Fibery MCP Server
Official## Deprecated
This local MCP server is **deprecated**. We support **Remote MCP Server** now, which can be connected via this url: **https://mcp.fibery.io/mcp**.
See the [Fibery MCP Server guide](https://the.fibery.io/@public/User_Guide/Guide/Fibery-MCP-Server-401) for setup instructions.
This repository will no longer receive feature updates. Please migrate to the remote server.
## Installation
If you still want to use this server...
### Installing via Smithery
To install Fibery MCP Server for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@Fibery-inc/fibery-mcp-server):
```bash
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](https://github.com/astral-sh/uv)
#### Installation Steps:
1. Install the tool using uv:
```bash
uv tool install fibery-mcp-server
```
2. Then, add this configuration to your MCP client config file. In Claude Desktop, you can access the config in **Settings → Developer → Edit Config**:
```json
{
"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:**
```json
{
"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"
]
}
}
}
```
TDQS
Scored across 7 tools
Most tools have distinct purposes (create, list, describe, query, update), but create_entity and create_entities_batch have significant overlap—both create entities, differing only in batch capability. The current_date tool stands out as a utility that doesn't clearly align with the Fibery domain, potentially causing confusion about its role in the set.
The naming follows a consistent verb_noun pattern (e.g., create_entity, list_databases, query_database) with clear, descriptive names. The only minor deviation is current_date, which uses a noun_noun pattern instead of a verb, slightly breaking the convention but remaining readable.
With 7 tools, the count is reasonable for a Fibery integration, covering core operations like creation, listing, querying, and updating. It's slightly lean but functional, as it includes essential CRUD-like actions and schema exploration tools, though it might benefit from a delete tool for full lifecycle coverage.
The toolset covers key operations for interacting with Fibery databases, including creation, querying, and updating, with tools for schema exploration. However, there are notable gaps: no delete_entity tool limits full CRUD coverage, and the current_date utility feels out of place without clear integration into the domain, potentially leaving agents unable to perform complete entity management workflows.