原型 · 预览版:收录官方注册中心里的全部服务器,每 30 分钟同步一次。评价和账户功能将在后续阶段推出。
PopNx MCP为使用 AI 的人准备的 MCP 服务器 · 用大白话讲清楚

AgentServices

作者:vbkotecha版本 6.0.0i★ –i在云端运行
注册名称to.agentservices/agentservices

安装

概览

作者提供的说明(英文原文)

52 paid x402 API endpoints for AI agents — crypto, data, DeFi, market intelligence.

PopNx MCP 的三大支柱

这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。

它能帮你做什么

我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。

  • 连接方式: 在云端运行
  • 传输方式: Streamable HTTP
  • 分类: 加密货币与区块链

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

你需要

你用的是哪个应用?

在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。

适用于网页版、桌面版和手机版 Claude:

  1. 打开 Settings → Connectors
  2. 点击 Add custom connector
  3. 粘贴下面的地址,然后点击 Add
  4. 如果要求登录,请登录作者的服务
SettingsConnectors1+ Add2https://…3
https://agentservices.to/mcp

在终端中运行这条命令

claude mcp add --transport http agentservices https://agentservices.to/mcp

在 Cursor 中打开

或者自己复制设置

粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json

{
  "mcpServers": {
    "agentservices": {
      "url": "https://agentservices.to/mcp"
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

在 VS Code 中打开

或者自己复制设置

粘贴到项目中的 .vscode/mcp.json

{
  "servers": {
    "agentservices": {
      "type": "http",
      "url": "https://agentservices.to/mcp"
    }
  }
}

浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。

ChatGPT 只能连接互联网上的服务器:

  1. 打开网页版 ChatGPT → Settings → Connectors (Apps)
  2. 点击 Create 或 Add(部分套餐需要先在 Advanced 中开启 Developer mode)
  3. 粘贴下面的地址,起个名字,然后保存
  4. 如果要求登录,请登录作者的服务
SettingsConnectors1+ Create2https://…3
https://agentservices.to/mcp

菜单名称可能因套餐和版本不同而略有差异。

你的选择通过 Cookie 保存在这台设备上,无需账户。

这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。

它能做什么

我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。

基础检查i

我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过域名 agentservices.to 验证(注册中心会核实域名所有权)

  • … 尚未检查

    仍在维护

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    有许可证

    我们还没有从 GitHub 读取这个仓库

  • … 尚未检查

    端点有响应

    尚未检查;我们会轮流检查各个端点

  • … 尚未检查

    使用 OAuth 登录

    尚未检查;我们会轮流检查各个端点

  • … 尚未检查

    工具描述中没有隐藏指令

    尚未检查;我们会在检查端点时读取工具列表

与“加密货币与区块链”中的其他服务器比较i

  • 星标数多于此分类中其他 1614 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 1614 个服务器的 42% 更新
  • 基础检查结果等于或优于此分类中其他 1614 个服务器的 100%

与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。

常见问题

AgentServices 安全吗?

它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。

它需要哪些密钥或代码?

注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。

它在我的电脑上运行还是在云端?

它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(6.0.0)于2个月前进入注册中心。

哪些应用可以使用它?

支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。

有什么可以替代它?

同一分类中有:gasrescue, xsolana, CashPan

替代选择

同一分类中其他作者的服务器,按星标数排序。

如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i

gasrescue

作者:gasrescue

Rescue USDC, USDT and USDG from wallets with no gas: send or swap them on EVM, Solana and Tron.

在你的电脑上运行今天更新
安装

xsolana

作者:XGamesFun

Design, check, simulate and launch Solana game economies on loot, one shared program, no contract.

在你的电脑上运行今天更新
安装

CashPan

作者:cashpan.app

Give your AI an allowance: pay approved people within on-chain spending limits.

在云端运行今天更新
安装

作者的 README

打开 README

按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。

AgentServices

The paid API layer for AI agents — data, intelligence, inference, and media via x402 micropayments

Canonical project: https://github.com/vbkotecha/agentservices-api

Official site: https://agentservices.to

License: Apache-2.0

AgentServices is an independent project. It is not affiliated with, endorsed by, or a replacement for any other x402 market-data provider.

Live at: agentservices.to | MCP Server: https://agentservices.to/mcp (Streamable HTTP) | Discovery: /.well-known/x402

What is this?

AgentServices is the monetized API layer for AI agents. No API keys, no subscriptions — agents pay per-request with USDC on Base using the x402 payment protocol.

60+ endpoints across crypto data, market intelligence, DeFi analytics, on-chain analytics, 400+ LLM models, image generation, text-to-speech, portfolio intelligence, and dispute resolution. 12 are free. 48+ are paid via x402 (from $0.002 to $0.25 per call).

What's new in v6.0
  • 400+ LLM models via OpenAI-compatible /v1/chat/completions — GPT, Claude, Gemini, DeepSeek, Grok, Llama, and more
  • Smart router — use model: "auto" and the gateway classifies your task and picks the cheapest model that handles it
  • Image generation — /v1/images/generations via gpt-image-2 ($0.05)
  • Text-to-speech — /v1/audio/speech with natural voices ($0.05)
  • 3 new MCP tools — chat, generate_image, text_to_speech

Buyer path: discover → try → pay → retain

Use the buyer quickstart for the complete path. The exact next action is to run the no-credential discovery check:

python3 examples/mcp_discovery_buyer_proof.py

Then follow the same buyer journey:

  1. Discover: confirm the hosted MCP server and free tool catalog with the MCP discovery proof.
  2. Try free: retrieve a real price result with the free SDK proof.
  3. Inspect the paid challenge: decode the live 402 terms with the paid SDK proof. It never signs or settles payment.
  4. Buy an outcome: pay the returned x402 terms, retry the same request, and retain the returned paid result. See the token-risk, market-pulse, and research-brief contracts for result limits and provenance.
  5. Retain evidence: run the existing receipt builder with the original challenge, paid response, and your wallet authorization or transaction reference.

The four proofs have different limits: discovery and free SDK verify no-spend access; the paid SDK proof verifies challenge shape only; the receipt builder hashes buyer-held evidence and does not verify settlement. None of them claims adoption, settlement, or revenue.

For activation measurement definitions, see Activation Metrics. To probe the live funnel, run python3 examples/check_activation_funnel.py.

Buyer path: discover → try → pay → retain

Use the buyer quickstart for the complete path. The exact next action is to run the no-credential discovery check:

python3 examples/mcp_discovery_buyer_proof.py

Then follow the same buyer journey:

  1. Discover: confirm the hosted MCP server and free tool catalog with the MCP discovery proof.
  2. Try free: retrieve a real price result with the free SDK proof.
  3. Inspect the paid challenge: decode the live 402 terms with the paid SDK proof. It never signs or settles payment.
  4. Buy an outcome: pay the returned x402 terms, retry the same request, and retain the returned paid result. See the token-risk, market-pulse, and research-brief contracts for result limits and provenance.
  5. Retain evidence: run the existing receipt builder with the original challenge, paid response, and your wallet authorization or transaction reference.

The four proofs have different limits: discovery and free SDK verify no-spend access; the paid SDK proof verifies challenge shape only; the receipt builder hashes buyer-held evidence and does not verify settlement. None of them claims adoption, settlement, or revenue.

Endpoints

Free (no payment required)
EndpointDescription
GET /v1/prices?symbols=BTC,ETHCurrent crypto prices (CoinGecko)
GET /v1/trendingTrending tokens by market activity
GET /v1/globalGlobal market cap, volume, BTC dominance
GET /v1/fear-greedCrypto Fear & Greed sentiment index
GET /v1/gasCurrent gas prices on Base/Ethereum
GET /v1/predictionsAI-generated market predictions
GET /v1/newsLatest crypto news headlines
GET /v1/social/trendingTrending social sentiment topics
GET /v1/geo?ip=1.2.3.4IP geolocation lookup
GET /v1/swap/quote?from=&to=&amount=DEX swap quote (0x integration)
GET /v1/policiesList dispute resolution policy templates
GET /v1/trade/hyperliquid/bootstrapHyperliquid agent-sign bootstrap (approveAgent flow)
POST /v1/trade/hyperliquid/orderForward agent-signed HL order (policy-gated)
POST /v1/trade/hyperliquid/cancelForward agent-signed HL cancel
GET /v1/trade/hyperliquid/orderHL order status (query: user, oid)
GET /v1/trade/hyperliquid/order/{id}HL order status (path param)
GET/PUT /v1/trade/hyperliquid/policyExecution leash (max notional, coin allowlist, kill switch)
POST /v1/trade/hyperliquid/paper/orderPaper/sim order for agent training
POST /v1/trade/hyperliquid/eval/orderPolicy pass/fail eval (training gym)
GET /healthAPI health check
Trade API — venue doors (FREE — not x402)

AgentServices is building venue trade doors under /v1/trade/{venue}/…. Hyperliquid ships first; more venues and a venue-neutral /v1/trade/execute router follow.

Each door is a policy leash + forward — not a smarter router. We do not claim better fills than the venue direct. Execution is free at the call (no x402 on the order path). Builder fees are omitted so routing through us is not more expensive than going direct.

We never collect venue API keys. Agents sign orders locally with an HL-approved agent wallet (approveAgent on the main wallet is the one human bootstrap step). AgentServices policy-checks (max notional, coin allowlist, kill switch) and forwards the signed payload.

Request bodies accept market_type: spot, perp, or future. Hyperliquid implements perp and spot today; unsupported types return a machine-readable market_type_not_supported error.

MCP toolHTTP equivalent
trade_hyperliquid_orderPOST /v1/trade/hyperliquid/order
trade_hyperliquid_cancelPOST /v1/trade/hyperliquid/cancel
trade_hyperliquid_order_statusGET /v1/trade/hyperliquid/order
trade_hyperliquid_get_policy / trade_hyperliquid_set_policyGET/PUT /v1/trade/hyperliquid/policy
trade_hyperliquid_paper_orderPOST /v1/trade/hyperliquid/paper/order
trade_hyperliquid_eval_orderPOST /v1/trade/hyperliquid/eval/order

Legacy hl_* MCP tool names remain as aliases. See GET /v1/trade/hyperliquid/bootstrap for the approveAgent signing model.

Roadmap: /v1/trade/{venue} for additional venues; /v1/trade/execute for venue-neutral routing later.

Paid — Data APIs (x402)
EndpointPriceDescription
GET /v1/indicators/BTC$0.02Technical indicators (RSI, MACD, Bollinger Bands, ATR, Support/Resistance)
GET /v1/yields$0.02Top DeFi yield pools by TVL
GET /v1/metadata?url=$0.01URL metadata extraction and unfurling
GET /v1/search?q=$0.01Web search for crypto/market information
GET /v1/onchain/:address$0.02On-chain analytics for any address
GET /v1/onchain/:address/tokens$0.03Token holdings for any address
Paid — Synthesis APIs (x402)
EndpointPriceDescription
GET /v1/token-risk/{token}$0.03Snapshot-based volatility, liquidity-proxy, and market-cap risk score
GET /v1/crypto-signals$0.04Aggregated buy/sell signals across multiple indicators
GET /v1/yield-comparison$0.03Compare yields across protocols with risk-adjusted returns
GET /v1/hn-sentiment$0.02Hacker News sentiment analysis for tech topics
GET /v1/npm-stats/:package$0.02NPM package download stats and trends
GET /v1/github-trending$0.02Trending GitHub repos by language/topic
GET /v1/marketing-intel$0.05Marketing intelligence: competitors, content gaps, ad copy
Paid — Bundled Intelligence (x402)
EndpointPriceDescription
GET /v1/research?q=$0.05Deep research: search + extract + synthesize in one call
GET /v1/portfolio?symbol=BTC$0.10Portfolio intelligence: price + signal + risk + sentiment + verdict
GET /v1/defi-strategy$0.25DeFi strategy report: top yields + TVL + comparison + risk flags
GET /v1/market-pulse$0.05Market pulse: fear-greed + trending + news + social + whales + global
GET /v1/onchain-overview$0.15On-chain overview: whales + exchange flows + stablecoin flows + correlation + DeFi TVL
Paid — AI Inference (x402)
EndpointPriceDescription
POST /v1/inference$0.03LLM inference (gpt-5.4/5.4-mini/5.5) — chat completions
POST /v1/complete$0.03Text completion (CodexSale proxy)
Paid — Dispute Resolution (x402)
EndpointPriceDescription
POST /v1/disputes$0.05AI-powered dispute resolution (7 policy templates)

Use Cases — What Agents Can Build

Portfolio Monitor
# ALL-IN-ONE: Get portfolio intelligence in a single call ($0.10)

Returns: price + technical signal + risk score + market sentiment + verdict

curl "https://agentservices.to/v1/portfolio?symbol=BTC"

Or build it yourself from individual endpoints:

Get current prices (FREE)

curl https://agentservices.to/v1/prices?symbols=BTC,ETH,SOL

Get technical signals for entry/exit ($0.04)

curl https://agentservices.to/v1/crypto-signals

Check snapshot-based token risk before buying ($0.03)

Use a CoinGecko-compatible identifier for portable direct HTTP calls.

curl https://api.agentservices.to/v1/token-risk/pepe

Contract and payment-receipt guidance: docs/token-risk-outcome-contract.md

DeFi Yield Optimizer
# ALL-IN-ONE: Get DeFi strategy report ($0.25)

Returns: top yields + protocol TVL + cross-chain comparison + risk flags

curl "https://agentservices.to/v1/defi-strategy"

Get all yield pools ranked by TVL ($0.02)

curl https://agentservices.to/v1/yields

Compare yields with risk-adjusted returns ($0.03)

curl https://agentservi

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx