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

Sato Kit

作者:satohubai版本 0.1.0i★ –i在你的电脑上运行
注册名称ai.satohub/kit

安装

概览

作者提供的说明(英文原文)

Prepare -> execute for onchain agent actions: policy pre-flight, simulation, receipt log.

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: 在你的电脑上运行
  • 传输方式: stdio
  • 分类: 其他

安装

选择你使用的 AI 应用,然后复制设置。

安装之前

  • 基础检查:1 项中通过 1 项
  • 在你的电脑上运行,拥有你的用户账户的权限(文件、网络、应用)。
  • 注册中心没有列出需要填写的密钥。

你需要

  • npm已安装 Node.js(用于 npx 命令)

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 …”。

打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json

{
  "mcpServers": {
    "kit": {
      "command": "npx",
      "args": [
        "-y",
        "@satohub/kit",
        "mcp"
      ]
    }
  }
}

在终端中运行这条命令

claude mcp add kit -- npx -y @satohub/kit 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": {
    "kit": {
      "command": "npx",
      "args": [
        "-y",
        "@satohub/kit",
        "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": {
    "kit": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@satohub/kit",
        "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。

这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。

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

它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。

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7日

  • ✓ 通过

    作者与仓库一致

    注册名称已通过域名 satohub.ai 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

  • – 不适用

    端点有响应

    它在你的电脑上运行,没有互联网端点

  • – 不适用

    使用 OAuth 登录

    在你的电脑上运行,改用本地设置

  • … 尚未检查

    工具描述中没有隐藏指令

    它在你的电脑上运行;我们只能读取互联网端点的工具列表

与“其他”中的其他服务器比较i

  • 星标数多于此分类中其他 32545 个服务器的 0%
  • 发布到注册中心的时间比此分类中其他 32545 个服务器的 51% 更新
  • 基础检查结果等于或优于此分类中其他 32545 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

Sato Kit 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?

它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。

它还在维护吗?

GitHub 仓库最后更新于–,最新版本(0.1.0)于38天前进入注册中心。

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。你的电脑上还需要有 Node.js。

有什么可以替代它?

同一分类中有:Spec Driven Development, Remote Desktop Commander, Python MCP

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

Spec Driven Development

作者:formulahendry

MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.

在你的电脑上运行★ 440MIT14个月前更新
安装

Remote Desktop Commander

作者:desktop-commander

Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.

在云端运行★ 211昨天更新
安装

Python MCP

作者:Files-com

Local-only Python MCP server for the Files.com API.

在你的电脑上运行今天更新
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。

@satohub/kit

0.1.1 preview.

Sato Kit wraps the tools agents already use (viem, signers, x402) with a prepare -> execute contract: an action prepares an unsigned intent, a policy pre-flight explains any refusal, the transaction is simulated, and execute({ intent_id }) hands it to your signer and appends a hash-chained sato.receipt/v1 line.

What it is not: not a wallet, not a custodian, not an agent framework, and not a guarantee. It never holds funds and ships no keys.

  • Fork by default. A policy's network defaults to fork; mainnet needs an explicit opt-in.
  • Pre-flight vs enforcement. The kit's policy check runs before an intent is returned and says which rule refused and why. It does not enforce anything once a key is in play. Enforcement lives in the signer (e.g. a CDP policy compiled from the same file).
  • `scan.payto_changed`. The scan block of policy.json records payto_changed (caution | refuse | off), but it is enforced only by hosts that implement it. The offline guard in satohub-core (scanRecipient) does not enforce it today: a changed x402 payTo needs the payee's earlier value, which the offline check is not given.
  • Swaps are venue-neutral. Any venue is accepted. Sato Swap is the labelled default and its fee is disclosed on every response, with a no-Sato-fee quote alongside; venue: "direct" skips Sato entirely.

Contracts (sato.action/v1, sato.policy/v1, sato.receipt/v1) live in src/spec (see VENDORED.md).

Install

npm install @satohub/kit viem

npx -y @satohub/kit@0.1 --help

Node 20 or later. viem is a peer; every framework SDK below is an optional peer, installed only if you use its subpath.

Honest limits

  • Pre-flight, not enforcement. evaluatePreflight runs before an intent is returned and names each refused rule with its limit and the observed value. Once a key is in play the kit enforces nothing: enforcement is the signer's (a CDP, Privy or Turnkey policy compiled from the same policy.json, OWS's policy engine, or a Safe's owners). viemLocalSigner enforces only its mainnet refusal.
  • x402 execution scope. x402.prepare reads what an x402 resource asks to be paid and returns a priced, policy-checked intent. execute does not send x402 payments: it sends EVM transactions, EIP-712 typed data (Safe proposals) and Solana transactions only. Pay through your x402 client.
  • AgentKit's own analytics call. AgentKit's @CreateAction decorator posts an invocation event to cca-lite.coinbase.com on every invoke. Actions consumed through fromAgentKitProvider still make that call; the kit neither blocks nor adds to it.
  • Unknown prices refuse. When a USD value cannot be read, a max_usd_* rule refuses with unknown_price rather than guessing.
  • Simulation is not a promise. A passing simulation says what the chain answered at that block.

Action reference

Generated from the registered descriptors by node scripts/gen-actions-doc.mjs (after npm run build); test/readme-actions.test.ts fails when this table drifts from the registry. "custody" is the descriptor's own answer to three sato.custody/v1 questions. toolset says whether the tool is in the default MCP profile or only under --toolsets all.

Registered actions
action idtool namekindeffectscustodychainstoolset
chain.readchain_readreadreadreads key: no; key leaves: no; moves funds: neverethereum, sepolia, base, base-sepolia, arbitrum, arbitrum-sepolia, optimism, optimism-sepolia, polygondefault, all
swap.quoteswap_quotereadquotereads key: no; key leaves: no; moves funds: neverethereum, base, arbitrum, optimism, polygondefault, all
swap.prepareswap_preparepreparequote, sign, broadcastreads key: no; key leaves: no; moves funds: with_approvalethereum, base, arbitrum, optimism, polygondefault, all
x402.preparex402_preparepreparesign, payreads key: no; key leaves: no; moves funds: with_approvalbase, base-sepolia, ethereum, sepolia, polygon, arbitrum, optimism, solana, solana-devnetdefault, all
erc8004.lookuperc8004_lookupreadreadreads key: no; key leaves: no; moves funds: neverethereum, base, arbitrum, optimism, polygonall
tx.simulatetx_simulatereadsimulatereads key: no; key leaves: no; moves funds: neverethereum, sepolia, base, base-sepolia, arbitrum, arbitrum-sepolia, optimism, optimism-sepolia, polygonall
token.approvals.listtoken_approvals_listreadreadreads key: no; key leaves: no; moves funds: neverethereum, sepolia, base, base-sepolia, arbitrum, arbitrum-sepolia, optimism, optimism-sepolia, polygonall
token.approvals.revoketoken_approvals_revokepreparesign, broadcastreads key: no; key leaves: no; moves funds: with_approvalethereum, sepolia, base, base-sepolia, arbitrum, arbitrum-sepolia, optimism, optimism-sepolia, polygonall
erc8004.registererc8004_registerpreparesign, broadcastreads key: no; key leaves: no; moves funds: with_approvalethereum, base, arbitrum, optimism, polygonall
bridge.quotebridge_quotereadquotereads key: no; key leaves: no; moves funds: neverethereum, base, arbitrum, optimism, polygonall
bridge.preparebridge_preparepreparequote, sign, broadcastreads key: no; key leaves: no; moves funds: with_approvalethereum, base, arbitrum, optimism, polygonall
safe.infosafe_inforeadreadreads key: no; key leaves: no; moves funds: neverethereum, sepolia, base, base-sepolia, arbitrum, optimism, polygonall
safe.proposesafe_proposepreparesignreads key: no; key leaves: no; moves funds: with_approvalethereum, sepolia, base, base-sepolia, arbitrum, optimism, polygonall
solana.readsolana_readreadreadreads key: no; key leaves: no; moves funds: neversolana, solana-devnetall
solana.transfersolana_transferpreparesign, broadcastreads key: no; key leaves: no; moves funds: with_approvalsolana, solana-devnetall
solana.swap.quotesolana_swap_quotereadquotereads key: no; key leaves: no; moves funds: neversolanaall
solana.swap.preparesolana_swap_preparepreparequote, sign, broadcastreads key: no; key leaves: no; moves funds: with_approvalsolanaall
Meta tools
tool namekindeffectstoolset
executeexecutesign, broadcastdefault, all
statusmetareaddefault, all
actions_searchmetareaddefault, all
actions_describemetareaddefault, all

Default MCP profile, in order: chain_read, swap_quote, swap_prepare, x402_prepare, execute, status, actions_search, actions_describe.

Actions consumed from an AgentKit provider (fromAgentKitProvider) are not in this table: they are built at runtime from the provider you pass, and appear under toolset all.

Entry points

importwhat it gives you
@satohub/kitcreateKit, coreActions, the tool surface, config loader, everything below re-exported
@satohub/kit/specthe vendored contracts: sato.action/v1, sato.policy/v1, sato.receipt/v1, id rules, descriptor lint
@satohub/kit/policyevaluatePreflight; compilers compileCdpPolicy, compilePrivyPolicy, compileTurnkeyPolicy
@satohub/kit/signersviemLocalSigner, owsSigner, cdpSigner, solanaLocalSigner, humanApprove
@satohub/kit/intentintent store, HMAC intent ids (loadOrCreateIntentSecret, verifyIntentId)
@satohub/kit/receiptsthe hash-chained sato.receipt/v1 log
@satohub/kit/actionsevery core action, descriptor and builder
@satohub/kit/ai-sdksatoKitTools(kit, opts) for the Vercel AI SDK
@satohub/kit/agentkitsatoKitActionProvider(kit, opts) and fromAgentKitProvider(provider, { chain })
@satohub/kit/claude-agent-sdkcreateSatoKitSdkServer(kit, opts) + requireApprovalHook()
@satohub/kit/openai-agentssatoKitOpenAITools(kit, opts)
@satohub/kit/langchainsatoKitLangChainTools(kit, opts)
@satohub/kit/elizasatoKitElizaPlugin(kit, opts) (compatibility adapter, see below)
@satohub/kit/mcpthe local MCP server (stdio)
@satohub/kit/clithe sato-kit CLI as a function
@satohub/kit/sato-osattachToSatoOs, proposeIntent
@satohub/kit/goatfromGoatPlugin(plugin, { chain }) — consume an existing GOAT plugin with the kit's guarantees
Signers
  • viemLocalSigner — a key in this process. Fork/testnet by default; refuses mainnet chain ids unless allowMainnet: true (not recommended). generate: true makes a throwaway in-memory key.
  • owsSigner — a structural adapter over an Open Wallet Standard account; OWS's policy engine enforces. See src/signers/OWS.md.
  • cdpSigner — a structural adapter over a Coinbase CDP server account; CDP enforces its policies. Pass a compiled policy as nativePolicy to carry it with the signer (the adapter does not register it).
  • solanaLocalSigner — local Solana signing for devnet and tests only; refuses any non-devnet payload and a mainnet-beta RPC, with no mainnet switch.
  • humanApprove(signer, approve) — wraps any signer so a person approves each summary before it signs.
Policy compilers

compileCdpPolicy, compilePrivyPolicy and compileTurnkeyPolicy turn one sato.policy/v1 into the provider's native policy document. Each result lists what did not compile (not_compiled) with the reason, so a rule the provider cannot express is never silently dropped.

CLI
sato-kit read <action> --input '<json>'      run a read-only action

sato-kit prepare --input ' ' build an intent; nothing is signed sato-kit execute --intent hand one prepared intent to the signer sato-kit mcp [--toolsets default|all] local MCP server over stdio sato-kit doctor check config, Sato Status and template drift

Config comes from the working directory: policy.json (absent means the default policy, network fork), .sato/ (intents, intent secret, receipts), SATO_RPC_URL_ per chain, and SATO_SIGNER=viem-local-fork (fork network only) for a local signer.

MCP server

npx -y @satohub/kit@0.1 mcp runs a stdio MCP server (registry name ai.satohub/kit). The default profile is the eight tools listed above; --toolsets all adds every other registered action. Tools that sign carry anthropic/requiresUserInteraction in _meta.

Sato Status

status and sato-kit doctor read the nightly per-action results (sato.action-status/v1) published by the templates repo. When that file cannot be read, the answer says so; nothing is filled in.

Recommended .gitignore

The file intent store and the intent HMAC secret live under .sato/ by default (intents/, intent.key, mode 0600). Keep them out of version control:

.sato/

License: MIT. The bundled Onchain Action Descriptor code (dist/spec) is Apache-2.0, copyright 2026 Prime Signal LLC: see LICENSE-ODA and NOTICE.

sato-kit doctor: template drift

In a repo made by create-sato-agent (one with sato.create.json), doctor also sends sato.create.json and sato.lock.json to https://satohub.ai/api/create/drift (3 s timeout) and prints the changes it returns: a newer template version that passed its checks, a custody change in a stored Sato Check profile for a pinned package, or a pinned package version that fails the templat

只显示了开头部分;其余内容请在仓库中阅读

问 PopNx