Fibery MCP Server

What is Fibery MCP Server about?

Provides a bridge between a Fibery workspace and any LLM provider that supports the Model Context Protocol, allowing users to interact with Fibery data through conversational interfaces.

How to use Fibery MCP Server?

Install – use Smithery (npx -y @smithery/cli install @Fibery-inc/fibery-mcp-server --client claude) or install the Python tool with uv (uv tool install fibery-mcp-server).
Configure – add a server entry to the MCP client config (e.g., Claude Desktop) that points to the installed executable and passes the Fibery host and API token.
Run – launch the LLM client; the server will expose tools such as list_databases, describe_database, query_database, create_entity, create_entities_batch, and update_entity.

Key Features

List all databases in a Fibery workspace.
Describe the schema of a specific database (field titles, names, types).
Query database content with flexible filters via the Fibery API.
Create single or batch entities with custom field values.
Update existing entities.
Works with any MCP‑compatible LLM (e.g., Claude for Desktop).

Use Cases

Rapid data retrieval: Ask an LLM “What projects are overdue?” and receive up‑to‑date records.
Conversational data entry: Create new tasks or contacts by describing them in plain language.
Bulk imports: Insert many entities from a spreadsheet via the batch creation tool.
Schema exploration: Quickly understand the structure of a newly onboarded Fibery workspace.
Automation scripts: Combine with other MCP tools to build end‑to‑end workflows.

FAQ

Q: Do I need a Fibery account? A: Yes, a Fibery workspace with an API token is required.

Q: Which LLM clients are supported? A: Any client that implements the MCP protocol, such as Claude for Desktop.

Q: Is Python required? A: The server runs as a Python tool (Python 3.10+). Installation via uv handles the environment automatically.

Q: Can I run the server locally? A: Absolutely. The command in the MCP config launches the server on your machine.

Q: How are credentials handled? A: Provide the API token either as a command‑line argument or via an environment variable in the config.

This MCP (Model Context Protocol) server provides integration between Fibery and any LLM provider supporting the MCP protocol (e.g., Claude for Desktop), allowing you to interact with your Fibery workspace using natural language.

✨ Features

Query Fibery entities using natural language
Get information about your Fibery databases and their fields
Create and update Fibery entities through conversational interfaces

📦 Installation

Installing via Smithery

To install Fibery MCP Server for Claude Desktop automatically via Smithery:

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

Installing via UV

Pre-requisites:

A Fibery account with an API token
Python 3.10 or higher
uv

Installation Steps:

Install the tool using uv:

uv tool install fibery-mcp-server

Then, add this configuration to your MCP client config file. In Claude Desktop, you can access the config in Settings → Developer → Edit Config:

{
    "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 "uv" command does not work, try absolute path (i.e. /Users/username/.local/bin/uv)

For Development:

{
    "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"
            ]
        }
    }
}

🚀 Available Tools

1. List Databases (`list_databases`)

Retrieves a list of all databases available in your Fibery workspace.

2. Describe Database (`describe_database`)

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

3. Query Database (`query_database`)

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

4. Create Entity (`create_entity`)

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

5. Create Entities (`create_entities_batch`)

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

6. Update Entity (`update_entity`)

Updates existing entities in your Fibery workspace with new field values.

Fibery MCP Server