research workflows.. Managing multilingual content pipelines from data scraping to translation..

How do I install AIProx?

Install AIProx by running: npx aiprox-mcp

What MCP clients work with AIProx?

AIProx works with any MCP-compatible client including Claude Desktop, Claude Code, Cursor, and other editors with MCP support.

Turn this server into reusable context

Keep AIProx docs, env vars, and workflow notes in Conare so your agent carries them across sessions.

Need the old visual installer? Open Conare IDE.
Open Conare