Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
Real-time and historical price feeds for 500+ crypto, equities, FX, and commodities assets.
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。
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。
选择你使用的 AI 应用,然后复制设置。
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:
https://mcp.pyth.network/mcp在终端中运行这条命令
claude mcp add --transport http pyth-network https://mcp.pyth.network/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"pyth-network": {
"url": "https://mcp.pyth.network/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。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"pyth-network": {
"type": "http",
"url": "https://mcp.pyth.network/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:
https://mcp.pyth.network/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。
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。
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6日
注册名称已通过 GitHub 账户 pyth-network 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
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。
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。
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。
GitHub 仓库最后更新于–,最新版本(0.3.2)于14天前进入注册中心。
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。
同一分类中有:Spec Driven Development, Remote Desktop Commander, Symantec Cloud DLP AIops
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
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Governed Symantec Cloud DLP — 14 MCP tools, read-only with audit.
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。
MCP server that gives AI assistants access to real-time and historical market data from Pyth — 500+ price feeds across crypto, equities, FX, commodities, and more.
Hosted at https://mcp.pyth.network/mcp
Each snippet sends your own Pyth Pro API key as an Authorization: Bearer header, so you set it once (see Access Token).
claude mcp add --transport http pyth https://mcp.pyth.network/mcp --header "Authorization: Bearer YOUR_TOKEN"
This adds Pyth only to the folder you run the command in. To use it in every project, add --scope user; any project you open can then call the price tools with your key.
Claude Desktop connects to remote servers as custom connectors, which can send your key as a header only where Anthropic's request-headers beta is enabled. To set the key once on any plan, bridge with mcp-remote (needs Node.js) in claude_desktop_config.json (Claude menu bar → Settings… → Developer → Edit Config):
{
"mcpServers": { "pyth": { "command": "npx", "args": ["-y", "mcp-remote@0.14.3", "https://mcp.pyth.network/mcp", "--header", "Authorization:${PYTH_AUTH_HEADER}"], "env": { "PYTH_AUTH_HEADER": "Bearer YOUR_TOKEN" } } } }
mcp-remote is a community package, not maintained by Pyth, and it handles your key; the snippet pins the version we tested.
Or add https://mcp.pyth.network/mcp as a custom connector: on Free, Pro or Max under Customize → Connectors → Add custom connector; on Team or Enterprise an Owner adds it under Organization settings → Connectors → Add → Custom, and members click Connect under Customize → Connectors. With the request-headers beta, choose No sign-in and add an authorization header Bearer YOUR_TOKEN (on Team and Enterprise plans the Owner sets it for the whole organization, so everyone shares that key); otherwise pass the key per call.
Add to ~/.cursor/mcp.json (global, so the key stays out of your repo):
{
"mcpServers": { "pyth": { "url": "https://mcp.pyth.network/mcp", "headers": { "Authorization": "Bearer YOUR_TOKEN" } } } }
To keep the key out of the file, write "Bearer ${env:PYTH_PRO_ACCESS_TOKEN}" and set that variable in your shell profile or system environment.
Add to ~/.copilot/mcp-config.json, a user-level file that VS Code's chat and its Agent Host sessions both read. It holds your key in plain text, so never copy it into a repository. (VS Code's ${input:...} prompt avoids that, but Agent Host sessions do not receive .vscode/mcp.json servers that use it.)
{
"mcpServers": { "pyth": { "type": "http", "url": "https://mcp.pyth.network/mcp", "headers": { "Authorization": "Bearer YOUR_TOKEN" }, "tools": ["*"] } } }
Any MCP client that supports Streamable HTTP: connect to https://mcp.pyth.network/mcp with the header Authorization: Bearer YOUR_TOKEN.
| Tool | Description | Auth Required |
|---|---|---|
get_symbols | Search and list price feeds; filter by asset type, instrument type or futures chain | Optional (adds Pro-only feeds and an entitled flag per feed) |
get_latest_price | Real-time prices for one or more feeds | Yes (access token) |
get_historical_price | Point-in-time price snapshots | Yes (access token) |
get_price_range | Every price update within a window of up to 60 seconds | Yes (access token) |
get_candlestick_data | OHLC candlestick bars for charting and analysis | Yes (access token) |
convert_date_to_timestamp | Convert date strings to Unix timestamps | No |
Tip: Use
get_symbolsfirst to discover available feeds. Price tools accept full symbols (Crypto.BTC/USD) or bare pairs (BTC/USD). A bare pair resolves to the live spot feed when there is one, otherwise to the only remaining match (e.g.BTC/USDT→ the Binance funding-rate feed); if several remain, the error lists them.
Every user brings their own Pyth Pro access token. It is required for get_latest_price, get_historical_price, get_price_range and get_candlestick_data. get_symbols works without one, but with a token it also lists feeds visible only to Pro keys and marks each feed entitled: true/false (whether your token can query it right now). convert_date_to_timestamp never needs one.
Authorization: Bearer header from your MCP client (see Quick Start), so your assistant does not handle it on every call.PYTH_PRO_ACCESS_TOKEN in the server's env block in your client config (see Local stdio config).access_token tool parameter. Your assistant asks for it when no token is configured. Clients that cannot send headers (e.g. Claude Desktop custom connectors without the request-headers beta) use this.PYTH_PRO_ACCESS_TOKEN in its own environment and only uses the key each user sends.stable return prices. Requested feeds that come back without a price (e.g. beta or coming_soon feeds, or a channel faster than the feed's min_channel) are listed in missing_feed_ids.Try these with any connected AI assistant:
For contributors working on the MCP server itself.
pnpm --filter @pythnetwork/mcp build
Run the inspector to interactively test tools:
npx @modelcontextprotocol/inspector --cli -- pnpm --filter @pythnetwork/mcp start:stdio:dev
To connect a client to a local build via stdio:
{
"mcpServers": { "pyth-mcp": { "command": "node", "args": [" /apps/mcp/dist/index.js"], "env": { "PYTH_PRO_ACCESS_TOKEN": "YOUR_TOKEN" } } } }
| Variable | Default | Description |
|---|---|---|
PYTH_CHANNEL | fixed_rate@200ms | Default price channel: real_time, fixed_rate@50ms, fixed_rate@200ms or fixed_rate@1000ms |
PYTH_LOG_LEVEL | info | Log level (debug/info/warn/error) |
PYTH_REQUEST_TIMEOUT_MS | 10000 | HTTP request timeout |
PYTH_PRO_ACCESS_TOKEN | — | Your own token, stdio only. Ignored by the HTTP server. |