Fibery Integration MCP Server

Customer Data PlatformsPython

Interact with your Fibery workspace using natural language

Available Tools

list_databases

Retrieves a list of all databases available in your Fibery workspace

describe_database

Provides a detailed breakdown of a specific database's structure, showing all fields with their titles, names, and types

query_database

Offers powerful, flexible access to your Fibery data through the Fibery API

create_entity

Creates new entities in your Fibery workspace with specified field values

create_entities_batch

Creates multiple new entities in your Fibery workspace with specified field values

update_entity

Updates existing entities in your Fibery workspace with new field values

The Fibery Integration provides a seamless connection between your Fibery workspace and AI assistants supporting the Model Context Protocol. This integration enables you to query, create, and update Fibery entities through natural language conversations, making it easier to manage your workspace data without switching contexts. With this integration, you can retrieve information about your Fibery databases and their fields, run complex queries against your data, and create or update entities - all through conversational interfaces. This powerful toolset bridges the gap between your knowledge management system and AI assistants, enhancing productivity and streamlining workflows.

Overview

The Fibery Integration allows you to interact with your Fibery workspace directly through AI assistants that support the Model Context Protocol (MCP). This integration enables natural language interactions with your Fibery data, making it easier to query information, create new entities, and update existing ones without leaving your conversation with the AI.

Prerequisites

Before installing the Fibery Integration, you'll need:

A Fibery account with an API token
Python 3.10 or higher
An MCP-compatible client (such as Claude Desktop)

Installation Options

Option 1: Install via Smithery (Recommended)

The easiest way to install the Fibery Integration is through Smithery:

npx -y @smithery/cli install @Fibery-inc/fibery-mcp-server --client claude

This command automatically configures the integration for Claude Desktop.

Option 2: Install via UV

Install the UV package manager if you haven't already
Install the Fibery Integration using UV:

uv tool install fibery-mcp-server

Configure your MCP client by adding the appropriate configuration to your client's settings

Configuration

To configure the Fibery Integration, you'll need to provide:

Your Fibery domain (e.g., your-domain.fibery.io)
Your Fibery API token

For Claude Desktop, access the configuration in Settings → Developer → Edit Config and add the following:

{
    "mcpServers": {
        "fibery-mcp-server": {
            "command": "uv",
            "args": [
                "tool",
                "run",
                "fibery-mcp-server",
                "--fibery-host",
                "your-domain.fibery.io",
                "--fibery-api-token",
                "your-api-token"
            ]
        }
    }
}

Note: If the "uv" command doesn't work, try using the absolute path (e.g., /Users/username/.local/bin/uv).

Usage Examples

Once installed, you can interact with your Fibery workspace using natural language. Here are some example prompts:

"Show me all the databases in my Fibery workspace"
"Describe the structure of the Projects database"
"Find all tasks assigned to me that are due this week"
"Create a new task in the Tasks database with high priority"
"Update the status of project XYZ to 'In Progress'"

The integration will interpret these requests and use the appropriate tools to interact with your Fibery workspace.

Troubleshooting

If you encounter issues with the integration:

Verify your Fibery API token is valid and has the necessary permissions
Check that your Fibery domain is correctly specified
Ensure you're using Python 3.10 or higher
Verify the MCP client configuration is correct

For development or debugging purposes, you can use the following configuration:

{
    "mcpServers": {
        "fibery-mcp-server": {
            "command": "uv",
            "args": [
                "--directory",
                "path/to/cloned/fibery-mcp-server",
                "run",
                "fibery-mcp-server",
                "--fibery-host",
                "your-domain.fibery.io",
                "--fibery-api-token",
                "your-api-token"
            ]
        }
    }
}