Signado-MCP

Signado MCP is a LinkedIn MCP server for warm leads.

От сообществаРаботаетБез входаГлобальныйБесплатноТолько чтение

Что умеет

  • Ping: Free connectivity check. Echoes the message back with the server timestamp. Costs no credits and touches no data.
  • List Warm Leads: List warm leads discovered from LinkedIn engagement, newest first (already ICP-scored where scoring has run). Free — costs no credits. Returns up to `limit` leads (default 50, max 200
  • Export Leads: Export warm leads as structured rows (same columns as the app's CSV export; one row per contact, engagement columns show the most recent engagement). Free — costs no credits. YOU write t

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

Signado MCP is a LinkedIn MCP server for warm leads. It connects Claude Code, Codex, ChatGPT, or any MCP client to your Signado workspace: list the people already talking about what you do on LinkedIn, see what they said, find emails, and save AI outreach drafts. OAuth sign-in, no API keys.

It never logs into your LinkedIn account.

Как подключить

Как подключить Signado-MCP к Claude

Адрес сервера, который нужно вставить в настройках Claude:

https://warm-leads--signado.run.tools

  1. Откройте Claude (сайт claude.ai или приложение для компьютера).
  2. Перейдите в Настройки → Коннекторы (в английском интерфейсе: Settings → Connectors).
  3. Нажмите Добавить пользовательский коннектор (Add custom connector).
  4. Вставьте адрес сервера, скопированный ниже, в поле URL удалённого MCP-сервера и нажмите Добавить.
  5. В чате нажмите + → Коннекторы и включите новый коннектор.

Пользовательские коннекторы доступны на тарифах Free, Pro, Max, Team и Enterprise. На Free можно добавить только один. В Team и Enterprise коннектор сначала добавляет владелец организации в Настройки организации → Коннекторы.

Авторизация

После нажатия Добавить откроется окно входа в сервис. Войдите под своим аккаунтом и подтвердите доступ. Пароль Claude не видит.

Как подключить Signado-MCP к ChatGPT

Адрес сервера, который нужно вставить в настройках ChatGPT:

https://warm-leads--signado.run.tools

  1. Откройте ChatGPT в браузере (chatgpt.com). Нужен тариф Plus, Pro, Business, Enterprise или Edu.
  2. Один раз включите режим разработчика: Настройки → Приложения → Дополнительные настройки → Режим разработчика (Settings → Apps → Advanced settings → Developer mode).
  3. Откройте Настройки → Коннекторы и нажмите Создать (Create).
  4. Заполните форму: Название (любое), Описание (одна фраза, что делает сервис), URL MCP-сервера (скопируйте ниже).
  5. В поле Аутентификация выберите OAuth, если сервис требует вход, иначе Нет. Нажмите Создать.
  6. В новом чате откройте + → Приложения/Коннекторы и включите коннектор.

Название раздела у OpenAI менялось (Connectors → Apps/Plugins). Если пункт называется иначе, ищите «режим разработчика» в настройках. В рабочих пространствах Business/Enterprise администратор должен разрешить пользовательские коннекторы.

Авторизация

При первом использовании ChatGPT откроет окно входа в сервис. Войдите и подтвердите доступ.

Как подключить Signado-MCP к Cursor

Адрес сервера, который нужно вставить в настройках Cursor:

https://warm-leads--signado.run.tools

Быстрый способ: нажмите кнопку Открыть в Cursor ниже, Cursor сам предложит добавить сервер.

Вручную:

  1. В Cursor откройте Settings → Cursor Settings → MCP и нажмите Add new global MCP server.
  2. Вставьте JSON, скопированный ниже, в открывшийся файл ~/.cursor/mcp.json (для одного проекта: .cursor/mcp.json в корне проекта).
  3. Сохраните файл. Сервер появится в списке MCP; при необходимости пройдите авторизацию по кнопке рядом с ним.

Авторизация

Если сервис требует вход, рядом с сервером в списке MCP появится кнопка авторизации.

Список инструментов сервера (12)

Технические названия из tools/list. Нужны только разработчикам.

pingFree connectivity check. Echoes the message back with the server timestamp. Costs no credits and touches no data.
list_warm_leadsList warm leads discovered from LinkedIn engagement, newest first (already ICP-scored where scoring has run). Free — costs no credits. Returns up to `limit` leads (default 50, max 200) with engagement context, company fields, and icp_score.
export_leadsExport warm leads as structured rows (same columns as the app's CSV export; one row per contact, engagement columns show the most recent engagement). Free — costs no credits. YOU write the CSV/file from the returned rows. `days` filters by discovery date and DEFAULTS TO 2 (set it explicitly for a longer window, max 365). Caps at 5000 rows and sets truncated=true if more exist within the window; use `limit` to request fewer.
remove_sourceRemove (archive) a discovery source by its exact source ID — stops its scheduled LinkedIn scraping. Free. DESTRUCTIVE for monitoring: queued scrape jobs are cancelled. Historical warm leads keep their source label, and re-adding the same keyword/creator later revives this source with its history.
preview_sourceRun a live preview of a discovery source (keyword or competitor_creator) BEFORE activating it: searches recent LinkedIn posts and samples real commenters so you can judge vertical fit. PAID — costs 1 credit per preview (charged up front, refunded automatically if the run fails to start or never completes). Takes ~10-60s. Requires a completed Business Profile. Provide a fresh idempotency_key per new preview; reuse the same key only to retry an uncertain call.
add_sourceAdd AND activate a LinkedIn discovery source (keyword search or competitor/creator profile) — this IS the start-monitoring act. Keyword sources accept keyword_mode: post_engagers (default, people commenting on matching posts) or post_authors (people who wrote matching posts). Creator profile sources do not accept keyword_mode. Free to call, but activation triggers a first scrape in ~5-15 minutes and recurring daily discovery spend (3 credits per new lead, from the workspace daily budget). REQUIRES confirm: true to act; without it returns a dry-run plan with budget impact. Re-adding a removed source revives its history. Idempotent: calling again on an active source is a no-op.
catchup_sourceQueue a one-time 7-day catch-up scan for an active keyword or creator discovery source. Requires confirm:true plus max_credits to mutate; confirm:false returns a dry-run instruction. The call itself does not charge credits. Stage-2 lead discovery later charges/refunds normal wallet credits through the existing lead_discovery settlement path, and the daily discovery budget is not affected.
find_emailFind work emails for warm leads by their contact IDs (get IDs from list_warm_leads). PAID — 5 credits per contact actually queued, charged up front; credits for emails NOT found are refunded automatically at settlement. Max 200 contacts per call. Contacts already emailed, already in flight, or without a LinkedIn profile are skipped free. Async: returns scrape_job_id; results land on the leads within ~1-5 minutes. Provide a fresh idempotency_key per new batch; reuse the same key only to retry an uncertain call.
qualifyQueue company qualification for warm leads by contact IDs (get IDs from list_warm_leads). PAID when confirm:true — 2 credits per contact actually queued, charged up front through the Qualify scrape_job; uncompleted contacts are refunded automatically at settlement after the worker runs. Contacts already pending, processing, completed, or failed are skipped free in normal mode. Use mode=requalify_completed only for an explicit re-qualify action on completed results; it resets completed qualification data and charges again. Requires confirm:true to mutate/charge; confirm:false returns a dry-run estimate. Provide a fresh idempotency_key per confirmed batch; reuse the same key only to retry an uncertain confirmed call.
draft_messageDraft AI outreach messages for warm leads (contact IDs from list_warm_leads). PAID — 7 credits PER CONTACT, so cost = 7 × number of contact_ids (each contact gets one AI-drafted message, charged as drafting proceeds; max 5 contacts per call). Creates a campaign (or reuses one via campaign_id from a previous call) and returns the drafted text. Template choice: template_id (see list_templates) OR inline_config (custom template body, tone, language, AI variables) — not both; default is the Warm Leads LinkedIn DM template. Takes ~10-40s per message. Failed or unresolved generations are NOT auto-refunded (matches the app). Requires a completed Business Profile. Run ONE draft call per campaign at a time — concurrent calls on the same campaign can mis-attribute failures and overwrite each other's template config. Provide a fresh idempotency_key per new batch; reuse the same key ONLY to retry an uncertain call — a reused key returns the previous call's stored result regardless of new arguments.
list_templatesList the message templates available to this workspace — system presets (e.g. the Warm Leads LinkedIn DM default) plus your own saved templates — with each template body, tone, language and AI variables. Also returns the authoring constraints (allowed tones, languages, variable max-lengths, static variables like {FirstName}, preset AI variables, and your plan's AI-variable limit) for building a save_template or draft_message inline_config. Free, read-only.
save_templateSave a reusable message template for this workspace (visible in the app's campaign wizard and via list_templates; usable in draft_message by template_id). Free. Provide the template body — static variables like {FirstName} and AI variables like {{icebreaker}} — plus tone, language and per-AI-variable instructions. Check list_templates first for allowed tones/languages/max-lengths and your plan's AI-variable limit (enforced at draft time, not save time). System templates cannot be modified.
Signado-MCP: подключить к Claude, ChatGPT, Cursor · Connectors.fun