能做什么
LinkedIn Sales Navigator contact and account search from your logged-in browser.
作者提供的原文
- 连接方式 在你的电脑上运行
- 账号或密钥 无需密钥
- 分类 营销与社交媒体
可搭配使用
教 AI 做这类工作的 Skill,可与本项一起使用
为什么排在这里
列表按使用分(满分 100)排序,由以下部分组成
| 热度 | 6/80 | GitHub 星标或每周下载量:较大的计 60,较小的计 20 |
|---|---|---|
| 新鲜度 | 12/12 | 30 天内有发布或代码更新得满分 |
| 仍在响应 | 0/8 | 上次检查时云端端点有响应 |
| 使用分 | 18/100 |
质量: 基础检查通过 3/3 项(仅展示,不用于排序) · 上升势头: 暂无数据 (只用于“上升中”标签)
安装
选择你使用的 AI 应用,然后复制设置。
用一句话让 AI 帮你安装
请帮我安装 LinkedIn Sales Navigator。按照 https://mcp.popnx.com/i/nick-choudhary-linkedin-sales-nav-mcp.md 操作,先把命令给我看,等我同意后再运行。粘贴到能在你电脑上工作的 AI(如 Claude Code、Cursor)。它会读取我们的步骤,先给你看命令,等你同意。无需密钥,无需注册。 · 查看 AI 会读取的全文
通过 3/3 项检查 · 在你的电脑上运行 · ✓ 命令已检查 2026年11月13日
第一步:你用哪个 AI?
选择你用的应用,步骤会显示在下方。
可连接 Claude,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次) · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
让 AI 帮你安装
把这段话复制到 Claude 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude 安装 MCP server LinkedIn Sales Navigator,按顺序:1) 用 uv --version 检查是否有 uv。没有的话,请让我从 https://docs.astral.sh/uv/getting-started/installation/ 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "linkedin-sales-nav": { "command": "uvx", "args": [ "linkedin-sales-nav-mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 LinkedIn Sales Navigator 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
安装 uv(如果还没有)
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
uv --version- 显示版本号(例如 uv …)= 已安装,可跳过这一步
- 显示 "command not found"(Windows 显示 "is not recognized")= 还没安装,或刚装好但需要关掉终端再重新打开
怎么打开终端
Mac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: uv 没有点选式安装程序。从 uv 官方页面复制适合你系统(macOS 或 Windows)的一行命令,粘贴到终端 · 不需要单独安装 Python,uv 会在需要时自动下载
装好后关掉终端再打开,重新运行同一条命令,应显示版本号:
uv --version安装一次,所有需要 uv 的工具都能用
打开电脑版 Claude 应用的设置文件
SettingsDeveloperEdit Config
粘贴这些设置并保存文件
{ "mcpServers": { "linkedin-sales-nav": { "command": "uvx", "args": [ "linkedin-sales-nav-mcp" ] } } }退出 Claude 再重新打开
试一试
用 LinkedIn Sales Navigator 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude 说正在使用 LinkedIn Sales Navigator,或回答中出现 LinkedIn Sales Navigator 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
ChatGPT 暂时无法连接 LinkedIn Sales Navigator
LinkedIn Sales Navigator 需要安装在你的电脑上,而 ChatGPT 只能连接在网上运行的服务器
你可以改用这些方式
A · 使用能连接 LinkedIn Sales Navigator 的应用
- 需要先在电脑上安装 Python (uv)(只需一次) · 仅限电脑上的 Claude 应用(Windows 或 Mac),网页和手机不可用
- 需要先在电脑上安装 Python (uv)(只需一次)
- 需要先在电脑上安装 Python (uv)(只需一次)
- 需要先在电脑上安装 Python (uv)(只需一次)
B · 营销与社交媒体 类中能连接 ChatGPT 的其他服务器
从同类中使用较多的里挑选,仅限用地址即可连接、无需密钥的
- Google Ads + Meta Ads + SEO/GEO MCP✓ ChatGPT
- Cargo✓ ChatGPT
- NotFair✓ ChatGPT
可连接 Claude Code,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次)
让 AI 帮你安装
把这段话复制到 Claude Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Claude Code 安装 MCP server LinkedIn Sales Navigator,按顺序:1) 用 uv --version 检查是否有 uv。没有的话,请让我从 https://docs.astral.sh/uv/getting-started/installation/ 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):claude mcp add --scope user linkedin-sales-nav -- uvx linkedin-sales-nav-mcp 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 LinkedIn Sales Navigator 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
安装 uv(如果还没有)
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
uv --version- 显示版本号(例如 uv …)= 已安装,可跳过这一步
- 显示 "command not found"(Windows 显示 "is not recognized")= 还没安装,或刚装好但需要关掉终端再重新打开
怎么打开终端
Mac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: uv 没有点选式安装程序。从 uv 官方页面复制适合你系统(macOS 或 Windows)的一行命令,粘贴到终端 · 不需要单独安装 Python,uv 会在需要时自动下载
装好后关掉终端再打开,重新运行同一条命令,应显示版本号:
uv --version安装一次,所有需要 uv 的工具都能用
打开终端
Mac:按 Command+空格,输入 Terminal · Windows:打开 PowerShell
粘贴这条命令并按 Enter
claude mcp add --scope user linkedin-sales-nav -- uvx linkedin-sales-nav-mcp在 Claude Code 中输入 /mcp
应能看到 LinkedIn Sales Navigator 在列表中并显示已连接
试一试
用 LinkedIn Sales Navigator 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Claude Code 说正在使用 LinkedIn Sales Navigator,或回答中出现 LinkedIn Sales Navigator 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Anthropic 帮助页面核实 · 你的界面可能因版本略有不同
可连接 Cursor,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次)
让 AI 帮你安装
把这段话复制到 Cursor 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 Cursor 安装 MCP server LinkedIn Sales Navigator,按顺序:1) 用 uv --version 检查是否有 uv。没有的话,请让我从 https://docs.astral.sh/uv/getting-started/installation/ 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "mcpServers": { "linkedin-sales-nav": { "command": "uvx", "args": [ "linkedin-sales-nav-mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 LinkedIn Sales Navigator 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
安装 uv(如果还没有)
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
uv --version- 显示版本号(例如 uv …)= 已安装,可跳过这一步
- 显示 "command not found"(Windows 显示 "is not recognized")= 还没安装,或刚装好但需要关掉终端再重新打开
怎么打开终端
Mac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: uv 没有点选式安装程序。从 uv 官方页面复制适合你系统(macOS 或 Windows)的一行命令,粘贴到终端 · 不需要单独安装 Python,uv 会在需要时自动下载
装好后关掉终端再打开,重新运行同一条命令,应显示版本号:
uv --version安装一次,所有需要 uv 的工具都能用
在 Cursor 中以 Agent 模式打开 AI 聊天
试一试
用 LinkedIn Sales Navigator 告诉我你能帮我做什么,然后做一件给我看✓ 如果 Cursor 说正在使用 LinkedIn Sales Navigator,或回答中出现 LinkedIn Sales Navigator 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 Cursor 帮助页面核实 · 你的界面可能因版本略有不同
可连接 VS Code,但需要先准备
需要先在电脑上安装 Python (uv)(只需一次)
让 AI 帮你安装
把这段话复制到 VS Code 的对话里。AI 会先检查电脑,告诉你要改哪个文件,并且每次都等你同意。
请在这台电脑上为 VS Code 安装 MCP server LinkedIn Sales Navigator,按顺序:1) 用 uv --version 检查是否有 uv。没有的话,请让我从 https://docs.astral.sh/uv/getting-started/installation/ 安装,不要自己安装。2) 只使用这份配置(已通过 PopNx MCP 检查):{ "servers": { "linkedin-sales-nav": { "type": "stdio", "command": "uvx", "args": [ "linkedin-sales-nav-mcp" ] } } } 3) 告诉我要修改的文件完整路径或要运行的命令,等我同意。4) 不需要密钥。5) 按约定执行,然后确认 LinkedIn Sales Navigator 的工具真的出现了。这段话不包含你的密钥。如果需要密钥,AI 会请你自己粘贴到文件或应用的输入框里。
安装 uv(如果还没有)
已经装好了吗?先检查 · 打开终端,输入这条命令后按 Enter
uv --version- 显示版本号(例如 uv …)= 已安装,可跳过这一步
- 显示 "command not found"(Windows 显示 "is not recognized")= 还没安装,或刚装好但需要关掉终端再重新打开
怎么打开终端
Mac:按 ⌘ + Space,输入 Terminal 后按 Enter
Windows:打开“开始”菜单,输入 Windows PowerShell,然后选“打开”
还没安装: uv 没有点选式安装程序。从 uv 官方页面复制适合你系统(macOS 或 Windows)的一行命令,粘贴到终端 · 不需要单独安装 Python,uv 会在需要时自动下载
装好后关掉终端再打开,重新运行同一条命令,应显示版本号:
uv --version安装一次,所有需要 uv 的工具都能用
在 VS Code 中以 Agent 模式打开 AI 聊天
试一试
用 LinkedIn Sales Navigator 告诉我你能帮我做什么,然后做一件给我看✓ 如果 VS Code 说正在使用 LinkedIn Sales Navigator,或回答中出现 LinkedIn Sales Navigator 的工具名称,就表示连接成功
菜单名称已于 2026年11月11日 对照 VS Code 帮助页面核实 · 你的界面可能因版本略有不同
开发者专用:终端命令和 JSON 设置
安装在电脑上
Claude Code
claude mcp add --scope user linkedin-sales-nav -- uvx linkedin-sales-nav-mcpClaude Desktop (claude_desktop_config.json)
{
"mcpServers": {
"linkedin-sales-nav": {
"command": "uvx",
"args": [
"linkedin-sales-nav-mcp"
]
}
}
}Cursor (~/.cursor/mcp.json)
{
"mcpServers": {
"linkedin-sales-nav": {
"command": "uvx",
"args": [
"linkedin-sales-nav-mcp"
]
}
}
}VS Code (mcp.json)
{
"servers": {
"linkedin-sales-nav": {
"type": "stdio",
"command": "uvx",
"args": [
"linkedin-sales-nav-mcp"
]
}
}
}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。
一览
哪些应用可以使用它
依据这个服务器的连接方式和各应用自己的文档,检查于 2026年11月10日。
在你的电脑上运行,适用于
ClaudeGooseLM StudioMsty StudioCherry StudioCursorVS Code + GitHub CopilotVisual StudioWindsurf (Devin Desktop)ZedKiroClineContinueJetBrains AI AssistantClaude CodeCodex CLIGemini CLIOpenCodenodecodeWarpLibreChatRaycast
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20日
- ✓ 通过
作者与仓库一致
注册名称已通过 GitHub 账户 nick-choudhary 验证,该账户拥有此仓库
- ✓ 通过
仍在维护
代码最后更新于9天前
- ✓ 通过
有许可证
使用 MIT
- – 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
已公开的漏洞(OSV.dev)
OSV.dev 中没有 linkedin-sales-nav-mcp@1.2.0 的记录
只检查这个版本的包本身,不包括所有依赖 · 检查于 2026年11月15日
作者:申请重新检查或报告信息错误
给作者:在 README 中加徽章
如果你是作者,可把这段代码贴到 README。徽章会链接回本页。
[](https://mcp.popnx.com/en/servers/nick-choudhary-linkedin-sales-nav-mcp)讨论
提问、分享技巧或报告无法使用。按“有帮助”数量排序。
用户评价
还没有评价
与“营销与社交媒体”中的其他服务器比较i
- 星标数多于此分类中其他 4243 个服务器的 91%
- 发布到注册中心的时间比此分类中其他 4243 个服务器的 20% 更新
- 基础检查结果等于或优于此分类中其他 4243 个服务器的 99%
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
LinkedIn Sales Navigator 安全吗?
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。
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9天前,最新版本(1.2.0)于3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。你的电脑上还需要有 Python (uv)。
有什么可以替代它?
同一分类中有:Relaticle, ChatbotX, X (Twitter) MCP Server by Xquik, Betterlytics, BibiGPT YouTube Video Summarizer
功能相近的其他选择
同一分类、其他作者、命令已通过检查。官方的排在前面,再按星标排序。
如何看卡片:↓ 每周下载量i★ 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
Relaticle
Open-source CRM your AI agents can write to: companies, people, opportunities, tasks and notes.
ChatbotX
Omnichannel customer messaging, CRM contacts, flows, sequences, broadcasts, and AI automation.
X (Twitter) MCP Server by Xquik
Xquik is the world's fastest and cheapest X (Twitter) data API with the most complete X data.
Betterlytics
Query your Betterlytics web analytics from AI agents: traffic, funnels, journeys, errors, uptime.
BibiGPT YouTube Video Summarizer
AI video summarizer: summarize and transcribe YouTube, Bilibili, TikTok and podcast videos.
| 本项 LinkedIn Sales Navigator | Relaticle | ChatbotX | X (Twitter) MCP Server by Xquik | Betterlytics | BibiGPT YouTube Video Summarizer | |
|---|---|---|---|---|---|---|
| 运行位置 | 需要安装在电脑上 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 | 在云端运行,无需安装 |
| 需要密钥 | 否 | 否 | 否 | 否 | 是 | 否 |
| 可在 Claude 中按 + 添加 | 否 | 否 | 否 | 否 | 否 | 否 |
| 基础检查 | 3/3 | 4/4 | 4/4 | 4/4 | 4/4 | 4/4 |
| 许可证 | MIT | AGPL-3.0 | NOASSERTION | MIT | AGPL-3.0 | MIT |
| 价格 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 | 登记中未列出费用 |
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。
LinkedIn Sales Navigator MCP Server
MCP server that gives AI assistants (Claude Desktop, Claude Code, any MCP client) access to LinkedIn Sales Navigator contact and account search — by driving a real, logged-in browser on your machine and capturing Sales Navigator's own search API responses.
Why this design (and why not cookie-replay)
The common approach — copy your li_at + JSESSIONID cookies and replay them as HTTP requests from a server — gets you logged out repeatedly. LinkedIn scores each session on IP, browser fingerprint, TLS, and the full cookie set; two replayed cookies from a different machine look like a hijacked session, so it invalidates them.
This server does the opposite. It keeps a persistent browser profile you log into once, by hand, and then lets that genuine session do the work:
MCP client (Claude) ──stdio/HTTP──> this server ──drives──> your logged-in Chromium ──> Sales Navigator
│ captures the JSON the browser itself receives (page.on "response")
Every request to LinkedIn originates from the real browser: your IP, your fingerprint, your full cookie jar, browser-generated CSRF/track headers, and the session is refreshed by the browser as normal. Nothing is replayed or reconstructed. That is what keeps you signed in.
We never automate the login itself — typing credentials is a strong bot signal. You sign in manually once; the profile persists.
Tools
| Tool | What it does |
|---|---|
search_contacts | People/lead search from a Sales Navigator URL. Navigates + paginates in the browser, saves records to SQLite, returns a small progress summary. |
search_accounts | Company/account search from a Sales Navigator URL. Same, for accounts. |
enrich_leads | Add Open Profile / InMail status to a saved contact search. By default (method="compose") it opens each lead's message panel and also records contact info and insights (recent posts, job change, shared connections). Opt-in and resumable — see Open Profile status. |
fetch_lead_profiles | Depth 3: full profiles for drafting (~15 KB/lead). Opt-in via ENABLE_PROFILE. |
get_lead_profile | Read one stored full profile. Local only, no LinkedIn call. |
pipeline_status | One funnel view: scraped → enriched → open → profiled → sent. |
reconcile_outreach | Settle sends stuck in sending against LinkedIn itself. |
run_outreach_batch | Draft and send for several leads in one call via MCP sampling. Same guards; dry_run defaults true. |
outreach_next | Live session: walks the search results, opens the next eligible lead's message panel from its row, captures it, and returns the lead's data to draft from. Non-Open-Profile leads and existing conversations are skipped automatically. mode: draft, supervised (30 s countdown) or auto (5 s). |
outreach_submit | Fills the open panel with the draft. draft mode saves it; otherwise a banner in the page counts down with Skip / Send now / Pause, and whatever the panel holds at zero (edits included) is re-checked and sent through the same two-phase commit, cap and dedupe as send_message. |
outreach_skip | Closes the open panel without sending and records why. |
What is code and what is model in a live session. Everything that can be decided from data is decided in code, before any tokens are spent: the ICP screen (FIT_RULES_FILE, applied before a panel is opened, so a rejected lead costs no LinkedIn request either), Open Profile and existing-thread checks, trimming the lead to a fixed budget (summary, current role, three recent posts), and the company block — LinkedIn's own Account IQ dossier boiled down to priorities, challenges, revenue model, workforce and news, or TinyFish news (TINYFISH_API_KEY) when the dossier is empty. The offer is sent once per session, not per lead. The model only writes the message. | check_replies | Read the inbox and mark leads who answered. Sends nothing. | | next_outreach_batch | Leads eligible for a first message — Open Profile first, anyone already contacted excluded. Read-only. | | send_message | Send ONE message. The only tool that writes to LinkedIn: off by default, dry_run=true by default. | | outreach_status | Counts by status and channel, plus remaining daily cap. | | check_session_status | Reports whether the browser profile has a live Sales Navigator session (tells you if you need to re-run --login). | | list_queries | Every saved search with its progress: url_hash, status, last_page, records_count. | | get_results | Pull a bounded slice (1–200) of a saved query's records into the conversation for analysis. | | export_results | Write a saved query's records to JSON and/or CSV under the output folder. |
Both search tools take a full Sales Navigator URL (build the search in the UI, copy it from the address bar) and a pages count (1–10, 25 results each).
Beyond tools, the server exposes one resource (sales-nav://queries — saved queries and their progress as attachable JSON context) and one prompt (sales_nav_search_workflow — the step-by-step prospecting playbook, for clients that support MCP prompts).
Search tools do not return the records
This is deliberate, and it is the thing most likely to surprise you. Records go to SQLite; the tool returns only a status object, so a 250-row scrape doesn't dump 250 rows into the model's context:
{
"url_hash": "a6ca46c9365bce93", "scraper_type": "contacts", "status": "paused", // new | in_progress | paused | complete "new_records_this_call": 25, "total_records": 25, "total_available": 11897313, "pages_fetched": 1, "last_page": 1, "next_page": 2, // null once exhausted "raw_dir": null, // set when include_raw=true "suggestion": "Saved 25 records so far (through page 1) ..." }
To get at the data, call get_results (a sample) or export_results (files), or read the SQLite database directly.
Pipeline depth
How far a query is taken is a property of the query, not of the call that made it, so a run resumed tomorrow knows what the search was collected for.
| Depth | Endpoints | Cost per lead | Gate |
|---|---|---|---|
search | lead search | one page per 25 | always on |
open_profile | + enrich_leads | ~240 B | ENABLE_ENRICH (default on) |
full | + fetch_lead_profiles | ~15 KB | ENABLE_PROFILE (default off) |
search_contacts(url, pages=4, depth="open_profile")
Depth is stored on the query and echoed back with a next_step. Requesting a depth the server has not enabled is refused with an explanation rather than silently downgraded, so a default install cannot be pointed at a list and made to pull thousands of full profiles.
enrich_leads and fetch_lead_profiles hit the *same* endpoint with different projections, and stay separate on purpose: the screen runs across a whole list to find who is free to message, the full fetch runs only for the leads you are about to write to. Merging them would pull heavy payloads for leads you never contact — and would make "recent activity" as stale as the screen.
Sending messages
This is the only capability that writes to LinkedIn, and it is treated differently from everything else here. Reading looks like a person browsing; a burst of messages looks like exactly what it is, and the consequence lands on your account rather than on the code. So every default is the cautious one:
| Guard | Default |
|---|---|
ENABLE_SENDING | false — a fresh install cannot message anyone |
dry_run | true — returns the exact draft, sends nothing |
ALLOW_CREDIT_SPEND | false — refuses anything that costs an InMail credit |
SEND_DAILY_CAP | 40, rolling 24h, across all campaigns |
SEND_DELAY_MIN/MAX | 45–120s between sends |
Free vs paid, and why enrichment comes first
Open Profile members can be messaged without spending an InMail credit; everyone else costs one from a finite monthly budget. The compose window states which it is — "Free to Open Profile" versus "Use 1 of N credits" — and the sender reads that line, records the channel, and refuses the paid path unless you have explicitly allowed it.
That is why enrich_leads matters commercially and not just as metadata: next_outreach_batch returns only confirmed Open Profile leads by default, so the free channel is the path of least resistance.
Never twice
Outreach state lives in lead_outreach, keyed on (member_id, campaign), and the exclusion is global: anyone with a sent row in *any* campaign is filtered out of every future batch. Dedupe elsewhere in this server saves a wasted request; here it prevents messaging the same human twice because two searches happened to find them. member_id is the only identifier stable across searches, which is why it is the key.
State is committed per send, never per batch — a crash must not leave a message delivered on LinkedIn but unrecorded here.
The offer file stays yours
The server never generates copy and never learns what you sell. Your positioning lives in a Markdown file that is gitignored and not packaged:
cp offer.example.md offer.md # then edit it
echo "OFFER_FILE=./offer.md" >> .env
The sales_nav_compose_message prompt renders that file together with the lead record and the drafting rules; your MCP client's model writes the message. With no offer file configured the prompt refuses to render at all.
The evidence gate
The drafting model must return the record fields it drew on:
{"subject": "...", "body": "...", "evidence_used": ["positions[0].title", "companyName"]}
Every entry is resolved against the lead record actually fetched. Name a field that does not exist and the message is rejected unsent. It is a cheap, deterministic check that "personalized" means grounded in data we really have — a message claiming a conference talk gets rejected because nothing supports it. Empty evidence_used is also rejected: that is a template, not personalization.
Unattended batches
Everywhere else the split is deliberate: the server decides *who*, your client's model decides *what to say*. That needs a human-driven turn — fine at a desk, useless on a schedule.
run_outreach_batch closes the gap with MCP sampling. The server asks your client for each draft (ctx.sample), so no model runs here, no API key lives here, and no copy is generated by this process — only a request for one.
Nothing is relaxed for automation. Every draft goes through the same send path as a hand-written one: the evidence gate, global dedupe, the daily cap, the free-channel-only default, two-phase commit. dry_run still defaults to true. A draft that fails to parse or fails validation is recorded and skipped rather than sent or allowed to end the run, and the batch stops early when the cap is reached.
run_outreach_batch(url_or_hash, campaign="q3", limit=5) # d