Appmixer MCP
Enables LLMs to automate workflows and interact with SaaS products and APIs through Appmixer's integration platform. It provides tools for managing automation flows and dynamically exposes custom tools via an MCP Gateway.
README
Appmixer MCP
A Model Context Protocol (MCP) server that provides LLMs with agentic workflow automation capabilities using Appmixer. This server enables LLMs to interact with other MCP servers configured via Appmixer or with custom built workflows that use 3rd party SaaS products, APIs or other utilities.
Requirements
- Node.js 20 or newer
- VS Code, Cursor, Windsurf, Claude Desktop or any other MCP client
Getting started
First, install the Appmixer MCP server with your client. A typical configuration looks like this:
{
"mcpServers": {
"appmixer-mcp": {
"command": "npx",
"args": [
"appmixer-mcp"
],
"env": {
"APPMIXER_BASE_URL": "<your-appmixer-tenant-api-base-url>",
"APPMIXER_ACCESS_TOKEN": "<your-appmixer-access-token>",
"APPMIXER_USERNAME": "<optional-appmixer-username>",
"APPMIXER_PASSWORD": "<optional-appmixer-password>"
}
}
}
}
<details> <summary><b>Install in Claude Desktop</b></summary>
Follow the MCP install guide, use following configuration:
{
"mcpServers": {
"appmixer-mcp": {
"command": "npx",
"args": [
"appmixer-mcp"
],
"env": {
"APPMIXER_BASE_URL": "<your-appmixer-tenant-api-base-url>",
"APPMIXER_ACCESS_TOKEN": "<your-appmixer-access-token>",
"APPMIXER_USERNAME": "<optional-appmixer-username>",
"APPMIXER_PASSWORD": "<optional-appmixer-password>"
}
}
}
}
</details>
<details> <summary><b>Install in Windsurf</b></summary>
Follow Windsuff MCP documentation. Use following configuration:
{
"mcpServers": {
"appmixer-mcp": {
"command": "npx",
"args": [
"appmixer-mcp"
],
"env": {
"APPMIXER_BASE_URL": "<your-appmixer-tenant-api-base-url>",
"APPMIXER_ACCESS_TOKEN": "<your-appmixer-access-token>",
"APPMIXER_USERNAME": "<optional-appmixer-username>",
"APPMIXER_PASSWORD": "<optional-appmixer-password>"
}
}
}
}
</details>
<details><summary><b>Install in VS Code</b></summary>
You can also install the Appmixer MCP server using the VS Code CLI:
# For VS Code
code --add-mcp '{"name":"appmixer-mcp","command":"npx","args":["appmixer-mcp","env":{"APPMIXER_BASE_URL":"","APPMIXER_ACCESS_TOKEN":""}]}'
After installation, the Appmixer MCP server will be available for use with your GitHub Copilot agent in VS Code. </details>
<details> <summary><b>Install in Cursor</b></summary>
Go to Cursor Settings -> MCP -> Add new MCP Server. Name to your liking, use command type with the command npx appmixer-mcp. You can also verify config or add command like arguments via clicking Edit.
{
"mcpServers": {
"appmixer-mcp": {
"command": "npx",
"args": [
"appmixer-mcp"
],
"env": {
"APPMIXER_BASE_URL": "<your-appmixer-tenant-api-base-url>",
"APPMIXER_ACCESS_TOKEN": "<your-appmixer-access-token>"
}
}
}
}
</details>
<details> <summary><b>Install in Claude Code</b></summary>
Use the Claude Code CLI to add the Appmixer MCP server:
claude mcp add appmixer-mcp npx appmixer-mcp -e APPMIXER_BASE_URL="" -e APPMIXER_ACCESS_TOKEN=""
</details>
Configuration
Appmixer MCP server supports following environment variables:
| Name | Description |
|---|---|
| APPMIXER_BASE_URL | Your Appmixer tenant API url. For example: https://api.YOUR_TENANT.appmixer.cloud |
| APPMIXER_ACCESS_TOKEN | Your Appmixer access token. See Authentication section below for more info. |
| APPMIXER_USERNAME | Your Appmixer username. See Authentication section below for more info. |
| APPMIXER_PASSWORD | Your Appmixer password. See Authentication section below for more info. |
| TOOLS | Set to api,mcpgateway by default meaning both the Appmixer API tools such as "get-flows" and "MCP Gateway" entry points are enabled. |
Authentication
You can either set the APPMIXER_ACCESS_TOKEN environment variable or use your APPMIXER_USERNAME and APPMIXER_PASSWORD credentials directly. Note that the former is way more secure. However, note that there's an expiration time on your access token in Appmixer (consult your Appmixer admin to see what the system setting GRIDD_JWT_TOKEN_EXP is set to (by default 30d)).
Tools
API Tools
- get-flows
- Parameters:
pattern(string): Pattern to filter flows by name.
- get-flow
- Parameters:
id(string): Flow ID
- Parameters:
- delete-flow
- Parameters:
id(string): Flow ID
- Parameters:
- start-flow
- Parameters:
id(string): Flow ID
- Parameters:
- stop-flow
- Parameters:
id(string): Flow ID
- Parameters:
- trigger-component
- Parameters:
id(string): Flow IDcomponentId(string): Component IDmethod(string): HTTP methodbody(string): JSON string that will be sent as the body of the HTTP call to the component.
- Parameters:
- send-app-event
- Parameters:
event(string): App Event namedata(string): JSON string that will be sent as the event data.
- Parameters:
- get-flow-logs
- Parameters:
id(string): Flow IDquery(string): Apache Lucene Query Parser Syntax to filter the logs based on a search criteria.
- Parameters:
MCP Gateway Tools
Every time you use the "MCP Gateway" component from the "MCP Tools" category in any of your running flows, the Appmixer MCP server automatically detects the tools connected to this component and lists those. Note that the server is able to detect the changes dynamically meaning just by starting/stopping your Appmixer flows that include the "MCP Gateway" component, you change the list of available tools.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
E2B
Using MCP to run code via e2b.