You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
[Linked API](https://linkedapi.io/?ref=linkedapi-mcp) MCP server connects your LinkedIn account to AI assistants like Claude, Cursor, and VS Code. Ask them to search for leads, send messages, analyze profiles, and much more – they'll handle it through our cloud browser, safely and automatically.
2
2
3
-
Model Context Protocol (MCP) server for [Linked API](https://linkedapi.io).
3
+
# Use cases
4
+
-**Sales automation assistant**. Ask your AI to find leads, check their profiles, and draft personalized outreach. It can search for "software engineers at companies with 50-200 employees in San Francisco", analyze their backgrounds, and suggest connection messages that actually make sense.
5
+
-**Recruitment assistant**. Let your assistant search for candidates with specific skills, review their experience, and send initial outreach. It handles the time-consuming parts while you focus on actually talking to people.
6
+
-**Conversation assistant**. Your AI can read your existing LinkedIn conversations and help you respond naturally. It understands the context of your chats, suggests relevant replies, and can even send follow-up messages.
7
+
-**Market research assistant**. Need competitor analysis? Your assistant can gather data about companies, their employees, and recent activities. Get insights about industry trends without spending hours on LinkedIn.
4
8
5
-
## Installation
9
+
# Installation
10
+
The MCP server needs tokens to access your LinkedIn account. Here's how to get them:
6
11
7
-
### Get API Tokens
12
+
1. Sign up at [Linked API Platform](https://app.linkedapi.io/?ref=github-mcp).
13
+
2. Choose your plan and complete the purchase.
14
+
3. Connect your LinkedIn account (it takes about 2 minutes).
15
+
4. Copy your tokens from the dashboard:
16
+
-`LINKED_API_TOKEN` – your main token that enables Linked API access.
17
+
-`IDENTIFICATION_TOKEN` – unique token for your LinkedIn account.
18
+
19
+
**Multiple LinkedIn accounts:**
8
20
9
-
1. Sign up at [Linked API](https://app.linkedapi.io?ref=linkedapi-mcp)
10
-
2. Get your **LINKED_API_TOKEN** and **IDENTIFICATION_TOKEN** from the dashboard
21
+
If you have multiple LinkedIn accounts, you'll get a separate identification token for each one, and you can create multiple MCP server instances – one for each account.
11
22
12
-
### Workflow Behavior
23
+
**Handling long-running workflows:**
13
24
14
-
Linked API workflows can take over 5 minutes to complete, which might cause the MCP client to disconnect before the results are ready. To address this, each tool invocation includes a `HEALTH_CHECK_PERIOD`— timeout setting in seconds, defaulting to 60 seconds. Once this period elapses, the MCP server will provide a response instructions for workflow restoration.
25
+
The configuration examples below include a `HEALTH_CHECK_PERIOD` variable. Different applications (Claude, VS Code, Cursor, Windsurf) have different timeout limits for MCP tool calls. Since some LinkedIn workflows can take several minutes to complete, this setting helps the MCP server handle these longer operations correctly – preventing disconnections and ensuring your workflows run to completion.
15
26
16
-
You can find recommended `HEALTH_CHECK_PERIOD` values for different MCP clients in examples below.
27
+
## Claude
17
28
18
-
### Claude Desktop
29
+
Add this to your Claude Desktop configuration file:
@@ -32,9 +46,10 @@ You can find recommended `HEALTH_CHECK_PERIOD` values for different MCP clients
32
46
}
33
47
}
34
48
```
49
+
Restart Claude Desktop after saving the config.
35
50
36
-
###Cursor
37
-
51
+
## Cursor
52
+
Add this configuration to your Cursor settings:
38
53
```json
39
54
{
40
55
"mcpServers": {
@@ -50,63 +65,98 @@ You can find recommended `HEALTH_CHECK_PERIOD` values for different MCP clients
50
65
}
51
66
}
52
67
```
68
+
You can also configure it through the UI: go to Cursor Settings > Tools & Integrations > MCP Tools Section, then click "New MCP Server" and paste the configuration.
53
69
54
-
## Example Usage
55
-
56
-
After setup, you can ask Claude or Cursor:
57
-
58
-
> "Find software engineers at Google in San Francisco"
59
-
60
-
> "Get the profile information for linkedin.com/in/john-doe"
61
-
62
-
> "Send a connection request to this person with a personalized note"
63
-
64
-
65
-
<details>
66
-
<summary><b>Available Tools</b></summary>
67
-
68
-
Standard tools:
69
-
-`fetch_person` - Get LinkedIn profile information with optional experience, education, skills, posts
70
-
-`fetch_company` - Get company information with optional employees, decision makers, posts
71
-
-`fetch_post` - Get post data and engagement metrics
72
-
-`search_people` - Search for people with advanced filtering
73
-
-`search_companies` - Search for companies with advanced filtering
74
-
-`send_message` - Send direct messages to connections
75
-
-`sync_conversation` - Sync conversation for polling
76
-
-`poll_conversations` - Monitor multiple conversations for new messages
77
-
-`send_connection_request` - Send connection requests with optional notes
78
-
-`check_connection_status` - Check connection status with someone
You can also configure it through the UI: go to Windsurf Settings > Advanced Settings > Cascade section, then click "Add Server" and paste the configuration.
107
+
108
+
# Available tools
109
+
The MCP server provides these tools for interacting with LinkedIn:
110
+
111
+
## Standard interface
112
+
|**Tool**|**Description**|
113
+
|:---------|----------:|
114
+
|`fetch_person`| Get person page information with optional experience, education, skills, posts |
115
+
|`fetch_company`| Get company information with optional employees, decision makers, posts |
116
+
|`fetch_post`| Get post information and engagement metrics |
117
+
|`search_people`| Search for people with advanced filtering |
118
+
|`search_companies`| Search for companies with advanced filtering |
119
+
|`send_message`| Send message to person |
120
+
|`sync_conversation`| Sync conversation for polling |
121
+
|`send_connection_request`| Send connection request with optional note |
122
+
|`check_connection_status`| Check connection status with person |
|`get_workflow_result`| Get workflow result by ID |
148
+
149
+
# Usage examples
150
+
With Linked API MCP, you can ask your AI-assistant things like:
151
+
> Find all decision makers at Acme Corp and send them connection requests.
152
+
153
+
> Search for product managers at fintech companies in New York with 50-200 employees.
154
+
155
+
> Tell me about 'https[]()://linkedin.com/in/jane-doe' including their work history and experience.
156
+
157
+
> Send a connection request to 'https[]()://linkedin.com/in/jane-doe' mentioning their recent article about AI in healthcare.
158
+
159
+
> Get all my pending connection requests and withdraw each one of them.
160
+
161
+
These are just basic examples. Since your assistant can execute custom workflows combining multiple actions, the automation potential is truly limitless.
0 commit comments