meetalfred-mcp
MCP server for MeetAlfred LinkedIn automation, enabling campaign monitoring, lead management, reply tracking, messaging, tag management, campaign CRUD, and social post scheduling.
README
meetalfred-mcp
<!-- mcp-name: io.github.cphoskins/meetalfred-mcp -->
MCP server for MeetAlfred — LinkedIn automation campaign monitoring, lead management, reply tracking, messaging, tag management, campaign CRUD, and social post scheduling.
Features
- Campaign monitoring — list, filter, pause/resume, rename, clone, archive campaigns
- Lead management — fetch leads, add to campaigns, tag, exclude, return to campaign
- Reply tracking — pull replies, view conversation threads, send messages
- Tag management — full CRUD on tags (create, list, update, delete)
- Lead tagging — add/set tags on individual leads or in bulk
- Social post scheduling — create, update, reschedule, archive, and delete LinkedIn posts
- Activity feed — review recent account actions across all channels
- Notifications — check unread count
- Team visibility — list team members and their connections
- User profile — get current authenticated user info
- White-label support — configurable base URLs for custom instances
Dual API Architecture
This server uses two MeetAlfred API layers:
| Layer | Auth | Required | Capabilities |
|---|---|---|---|
| Webhook API | MEETALFRED_API_KEY |
Yes | Campaigns, leads, replies, connections, activity (read-heavy) |
| Internal API | MEETALFRED_JWT_TOKEN |
No | Tags CRUD, campaign management, messaging, lead ops, post scheduling, notifications |
The webhook API provides core read operations. The internal API (optional) enables full CRUD, messaging, and richer data. Both work simultaneously.
Installation
pip install meetalfred-mcp
Or install from source:
git clone https://github.com/cphoskins/meetalfred-mcp.git
cd meetalfred-mcp
pip install -e .
Configuration
Get your API key
- Log in to MeetAlfred
- Go to Settings > Integrations > Webhooks
- Generate an API key
Get your JWT token (optional, for internal API)
- Log in to MeetAlfred in your browser
- Open DevTools > Application > Cookies
- Copy the
tokencookie value
Claude Code
Add to your .claude/settings.json or project .mcp.json:
{
"mcpServers": {
"meetalfred": {
"command": "meetalfred-mcp",
"env": {
"MEETALFRED_API_KEY": "your-api-key-here",
"MEETALFRED_JWT_TOKEN": "your-jwt-token-here"
}
}
}
}
White-label instances
If you're using a white-label MeetAlfred instance, set the base URLs:
{
"mcpServers": {
"meetalfred": {
"command": "meetalfred-mcp",
"env": {
"MEETALFRED_API_KEY": "your-api-key-here",
"MEETALFRED_JWT_TOKEN": "your-jwt-token-here",
"MEETALFRED_BASE_URL": "https://api.your-instance.com/api/integrations/webhook",
"MEETALFRED_API_BASE_URL": "https://api.your-instance.com/api/v1"
}
}
}
}
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"meetalfred": {
"command": "python",
"args": ["-m", "meetalfred_mcp.server"],
"env": {
"MEETALFRED_API_KEY": "your-api-key-here",
"MEETALFRED_JWT_TOKEN": "your-jwt-token-here"
}
}
}
}
Tools
Webhook API (requires MEETALFRED_API_KEY)
| Tool | Description |
|---|---|
get_campaigns |
List campaigns by type (active, draft, archived, all) |
get_leads |
Fetch leads with campaign and person details |
add_lead |
Add a new lead to a campaign (LinkedIn URL required) |
get_replies |
Get reply messages from leads across campaigns |
get_connections |
Get LinkedIn connections with full profile data |
get_team_members |
List team members (requires team owner access) |
get_member_connections |
Get connections across team members |
get_last_actions |
Get recent activity by type (invites, accepted, messages, replies, etc.) |
Internal API — Tags (requires MEETALFRED_JWT_TOKEN)
| Tool | Description |
|---|---|
get_all_tags |
Get all tags (no pagination) |
list_tags |
List tags with pagination and sorting |
create_tag |
Create a new tag |
update_tag |
Rename an existing tag |
delete_tag |
Delete a tag |
Internal API — Campaigns (requires MEETALFRED_JWT_TOKEN)
| Tool | Description |
|---|---|
list_campaigns_detailed |
List campaigns with full details, stats, and filtering |
get_campaign |
Get full details of a single campaign |
get_campaign_counts |
Get campaign counts by status |
get_campaigns_grouped |
Get all campaigns grouped by category |
update_campaign |
Update campaign fields (name, status) |
delete_campaign |
Delete a campaign |
pause_campaign |
Pause a running campaign |
resume_campaign |
Resume a paused campaign |
rename_campaign |
Rename a campaign |
clone_campaign |
Clone (duplicate) a campaign |
archive_campaign |
Archive a campaign |
Internal API — Messaging (requires MEETALFRED_JWT_TOKEN)
| Tool | Description |
|---|---|
list_replies_detailed |
List replies with full details and sorting |
get_conversation_messages |
Get messages in a conversation thread |
send_message |
Send a message in a conversation (reply to a lead) |
Internal API — Lead Management (requires MEETALFRED_JWT_TOKEN)
| Tool | Description |
|---|---|
get_campaign_leads |
List leads in a campaign with status filtering |
get_lead_statuses |
Get lead status counts for a campaign |
return_lead_to_campaign |
Return leads to a campaign sequence |
add_tags_to_leads |
Add tags to one or more leads |
exclude_leads |
Exclude or un-exclude leads from campaigns |
Internal API — Posts / Social Publishing (requires MEETALFRED_JWT_TOKEN)
| Tool | Description |
|---|---|
list_posts |
List scheduled and published posts with engagement stats |
get_post_types |
Get post counts by platform (LinkedIn, Facebook, Instagram, Twitter) |
get_post |
Get full details of a single post (content, status, schedule, audience) |
create_post |
Create a new scheduled LinkedIn post (set title, content, time, audience) |
update_post |
Update a pending post's content, title, audience, or schedule |
update_post_time |
Reschedule a pending post to a new time |
archive_post |
Archive a post |
delete_post |
Delete a post |
Internal API — Other (requires MEETALFRED_JWT_TOKEN)
| Tool | Description |
|---|---|
get_current_user |
Get the current authenticated user's profile |
get_unread_notification_count |
Get count of unread notifications |
Environment Variables
| Variable | Required | Description |
|---|---|---|
MEETALFRED_API_KEY |
Yes | API key from Settings > Integrations > Webhooks |
MEETALFRED_JWT_TOKEN |
No | JWT token for internal API (enables tags, campaign CRUD, messaging, post scheduling) |
MEETALFRED_BASE_URL |
No | Override webhook API base URL for white-label instances |
MEETALFRED_API_BASE_URL |
No | Override internal API base URL for white-label instances |
Common Workflows
Reply to a lead
1. list_replies_detailed() → find reply with conversationUrn
2. get_conversation_messages(conversationUrn) → read conversation history
3. send_message(conversationUrn, "Your reply text")
Return a lead to a campaign
1. get_campaign_leads(campaignId, "replied") → find lead entityUrn
2. return_lead_to_campaign([entityUrn], campaignId)
Schedule a LinkedIn post
1. create_post(title="Internal label", content="Post body text", scheduled_at="2026-03-15T14:00:00.000Z")
2. list_posts() → verify post was created, get post ID
3. update_post_time(postId, "2026-03-16T15:00:00.000Z") → reschedule if needed
Tag leads from a campaign
1. get_all_tags() → find or create tag IDs
2. get_campaign_leads(campaignId) → get entity URNs
3. add_tags_to_leads([entityUrns], [tagIds])
Development
git clone https://github.com/cphoskins/meetalfred-mcp.git
cd meetalfred-mcp
pip install -e ".[dev]"
pytest tests/
License
MIT
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。