11agents Cloud MCP

Registre officiel Recherche et web

Cloud MCP for project data, analytics, research, content planning, media generation, and growth.

Installation

Ajoutez ceci à la configuration MCP de votre client (Claude Desktop : claude_desktop_config.json ; Cursor : .cursor/mcp.json ; VS Code et les autres utilisent la même forme « mcpServers »).

Remote (streamable-http)
Claude Code
claude mcp add --transport http 11agents-cloud-mcp 'https://app.11agents.ai/mcp' --header 'Authorization: <11agents project token, sent as a Bearer token.>'
Configuration JSON (Claude Desktop, Cursor, VS Code)
{
    "mcpServers": {
        "11agents-cloud-mcp": {
            "type": "http",
            "url": "https://app.11agents.ai/mcp",
            "headers": {
                "Authorization": "<11agents project token, sent as a Bearer token.>"
            }
        }
    }
}

Documentation

Tirée du README du projet sur GitHub, actualisée chaque semaine. Les liens ouvrent GitHub.

Sommaire
  1. 11agents Cloud MCP
  2. Connect
  3. Capabilities
  4. Security and support

11agents Cloud MCP

Connect AI agents to a project-scoped growth workspace through one hosted Model Context Protocol server. The server exposes 25 tools for project knowledge, structured data, analytics, research, planning, media generation, short-drama intelligence, reports, and skill synchronization.

Connect

  • MCP endpoint: https://app.11agents.ai/mcp
  • Transport: Streamable HTTP
  • Authentication: Authorization: Bearer <project token>
  • Discovery: https://app.11agents.ai/.well-known/mcp.json

Create or open a project at 11agents, open its MCP page, and copy the project token. Keep the token secret: it grants access to that project's MCP tools and data.

Use this generic remote-server configuration in clients that accept MCP JSON:

{
  "mcpServers": {
    "11agents": {
      "type": "streamable-http",
      "url": "https://app.11agents.ai/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_PROJECT_TOKEN"
      }
    }
  }
}

Client configuration formats differ. If a client has separate URL and header fields, use the endpoint above and add the Authorization header exactly as shown.

Capabilities

AreaTools
Project knowledge and dataknowledge_sync, database_sync, data_format_define, data_push
Advertising and analyticsads_daily_snapshot_push, analytics_summary, analytics_funnel, analytics_channels, analytics_events
Planningagent_planning
SEO and AI visibility researchahrefs_keyword_research, ahrefs_domain_research, querit_ai_citation_research, apodex_deep_research
Image and audio generationimage_prompt_generate, image_generate, image_generate_async, image_job_get, image_job_image_get, fish_audio_tts
Short-drama intelligence and reportsradar_top_dramas, radar_data_publish, insight_card_publish
Agent skill syncskill_list, skill_file_get

The server returns only tools available to the authenticated project. Some write, paid-provider, or publishing actions may require project permissions or approval.

Security and support

This repository contains public metadata and connection documentation for the hosted server. The production service remains hosted and maintained by 11agents.

Questions fréquentes

Qu'est-ce que 11agents Cloud MCP ?

Cloud MCP for project data, analytics, research, content planning, media generation, and growth.

Comment installer 11agents Cloud MCP ?

Il fonctionne comme serveur distant. Dans Claude Code : claude mcp add --transport http 11agents-cloud-mcp 'https://app.11agents.ai/mcp' --header 'Authorization: <11agents project token, sent as a Bearer token.>'. Pour les autres clients, collez la configuration JSON de cette page dans leurs réglages MCP.

Faut-il une clé API pour 11agents Cloud MCP ?

Oui. Il attend Authorization, à renseigner dans sa configuration.

11agents Cloud MCP est-il open source ?

Oui. Son code est sur GitHub sous licence MIT.

Qui maintient 11agents Cloud MCP ?

Il est publié par 11Agents. AI.tn le référence sans le maintenir ni le recommander.

Issu du registre MCP officiel. Être listé n'est pas une recommandation : vérifiez le code et les permissions d'un serveur avant de lui donner accès à vos données.