No install? Use cloud.anythingmcp.com directly.
Sign in, install the Outreach in one click, paste the credentials, mint an MCP API key — done. No Docker, no git clone, no local server to run.
TL;DR
Drive Outreach (sales engagement platform) from any AI agent: prospects, accounts, sequences, sequence enrollment, tasks, users. 11 tools, OAuth2 Bearer auth, JSON:API spec.
💡 Без установки? Используйте cloud.anythingmcp.com напрямую. Войдите, нажмите Connectors → Outreach, вставьте учётные данные, создайте MCP API key — готово. Без Docker, без
git clone, без локального сервера.
Outreach + Gemini
Drive Outreach (sales engagement platform) from any AI agent: prospects, accounts, sequences, sequence enrollment, tasks, users. 11 tools, OAuth2 Bearer auth, JSON:API spec.
Предварительные требования
Полные инструкции по настройке встроены в коннектор (видны в магазине при выборе коннектора). Требуемые переменные окружения:
OUTREACH_ACCESS_TOKEN
Шаг 1 — Получите учётные данные
outreach.io).
Setup:
- Outreach API access is OAuth2-only — no static API keys. Register an OAuth app at https://developers.outreach.io.
- Run the OAuth2 authorization-code flow to obtain an access_token (short-lived, ~7200 s) + refresh_token (long-lived). The access_token is what you pass to the connector.
- Set
OUTREACH_ACCESS_TOKEN. - Refresh logic: handle refresh-token rotation externally (the engine refreshes BEARER_TOKEN on 401 if
refreshToken+tokenUrlare present in authConfig — but per-tenant OAuth2 setup is outside this connector's scope).
Authentication: Authorization: Bearer ${OUTREACH_ACCESS_TOKEN}.
…(continued in the in-app connector instructions)
Шаг 2 — Установите адаптер
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
Шаг 3 — Добавьте коннектор в Gemini
Gemini CLI читает MCP-серверы из ~/.gemini/settings.json (или %APPDATA%\gemini\settings.json в Windows). Добавьте:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Получите MCP API key в AnythingMCP → Profile → MCP API Keys → New Key.
- Сохраните файл и перезапустите
gemini. - Запустите
/mcpв Gemini CLI —Outreachдолжен быть доступен. - Vertex AI Studio: передайте
https://cloud.anythingmcp.com/mcpв массивtoolsзапроса с тем же Bearer-заголовком.
Доступные инструменты
| Tool | What it does |
|---|---|
outreach_list_prospects | List prospects with filters |
outreach_get_prospect | Fetch a prospect by ID with full attributes and relationships |
outreach_create_prospect | Create a prospect |
outreach_update_prospect | Update a prospect |
outreach_list_accounts | List accounts with filters |
outreach_list_sequences | List sequences (cadences) |
outreach_enroll_in_sequence | Enroll a prospect in a sequence (create sequenceState) |
outreach_list_mailboxes | List mailboxes (email accounts connected to Outreach for sending) |
outreach_list_users | List Outreach users |
outreach_list_tasks | List tasks (manual steps in sequences that need agent action — calls, custom emails, LinkedIn DMs) |
outreach_list_stages | List prospect stages defined on the org (the funnel positions like Lead/MQL/SQL/Opportunity) |
FAQ
Поддерживают ли Gemini 1.5 Pro или 2.x MCP? Да — Gemini CLI ≥ 0.4 и Vertex AI tools API принимают MCP-коннекторы httpUrl с Bearer-заголовком.
Следующие шаги
Это руководство помогло?