Fibery
About
Provides a flexible integration with the Fibery API, enabling querying, creating, and updating entities across collaborative work tracking platforms through standardized tools.
Details
- Author
- fibery-inc
- Repository
- Fibery-inc/fibery-mcp-server
- GitHub stars
- 26
- Downloads
- 1,938
- License
- MIT License
- Categories
- Productivity, Database, Project Management, Automation, Developer Tools, Design, Workplace, AI, Search, API, Infrastructure, Other
- Tags
- #integration
Jump to
- Deprecated; use the remote server at https://mcp.fibery.io/mcp.
- Installed via uv or Smitherly.
- Requires Python 3.10 or higher.
- Connects to a Fibery account using an API token.
- Provides a local MCP server for AI assistants.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
FiberyCommand (node, npx, python, etc.)uvArguments-
Argument 1
tool -
Argument 2
run -
Argument 3
fibery-mcp-server -
Argument 4
--fibery-host -
Argument 5
your-domain.fibery.io -
Argument 6
--fibery-api-token -
Argument 7
your-api-token
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
If you still want to use this server...
To install Fibery MCP Server for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @Fibery-inc/fibery-mcp-server --client claude
1. Install the tool using uv:
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:
{
"mcpServers": {
"fibery-mcp-server": {
"command": "uv",
"args": [
"tool",
"run",
"fibery-mcp-server",
"--fibery-host",
"your-domain.fibery.io",
"--fibery-api-token",
"your-api-token"
]
}
}
}
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"fibery": {
"cwd": "",
"env": {},
"args": [
"tool",
"run",
"fibery-mcp-server",
"--fibery-host",
"your-domain.fibery.io",
"--fibery-api-token",
"your-api-token"
],
"shell": false,
"command": "uv"
}
}
}Linux
{
"cwd": "",
"env": [],
"args": [
"tool",
"run",
"fibery-mcp-server",
"--fibery-host",
"your-domain.fibery.io",
"--fibery-api-token",
"your-api-token"
],
"shell": false,
"command": "uv"
}Macos
{
"cwd": "",
"env": [],
"args": [
"tool",
"run",
"fibery-mcp-server",
"--fibery-host",
"your-domain.fibery.io",
"--fibery-api-token",
"your-api-token"
],
"shell": false,
"command": "uv"
}Windows
{
"cwd": "",
"env": [],
"args": [
"tool",
"run",
"fibery-mcp-server",
"--fibery-host",
"your-domain.fibery.io",
"--fibery-api-token",
"your-api-token"
],
"shell": false,
"command": "uv"
}- Query entities across your Fibery workspace— usefibery_graphqlto run GraphQL queries and retrieve entities, fields, and relationships.
- List available types and their fields— callschema_queryto discover database types, field names, and type structures.
- Execute arbitrary GraphQL operations— send any supported Fibery GraphQL query or mutation via thefibery_graphqltool.
- Run raw SQL-like commands— usefibery_commandto perform bulk updates, create entities, or run other server-side commands.
This local MCP server isdeprecated. We supportRemote MCP Servernow, which can be connected via this url:https://mcp.fibery.io/mcp.
See theFibery MCP Server guidefor setup instructions.
This repository will no longer receive feature updates. Please migrate to the remote server.
To install Fibery MCP Server for Claude Desktop automatically viaSmithery:
npx -y @smithery/cli install @Fibery-inc/fibery-mcp-server --client claude
- A Fibery account with an API token
- Python 3.10 or higher
- uv
- Then, add this configuration to your MCP client config file. In Claude Desktop, you can access the config inSettings → 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)
{ "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" ] } } }
MCP-native open-source Notion alternative: read and write pages, customizable databases, and kanban/calendar boards over a remote MCP server (OAuth 2.1 + PKCE, scoped tokens, audit log).
Keep teams & agents coordinated automatically
Connect to the Taskade platform via MCP. Access tasks, projects, workflows, and AI agents in real-time through a unified workspace and API.
A universal remote MCP server that connects to popular productivity tools such as Notion, Monday, AirTable, and many more.
advanced-math-mcp — MCP server for linear algebra, calculus, and symbolic math. 17 tools with a unified evaluate() expression engine. Supports matrices, eigenvalues, SVD, integrals, limits, derivatives, and more.
An MCP interface for Atlassian products, including Jira and Bitbucket.
The Outcome Backcasting MCP is a strategic planning tool that helps you work backwards from a desired future outcome to identify the specific steps, resources, and dependencies needed to achieve your goals. Unlike traditional forward planning, backcasting starts with your end goal and creates a reverse roadmap to get there.
About A repo-native task graph as plain Markdown files, served to AI agents over MCP and to humans over a clean web UI .
Integrate ClickUp with AI applications to manage tasks, spaces, lists, and folders.
Interact with the ClickUp API to manage tasks, lists, and spaces, automating project planning and workflows.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
