Fibery MCP Server

What is Fibery MCP Server about?

Fibery MCP Server bridges a Fibery workspace with large language models that support the Model Context Protocol, allowing users to ask questions, retrieve data, and modify entities in plain language.

How to use Fibery MCP Server?

Install the server (e.g., via uv tool install fibery-mcp-server).
Configure the MCP client (Claude Desktop, etc.) with the command and arguments that include your Fibery host and API token.
Run the server; the client will communicate through the defined MCP endpoint.
Invoke the provided tools—list databases, describe a database, query, create, or update entities—through natural‑language prompts.

Key features of Fibery MCP Server

List all databases in a Fibery workspace.
Describe the schema of a specific database (fields, titles, types).
Perform flexible queries against Fibery data.
Create single or multiple new entities with specified field values.
Update existing entities.

Use cases of Fibery MCP Server

Rapid data exploration: Ask an LLM to fetch records or summarize information without writing API calls.
Conversational UI for workflows: Enable non‑technical team members to add or modify items using chat interfaces.
Automation scripts: Trigger entity creation or updates from other tools via natural‑language instructions.
Documentation assistance: Generate overviews of databases and their relationships on demand.

FAQ from the Fibery MCP Server

What LLM providers are supported? Any provider that implements the MCP protocol (e.g., Claude for Desktop).
Do I need a Python environment? Yes, Python 3.10+ and uv are required for installation.
How is authentication handled? Provide your Fibery API token in the MCP client configuration.
Can I run the server locally for development? Yes, clone the repo and configure the args in the client to use --directory pointing to the local path.
Is there a Node.js installation method? Currently the server is distributed as a Python tool; a Node.js wrapper is not provided.

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