@b2b-saas-inc/olli-mcp-server

@b2b-saas-inc/olli-mcp-server

Lets LLMs manage social media presence via olli.social API, with tools for campaigns, drafts, analytics, and more.

Category
访问服务器

README

@b2b-saas-inc/olli-mcp-server

MCP server for olli.social — lets LLMs manage your social presence via API key.

Installation

Add to your Claude Desktop (or other MCP client) config:

{
  "mcpServers": {
    "olli": {
      "command": "npx",
      "args": ["-y", "@b2b-saas-inc/olli-mcp-server"],
      "env": {
        "OLLI_API_KEY": "olli_sk_your_key_here"
      }
    }
  }
}

Generate an API key in your olli.social profile settings under API Keys.

Configuration

Variable Required Default
OLLI_API_KEY Yes —
OLLI_BASE_URL No https://api.olli.social/v1

Tools (68)

Category Tools
Workspaces list_workspaces, get_workspace, update_workspace, list_memberships, update_membership, remove_membership, list_invitations, create_invitation, delete_invitation, get_feature_flags, get_plan_features
Campaigns list_campaigns, get_campaign, create_campaign, update_campaign, delete_campaign
Drafts list_drafts, get_draft, create_draft, update_draft, delete_draft, publish_draft, schedule_draft
Calendar list_calendar_events, get_calendar_event, create_calendar_event, update_calendar_event, delete_calendar_event
Assets list_assets, get_asset, create_asset, delete_asset
ICPs list_icps, create_icp, update_icp, delete_icp
Industries list_industries, create_industry, update_industry, delete_industry
Products list_products, create_product, update_product, delete_product
Teams list_teams, get_team, create_team, update_team, delete_team, list_team_members, add_team_member, remove_team_member
AI generate_post, improve_content, create_variations, suggest_hashtags, analyze_content, get_ai_usage, campaign_generate, avatar_chat, list_avatar_conversations, get_avatar_conversation
Analytics get_analytics
Amplification list_amplification_posts, get_amplification_post, create_amplification_post, delete_amplification_post
Leaderboard get_leaderboard
Integrations list_integrations, get_linkedin_organizations, select_linkedin_organization, sync_linkedin, get_linkedin_analytics, disconnect_integration
Notifications list_notifications, mark_notification_read, mark_all_notifications_read, delete_notification
Support list_support_tickets, get_support_ticket, create_support_ticket, list_ticket_messages, reply_to_ticket
Billing get_billing, list_invoices

All workspace-scoped tools require a workspace_id (slug or UUID, e.g. "olli-demo").

Development

npm install
OLLI_API_KEY=olli_sk_... npm run dev
npm run build

License

MIT

Schema Sync

Avatar tool schemas are sourced from olli-social-app's AvatarToolRegistry — the single source of truth for all 34 avatar AI tool definitions. Instead of maintaining duplicate schemas in TypeScript, this MCP server imports them as JSON.

How it works

  1. The Rails app exposes GET /api/v1/ai/avatar_schemas (protected by shared secret)
  2. Running npm run sync-schemas fetches the schemas and writes them to src/generated/avatar-schemas.json
  3. At startup, the MCP server reads this JSON file and dynamically registers avatar tools
  4. Each avatar tool proxies execution back to the Rails avatar endpoint

Setup

Add these variables to your .env file:

MCP_RAILS_URL=https://api.olli.social
MCP_SHARED_SECRET=your_shared_secret_here

MCP_RAILS_URL is the base URL of your olli-social-app Rails server.
MCP_SHARED_SECRET must match the MCP_SHARED_SECRET environment variable on the Rails side.

Syncing schemas

# Pull latest avatar tool schemas from Rails
npm run sync-schemas

The output file src/generated/avatar-schemas.json is committed to the repo for reproducible builds. Re-run the sync whenever avatar tool definitions change in the Rails app (i.e., when AvatarToolRegistry::SCHEMA_VERSION is bumped).

Adding new avatar tools

New avatar tools should be added to AvatarToolRegistry in olli-social-app — never directly in this MCP server. After adding tools in Rails:

  1. Bump SCHEMA_VERSION in avatar_tool_registry.rb
  2. Run npm run sync-schemas in this repo
  3. Commit the updated avatar-schemas.json

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选