No install? Use cloud.anythingmcp.com directly.
Sign in, install the LinkedIn 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 LinkedIn (profile + shared posts) for the authenticated user from any AI agent. Limited scope: most LinkedIn features require Marketing Developer Platform approval. 5 tools, OAuth2 Bearer auth.
💡 ¿Sin instalación? Usa cloud.anythingmcp.com directamente. Inicia sesión, pulsa Connectors → LinkedIn, pega tus credenciales, genera una MCP API key — listo. Sin Docker, sin
git clone, sin servidor local.
LinkedIn + Gemini
Drive LinkedIn (profile + shared posts) for the authenticated user from any AI agent. Limited scope: most LinkedIn features require Marketing Developer Platform approval. 5 tools, OAuth2 Bearer auth.
Requisitos previos
Las instrucciones de configuración completas están incluidas en el conector (visibles en el store al seleccionarlo). Las variables de entorno requeridas:
LINKEDIN_ACCESS_TOKEN
Paso 1 — Obtener credenciales
microsoft.com/en-us/linkedin/).
HEAVY GATING: LinkedIn's API is one of the most restricted public APIs. Most useful endpoints (read posts, search profiles, fetch connections, manage company pages) require Marketing Developer Platform approval from LinkedIn — a partnership program with significant requirements (existing app + revenue commitments).
What WORKS without partnership:
- 'Sign in with LinkedIn using OpenID Connect' product scopes:
openid,profile,email,w_member_social(post on behalf of user).
…(continued in the in-app connector instructions)
Paso 2 — Instalar el adapter
git clone https://github.com/HelpCode-ai/anythingmcp.git
cd anythingmcp && docker compose up -d
Paso 3 — Añadir el conector en Gemini
Gemini CLI lee servidores MCP desde ~/.gemini/settings.json (o %APPDATA%\gemini\settings.json en Windows). Añade:
{
"mcpServers": {
"anythingmcp": {
"httpUrl": "https://cloud.anythingmcp.com/mcp",
"headers": { "Authorization": "Bearer YOUR_MCP_API_KEY" }
}
}
}
- Obtén tu MCP API key desde AnythingMCP → Perfil → MCP API Keys → Nueva Key.
- Guarda el archivo y reinicia
gemini. - Ejecuta
/mcpen la Gemini CLI —LinkedIndebería aparecer como disponible. - Vertex AI Studio: pasa
https://cloud.anythingmcp.com/mcpal arraytoolsde tu petición con el mismo header Bearer.
Herramientas disponibles
| Tool | What it does |
|---|---|
linkedin_userinfo | Get the authenticated user's profile (OpenID Connect userinfo endpoint) |
linkedin_create_post | Share a text or article post on behalf of the user |
linkedin_get_post | Get a previously-created post by URN (you can only fetch posts you authored unless you have higher-tier scopes) |
linkedin_delete_post | Delete a post you authored |
linkedin_register_image_upload | Step 1 of image upload: register an upload |
FAQ
¿Gemini 1.5 Pro o 2.x soportan MCP? Sí — Gemini CLI ≥ 0.4 y la API de tools de Vertex AI aceptan conectores MCP httpUrl con header Bearer.
Siguientes pasos
¿Te ha sido útil esta guía?