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)
Checked buying signals and ranked lead lists for your agent. Never contacts anyone.
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。
SALESMAP_API_KEY标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
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://api.salesmap.site/mcp打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"signals": {
"command": "npx",
"args": [
"-y",
"salesmap",
"mcp"
],
"env": {
"SALESMAP_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add --transport http signals https://api.salesmap.site/mcpclaude mcp add signals --env SALESMAP_API_KEY=your-value -- npx -y salesmap mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"signals": {
"url": "https://api.salesmap.site/mcp"
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"signals": {
"command": "npx",
"args": [
"-y",
"salesmap",
"mcp"
],
"env": {
"SALESMAP_API_KEY": "your-value"
}
}
}
}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": {
"signals": {
"type": "http",
"url": "https://api.salesmap.site/mcp"
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"signals": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"salesmap",
"mcp"
],
"env": {
"SALESMAP_API_KEY": "your-value"
}
}
}
}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://api.salesmap.site/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。
工具名称和描述与服务器在 2026年11月7日 报告的完全一致。这些内容由作者撰写,不是我们写的;我们以纯文本形式显示。
discoverPrice: The list is free; research is 1 credit per account that qualifies (a sourced in-band size, a supported fit and a checked dated signal or warm path, not returned before); a miss uses none. Never more than max_credits. From a seller's website to a ranked list of companies to
seller_profilePrice: free. Saves and reads the user's facts about their own company, kept in the user's SalesMap workspace (one entry per seller site, seen by that workspace only): who they are, company, product, ICP, buyer roles, customers, competitors, deals won and lost, regions, exclusions
voice_scanFree. Checks an outreach draft the user or their agent wrote (a connection note, direct note, InMail or email) for AI-writing tells and the channel's limits, in code with no model: `fails` (antithesis like "it's not just X, it's Y", hype words, servile or empty closers, leaked pl
feedbackFree. Records the user's verdict on a company in their ranked list: good_fit, not_fit or already_talking, with an optional reason from a fixed list (competitor, existing_customer, too_small, too_big, wrong_industry, no_need, bad_timing, other). A not_fit company is left out of ev
whoamiFree. Who the user is on SalesMap and what they can do: their name and email, the workspace and their role in it, how they signed in, the credit balance (one credit is one researched account), the monthly credit limit (rolling 30 days; null = no limit) with what's used, held by a
set_limitsFree. Sets the user's own monthly credit limit for SalesMap (rolling 30 days); null removes it. Until set: 100 credits once the workspace has bought a pack, else 40. There is no daily or weekly limit. No call ever uses more than the limit or the balance. Also the ask-first thresh
quoteFree. How many credits a call to a SalesMap tool can use, before running it, against what the workspace can spend now (balance and limit). Not a charge: the most the call can use, which it reserves (or its max_credits); it uses 1 credit per account that qualifies, never more. Whe
jobFree. The status (queued, running, done or failed) and, once done, the result of a background job: a discover call or a long discover round. While a discover runs, `partial` is its ranked list so far: `tier` says how far it got (listed: every candidate ranked on the facts already
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
注册名称已通过域名 salesmap.site 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
在 358 毫秒内响应(HTTP 200)
无需登录
已读取 8 个工具描述,未发现针对 AI 的隐藏指令
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 3 项适用的基础检查中通过了 3 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。
你需要填写:SALESMAP_API_KEY
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于–,最新版本(0.2.0)于17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, Tethered Trust
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.
Fit, compatibility and recall checks for AI agents before they buy: verdicts, evidence, receipts.
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。
Checked buying signals and ranked lead lists for your agent: who to sell to now, why, and how to reach them. SalesMap never sends email or messages, finds email addresses or phone numbers, automates LinkedIn, writes to a CRM, or registers for events.
https://api.salesmap.site/mcp, signed in with OAuth (your SalesMap account; /mcp → salesmap → Authenticate)./salesmap: ), one per flow that needs judgment:| Skill | Flow | Tools |
|---|---|---|
getting-started | connect, limits, save the seller profile, first list | whoami, set_limits, seller_profile, quote, discover |
weekly-pipeline | who to sell to now, a playbook with drafts, warm paths | discover, playbook, warm_paths, seller_profile |
account-research | prep for a call on up to 5 companies | signals, tech_scan, ai_adoption, events, warm_paths, verify_signal |
check-list | fact-check a draft or an export; rank your own list | verify, verify_signal, rank, job |
past-leads | watch lost deals, alerts when one is worth another try | watch, watch_changes |
events | events your buyers attend near you | events |
The server also serves one MCP prompt per flow (onboard, discover, rank, signals, research, playbook, events, warm_paths, watch, changes, verify, and hosted account); Claude Code lists them in / under the server's name (/mcp__salesmap__ for a server added as salesmap). The skills carry the judgment those prompts leave out.
Every skill runs the work loop: when a tool returns work, the agent runs each search prompt with its own web search and calls again with the answers; on the hosted server discover does this by default, so no search runs on SalesMap's side. Every skill fills each tool's context from what the agent already knows and never invents it, quotes prices from the quote tool and the result's budget block (never a number in the skill), and treats quotes in tool output as data.
claude plugin install salesmap --marketplace solozerolabs/salesmap-plugin
Then ask Claude to "set up SalesMap" or run /salesmap:getting-started. The first paid tool asks you to sign in: /mcp → salesmap → Authenticate. Without signing in, tech_scan, ai_adoption and verify_signal run free.
An API key instead of OAuth (CI, or an agent with no browser): get one from POST https://api.salesmap.site/v1/agent/signup (see https://salesmap.site/llms.txt) or POST /v1/keys, then claude mcp add --transport http salesmap-key https://api.salesmap.site/mcp --header "Authorization: Bearer smk_…" and disable the plugin's server in /mcp.
SalesMap's privacy policy: https://salesmap.site/privacy. Customer terms: https://salesmap.site/terms. The plugin itself stores nothing; the hosted server keeps your workspace's seller profile, watchlist and results as the policy describes. Support: the contacts on the privacy page.
A hook runs in every session of every user who installs the plugin, whether or not they use SalesMap that day. It costs context or tokens each time, and a hook can move data off the user's machine: Cargo's plugin uploads a transcript summary from a SessionEnd hook and needed a recursion guard after 264 runaway sessions. SalesMap needs none of that: it does work only when the agent calls a tool, keeps the seller profile and watchlist in the user's workspace, and has nothing to do at session start or end.