Linkd MCP Server
# Linkd MCP Server
This is an unofficial Model Context Protocol (MCP) Server for Linkd..
More information about automcp can be found at [automcp.app](https://automcp.app).
For detailed API documentation and usage examples, visit the [official Linkd documentation](https://docs.linkd.inc/).
More information about the Model Context Protocol can be found [here](https://modelcontextprotocol.io/introduction).
## Table of Contents
- [Installation](#installation)
- [Usage](#usage)
- [Tools](#tools)
- [Configuration](#configuration)
- [License](#license)
## Installation
### Manual Installation
To install the server, run:
```bash
npx linkd-mcp <YOUR-LINKD-API-KEY>
```
## Running on Cursor
Add to `~/.cursor/mcp.json` like this:
```json
{
"mcpServers": {
"linkd": {
"command": "npx",
"args": ["-y", "linkd-mcp"],
"env": {
"LINKD_API_KEY": "YOUR-API-KEY"
}
}
}
}
```
## Running on Windsurf
Add to your `./codeium/windsurf/model_config.json` like this:
```json
{
"mcpServers": {
"linkd": {
"command": "npx",
"args": ["-y", "linkd-mcp"],
"env": {
"LINKD_API_KEY": "YOUR-API-KEY"
}
}
}
}
```
## Claude Desktop app
This is an example config for the Linkd MCP server for the Claude Desktop client.
```json
{
"mcpServers": {
"linkd": {
"command": "npx",
"args": ["--yes", "linkd-mcp"],
"env": {
"LINKD_API_KEY": "your-api-key"
}
}
}
}
```
## Tools
* `search_for_users` - Search for LinkedIn users with filters like query, school, and match threshold
* `search_for_companies` - Search for companies on Linkd using filters like query and match threshold
* `enrich_linkedin` - Retrieves detailed profile information for a specific LinkedIn URL (1 credit per lookup)
* `retrieve_contacts` - Retrieves email addresses and phone numbers for a LinkedIn profile (1 credit per lookup)
* `scrape_linkedin` - Retrieves detailed profile data and posts with comments from a LinkedIn profile URL (2 credits per request)
* `research_profile` - Research a profile using email or phone number
* `initiate_deep_research` - Start a deep research job for comprehensive LinkedIn data gathering
* `check_deep_research_status` - Check the status of an ongoing deep research job
## License
This project is licensed under the MIT License.
TDQS
Scored across 7 tools
Most tools have distinct purposes, but 'enrich_linkedin' and 'scrape_linkedin' could be confused as both retrieve detailed profile information. The descriptions clarify that 'scrape_linkedin' includes posts and comments, while 'enrich_linkedin' is more basic, but the overlap in core functionality might cause misselection.
Tool names follow a consistent snake_case pattern with clear verb_noun structures, such as 'check_deep_research_status' and 'search_for_users'. Minor deviations exist, like 'enrich_linkedin' using a verb without an explicit object, but overall the naming is predictable and readable.
With 7 tools, the count is well-scoped for a LinkedIn-focused server, covering key operations like profile retrieval, research, and searches. Each tool appears to earn its place without being excessive or insufficient for the domain.
The toolset provides good coverage for LinkedIn operations, including profile enrichment, contact retrieval, and searches for users and companies. Minor gaps exist, such as no explicit update or delete tools, but these are less critical in a data retrieval context, and agents can likely work around them.