MCP Servers Overview
How FlowTrux uses Model Context Protocol servers to connect AI agents with external tools
MCP (Model Context Protocol) is a standardized way for AI models to discover and use external tools. In FlowTrux, MCP servers give your workflows access to tools like Slack messaging, Google Sheets, file storage, fleet telematics, and more.
How It Works
Each MCP server exposes a set of tools with well-defined parameters. Your workflows use them in two ways:
- Agent nodes - you attach tools to an agent, and the AI model decides when to call them and with what parameters while working on its task.
- Action nodes - you call one specific tool directly with parameters you define (including template variables from previous steps).
Tool results flow back into the workflow like any other node output, so you can reference them from later steps.
Built-in Servers
FlowTrux includes the following built-in MCP servers:
| Server | Description | Documentation |
|---|---|---|
| Slack | Send messages, manage channels, upload files | Slack |
| Telegram | Send messages and documents via Telegram Bot | Telegram |
| Google Workspace | Sheets, Gmail, Calendar, Drive | Google Workspace |
| Stocks | Financial market data (Polygon.io, Finnhub) | Stocks |
| Files | Organization file storage | Files |
| SSH | Remote server command execution and file transfer | SSH |
| Twilio | SMS, voice calls, WhatsApp messaging | Twilio |
| YouTrack | JetBrains YouTrack issue tracking | YouTrack |
| PDF document generation (markdown, reports, tables) | PDF Generator | |
| Notion | Pages, databases, blocks, comments | Notion |
| GitHub | Issues, PRs, repos, Actions workflows | GitHub |
| Jira | Issues, projects, sprints, transitions | Jira |
| Wialon | Telematics: units, messages, geofences, reports, drivers | Wialon |
External Servers
You can also connect remote MCP-compatible servers by URL, when available in your deployment. See External Servers for details.
Setup
1. Add an MCP Server
- Navigate to Settings > MCP Servers (requires OWNER or ADMIN role).
- Click Add Server.
- Choose a built-in server type, or External for a remote server.
- Enter the required configuration (API keys, tokens, etc.).
- Click Save.
MCP server configurations belong to your organization. You can create several configurations of the same server under different names - for example, two Slack configs with different bot tokens, each assigned to a different workspace.
All credentials are encrypted before being stored.
2. Assign to a Workspace
MCP servers are not automatically available in all workspaces:
- Go to Settings > Workspaces.
- Click Edit on the target workspace.
- Under MCP Servers, select which servers this workspace can use.
- Click Save.
3. Use in a Workflow
Once assigned to a workspace, MCP tools become available in:
- Agent nodes - Add tools in the Inspector panel so the AI can call them.
- Action nodes - Select "MCP" as the action type to call a specific tool directly.
Security
- Credentials are encrypted at rest and are never passed through the AI model.
- Data is scoped to your organization and workspace - servers can only access resources belonging to the organization and workspace they are configured for.
Plan Limits
Your organization's plan may limit the number of MCP server configurations. Check Settings > Plan & Usage to see your current limits.