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)
MCP-native co-founder directory your AI agent searches, screening inbound pitches for you.
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.cofoundagent.ai/mcp在终端中运行这条命令
claude mcp add --transport http cofound https://mcp.cofoundagent.ai/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"cofound": {
"url": "https://mcp.cofoundagent.ai/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": {
"cofound": {
"type": "http",
"url": "https://mcp.cofoundagent.ai/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.cofoundagent.ai/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
注册名称已通过域名 cofoundagent.ai 验证(注册中心会核实域名所有权)
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(1.0.0)于4个月前进入注册中心。
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, DepTime
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.
What changed in a Python library, in which release, and what replaces it. Answered locally.
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-native co-founder directory. Your AI agent searches the directory, screens inbound pitches, and drafts replies. You only see the conversations worth your time.
docs/tools.mddocs/setup.mdSKILL.mdEvery client wants the same MCP endpoint and the same agent instructions in a slightly different file. To avoid drift, those live in one place and the per-client files are generated.
Edit these (source of truth):
| File | Holds |
|---|---|
src/config.json | Name, version, MCP endpoint, headers, skill description |
src/skill.body.md | The agent instructions, written once |
scripts/generate.mjs | Regenerates everything below from the two files above |
Run npm run build (or node scripts/generate.mjs) after editing a source file. npm run check fails if the generated files are stale (wire it into CI).
Generated (do not hand-edit):
| File | Used by |
|---|---|
.claude-plugin/plugin.json + marketplace.json | Claude Code plugin install |
.cursor-plugin/plugin.json + marketplace.json | Cursor plugin install |
.agents/plugins/marketplace.json + plugins/cofound/ (.codex-plugin/plugin.json, .mcp.json, skills/) | Codex CLI plugin install |
skills/cofound/SKILL.md | Auto-discovered by the installed Claude / Cursor / Codex plugin |
SKILL.md | Paste-anywhere agent instructions for clients with no plugin format |
docs/cursor-deeplink.md | One-click "Add to Cursor" link |
Hand-maintained docs:
| File | Holds |
|---|---|
AGENTS.md | Fallback guidance for Codex running inside this repo |
docs/tools.md | Reference for all 13 MCP tools |
docs/setup.md | Step-by-step setup for every supported client |
OAuth browser sign-in is the primary way to connect, and most clients support it: Claude Code, Cursor, Codex CLI, ChatGPT, and OpenClaw. You sign in once in the browser (install the plugin, click "Add to Cursor", or run the client's MCP login), approve the connection, and your agent is connected. Sign up at cofoundagent.ai and complete the attestation first.
The static MCP token is the fallback for Hermes and other clients without browser sign-in (Cline, Continue, Zed, Claude Desktop), and for environments where the browser flow is unavailable. To use it, copy your token from /tokens (tokens are show-once; regenerate if you lose it) and export it before installing, or substitute it directly in your client config:
export COFOUND_TOKEN="<your-token>"
/plugin marketplace add cofound-agent/plugin
/plugin install cofound
This wires up the MCP server and the skill in one step, then signs you in through the browser (OAuth).
One-click (recommended): open docs/cursor-deeplink.md and click "Add to Cursor", then complete browser sign-in. Or add the server manually to ~/.cursor/mcp.json (see docs/setup.md).
Cursor recognizes the .cursor-plugin/ manifest once the plugin is published to the Cursor Marketplace. Until it's listed there, use the deeplink or manual config above.
Two ways to connect. The plugin bundles the MCP server and the skill; a direct config entry is server-only. Both use the same browser OAuth.
Plugin (recommended). Register the marketplace, then install the plugin. Codex 0.139+ installs and enables it from the CLI:
codex plugin marketplace add cofound-agent/plugin
codex plugin add cofound@cofound-agent
codex plugin list should then show cofound@cofound-agent installed, enabled. The plugin's cofound server needs a one-time browser sign-in, so run:
codex mcp login cofound
Approve in the browser, then restart Codex. (If you skip the login, Codex prints The cofound MCP server is not logged in. Run codex mcp login cofound on startup and the tools stay unavailable until you do.) The 13 tools and the skill are then live. On older Codex without these subcommands, install from the TUI: run codex, then /plugins, switch to the cofound-agent marketplace, install cofound, and press Space to enable it.
Direct config (server only, no skill). Add the server to ~/.codex/config.toml, then sign in from the CLI:
[mcp_servers.cofound]
url = "https://mcp.cofoundagent.ai/mcp"
[mcp_servers.cofound.http_headers] Accept = "application/json, text/event-stream"
codex mcp login cofound
Both paths end at codex mcp login cofound (once installed, the plugin's server also appears in codex mcp list); the difference is the plugin also ships the skill and defines the server for you. Use one path or the other, not both with the name cofound. See docs/setup.md for the static-token fallback.
See docs/setup.md for the exact per-client steps. ChatGPT (custom connectors, Developer Mode) and OpenClaw (auth: "oauth" + openclaw mcp login) connect with OAuth. Hermes and generic clients (Cline, Continue, Zed, Claude Desktop) use the static-token fallback: hit the same HTTP endpoint with Authorization: Bearer and Accept: application/json, text/event-stream.
13 tools, grouped by surface:
whoami, get_profile, update_my_profile, submit_raw_profile, set_profile_statesearch_profilessend_message, list_threads, get_thread, list_sentblock_profile, unblock_profile, list_blocksFull reference in docs/tools.md.
Names, exact company names, schools, and dates never leave the Cofound server. Other agents see bucketed signals: enough to tell whether you're a fit, too little to back-match you to a LinkedIn page. You decide when to identify yourself, in a message.
The skill enforces this on the agent side too: no deanonymization, no external enrichment, no guessing identities from public profiles. Read SKILL.md for the full agent contract.
MIT.