mirror of
https://github.com/PrefectHQ/fastmcp.git
synced 2026-08-28 10:18:08 +02:00
feat: add fastmcp install goose command (#3040)
This commit is contained in:
Jeremiah Lowin
GitHub
parent
12cb58f220
commit
1bbbee37a6
15 changed files with 787 additions and 26 deletions
|
|
@ -254,6 +254,7 @@
|
|||
"integrations/claude-desktop",
|
||||
"integrations/cursor",
|
||||
"integrations/gemini-cli",
|
||||
"integrations/goose",
|
||||
"integrations/mcp-json-configuration"
|
||||
]
|
||||
},
|
||||
|
|
@ -307,6 +308,7 @@
|
|||
"python-sdk/fastmcp-cli-install-claude_desktop",
|
||||
"python-sdk/fastmcp-cli-install-cursor",
|
||||
"python-sdk/fastmcp-cli-install-gemini_cli",
|
||||
"python-sdk/fastmcp-cli-install-goose",
|
||||
"python-sdk/fastmcp-cli-install-mcp_json",
|
||||
"python-sdk/fastmcp-cli-install-shared"
|
||||
]
|
||||
|
|
|
|||
|
|
@ -5,7 +5,7 @@ description: Connect FastMCP servers to ChatGPT in Chat and Deep Research modes
|
|||
icon: message-smile
|
||||
---
|
||||
|
||||
ChatGPT supports MCP servers through remote HTTP connections in two modes: **Chat mode** for interactive conversations and **Deep Research mode** for comprehensive information retrieval.
|
||||
[ChatGPT](https://chatgpt.com/) supports MCP servers through remote HTTP connections in two modes: **Chat mode** for interactive conversations and **Deep Research mode** for comprehensive information retrieval.
|
||||
|
||||
<Tip>
|
||||
**Developer Mode Required for Chat Mode**: To use MCP servers in regular ChatGPT conversations, you must first enable Developer Mode in your ChatGPT settings. This feature is available for ChatGPT Pro, Team, Enterprise, and Edu users.
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@ import { LocalFocusTip } from "/snippets/local-focus.mdx"
|
|||
|
||||
<LocalFocusTip />
|
||||
|
||||
Claude Code supports MCP servers through multiple transport methods including STDIO, SSE, and HTTP, allowing you to extend Claude's capabilities with custom tools, resources, and prompts from your FastMCP servers.
|
||||
[Claude Code](https://docs.anthropic.com/en/docs/claude-code) supports MCP servers through multiple transport methods including STDIO, SSE, and HTTP, allowing you to extend Claude's capabilities with custom tools, resources, and prompts from your FastMCP servers.
|
||||
|
||||
## Requirements
|
||||
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@ import { LocalFocusTip } from "/snippets/local-focus.mdx"
|
|||
|
||||
<LocalFocusTip />
|
||||
|
||||
Claude Desktop supports MCP servers through local STDIO connections and remote servers (beta), allowing you to extend Claude's capabilities with custom tools, resources, and prompts from your FastMCP servers.
|
||||
[Claude Desktop](https://www.claude.com/download) supports MCP servers through local STDIO connections and remote servers (beta), allowing you to extend Claude's capabilities with custom tools, resources, and prompts from your FastMCP servers.
|
||||
|
||||
<Note>
|
||||
Remote MCP server support is currently in beta and available for users on Claude Pro, Max, Team, and Enterprise plans (as of June 2025). Most users will still need to use local STDIO connections.
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@ import { LocalFocusTip } from "/snippets/local-focus.mdx"
|
|||
|
||||
<LocalFocusTip />
|
||||
|
||||
Cursor supports MCP servers through multiple transport methods including STDIO, SSE, and Streamable HTTP, allowing you to extend Cursor's AI assistant with custom tools, resources, and prompts from your FastMCP servers.
|
||||
[Cursor](https://www.cursor.com/) supports MCP servers through multiple transport methods including STDIO, SSE, and Streamable HTTP, allowing you to extend Cursor's AI assistant with custom tools, resources, and prompts from your FastMCP servers.
|
||||
|
||||
## Requirements
|
||||
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@ import { LocalFocusTip } from "/snippets/local-focus.mdx"
|
|||
|
||||
<LocalFocusTip />
|
||||
|
||||
Gemini CLI supports MCP servers through multiple transport methods including STDIO, SSE, and HTTP, allowing you to extend Gemini's capabilities with custom tools, resources, and prompts from your FastMCP servers.
|
||||
[Gemini CLI](https://geminicli.com/) supports MCP servers through multiple transport methods including STDIO, SSE, and HTTP, allowing you to extend Gemini's capabilities with custom tools, resources, and prompts from your FastMCP servers.
|
||||
|
||||
## Requirements
|
||||
|
||||
|
|
|
|||
178
docs/integrations/goose.mdx
Normal file
178
docs/integrations/goose.mdx
Normal file
|
|
@ -0,0 +1,178 @@
|
|||
---
|
||||
title: Goose 🤝 FastMCP
|
||||
sidebarTitle: Goose
|
||||
description: Install and use FastMCP servers in Goose
|
||||
icon: message-smile
|
||||
---
|
||||
|
||||
import { VersionBadge } from "/snippets/version-badge.mdx"
|
||||
import { LocalFocusTip } from "/snippets/local-focus.mdx"
|
||||
|
||||
<LocalFocusTip />
|
||||
|
||||
[Goose](https://block.github.io/goose/) is an open-source AI agent from Block that supports MCP servers as extensions. FastMCP can install your server directly into Goose using its deeplink protocol — one command opens Goose with an install dialog ready to go.
|
||||
|
||||
## Requirements
|
||||
|
||||
This integration uses Goose's deeplink protocol to register your server as a STDIO extension running via `uvx`. You must have Goose installed on your system for the deeplink to open automatically.
|
||||
|
||||
For remote deployments, configure your FastMCP server with HTTP transport and add it to Goose directly using `goose configure` or the config file.
|
||||
|
||||
## Create a Server
|
||||
|
||||
The examples in this guide will use the following simple dice-rolling server, saved as `server.py`.
|
||||
|
||||
```python server.py
|
||||
import random
|
||||
from fastmcp import FastMCP
|
||||
|
||||
mcp = FastMCP(name="Dice Roller")
|
||||
|
||||
@mcp.tool
|
||||
def roll_dice(n_dice: int) -> list[int]:
|
||||
"""Roll `n_dice` 6-sided dice and return the results."""
|
||||
return [random.randint(1, 6) for _ in range(n_dice)]
|
||||
|
||||
if __name__ == "__main__":
|
||||
mcp.run()
|
||||
```
|
||||
|
||||
## Install the Server
|
||||
|
||||
### FastMCP CLI
|
||||
<VersionBadge version="3.0.0" />
|
||||
|
||||
The easiest way to install a FastMCP server in Goose is using the `fastmcp install goose` command. This generates a `goose://` deeplink and opens it, prompting Goose to install the server.
|
||||
|
||||
```bash
|
||||
fastmcp install goose server.py
|
||||
```
|
||||
|
||||
The install command supports the same `file.py:object` notation as the `run` command. If no object is specified, it will automatically look for a FastMCP server object named `mcp`, `server`, or `app` in your file:
|
||||
|
||||
```bash
|
||||
# These are equivalent if your server object is named 'mcp'
|
||||
fastmcp install goose server.py
|
||||
fastmcp install goose server.py:mcp
|
||||
|
||||
# Use explicit object name if your server has a different name
|
||||
fastmcp install goose server.py:my_custom_server
|
||||
```
|
||||
|
||||
Under the hood, the generated command uses `uvx` to run your server in an isolated environment. Goose requires `uvx` rather than `uv run`, so the install produces a command like:
|
||||
|
||||
```bash
|
||||
uvx --with pandas fastmcp run /path/to/server.py
|
||||
```
|
||||
|
||||
#### Dependencies
|
||||
|
||||
Use the `--with` flag to specify additional packages your server needs:
|
||||
|
||||
```bash
|
||||
fastmcp install goose server.py --with pandas --with requests
|
||||
```
|
||||
|
||||
Alternatively, you can use a `fastmcp.json` configuration file (recommended):
|
||||
|
||||
```json fastmcp.json
|
||||
{
|
||||
"$schema": "https://gofastmcp.com/public/schemas/fastmcp.json/v1.json",
|
||||
"source": {
|
||||
"path": "server.py",
|
||||
"entrypoint": "mcp"
|
||||
},
|
||||
"environment": {
|
||||
"dependencies": ["pandas", "requests"]
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
#### Python Version
|
||||
|
||||
Use `--python` to specify which Python version your server should use:
|
||||
|
||||
```bash
|
||||
fastmcp install goose server.py --python 3.11
|
||||
```
|
||||
|
||||
<Note>
|
||||
The Goose install uses `uvx`, which does not support `--project`, `--with-requirements`, or `--with-editable`. If you need these options, use `fastmcp install mcp-json` to generate a full configuration and add it to Goose manually.
|
||||
</Note>
|
||||
|
||||
#### Environment Variables
|
||||
|
||||
Goose's deeplink protocol does not support environment variables. If your server needs them (like API keys), you have two options:
|
||||
|
||||
1. **Configure after install**: Run `goose configure` and add environment variables to the extension.
|
||||
2. **Manual config**: Use `fastmcp install mcp-json` to generate the full configuration, then add it to `~/.config/goose/config.yaml` with the `envs` field.
|
||||
|
||||
### Manual Configuration
|
||||
|
||||
For more control, you can manually edit Goose's configuration file at `~/.config/goose/config.yaml`:
|
||||
|
||||
```yaml
|
||||
extensions:
|
||||
dice-roller:
|
||||
name: Dice Roller
|
||||
cmd: uvx
|
||||
args: [fastmcp, run, /path/to/server.py]
|
||||
enabled: true
|
||||
type: stdio
|
||||
timeout: 300
|
||||
```
|
||||
|
||||
#### Dependencies
|
||||
|
||||
When manually configuring, add packages using `--with` flags in the args:
|
||||
|
||||
```yaml
|
||||
extensions:
|
||||
dice-roller:
|
||||
name: Dice Roller
|
||||
cmd: uvx
|
||||
args: [--with, pandas, --with, requests, fastmcp, run, /path/to/server.py]
|
||||
enabled: true
|
||||
type: stdio
|
||||
timeout: 300
|
||||
```
|
||||
|
||||
#### Environment Variables
|
||||
|
||||
Environment variables can be specified in the `envs` field:
|
||||
|
||||
```yaml
|
||||
extensions:
|
||||
weather-server:
|
||||
name: Weather Server
|
||||
cmd: uvx
|
||||
args: [fastmcp, run, /path/to/weather_server.py]
|
||||
enabled: true
|
||||
envs:
|
||||
API_KEY: your-api-key
|
||||
DEBUG: "true"
|
||||
type: stdio
|
||||
timeout: 300
|
||||
```
|
||||
|
||||
You can also use `goose configure` to add extensions interactively, which prompts for environment variables.
|
||||
|
||||
<Warning>
|
||||
**`uvx` (from `uv`) must be installed and available in your system PATH**. Goose uses `uvx` to run Python-based extensions in isolated environments.
|
||||
</Warning>
|
||||
|
||||
## Using the Server
|
||||
|
||||
Once your server is installed, you can start using your FastMCP server with Goose.
|
||||
|
||||
Try asking Goose something like:
|
||||
|
||||
> "Roll some dice for me"
|
||||
|
||||
Goose will automatically detect your `roll_dice` tool and use it to fulfill your request, returning something like:
|
||||
|
||||
> 🎲 Here are your dice rolls: 4, 6, 4
|
||||
>
|
||||
> You rolled 3 dice with a total of 14!
|
||||
|
||||
Goose can now access all the tools, resources, and prompts you've defined in your FastMCP server.
|
||||
|
|
@ -301,6 +301,7 @@ Install a MCP server in MCP client applications. FastMCP currently supports the
|
|||
- **Claude Desktop** - Installs via direct configuration file modification
|
||||
- **Cursor** - Installs via deeplink that opens Cursor for user confirmation
|
||||
- **Gemini CLI** - Installs via Gemini CLI's built-in MCP management system
|
||||
- **Goose** - Installs via deeplink that opens Goose for user confirmation (uses `uvx`)
|
||||
- **MCP JSON** - Generates standard MCP JSON configuration for manual use
|
||||
- **Stdio** - Outputs the shell command to run a server over stdio transport
|
||||
|
||||
|
|
@ -309,6 +310,7 @@ fastmcp install claude-code server.py
|
|||
fastmcp install claude-desktop server.py
|
||||
fastmcp install cursor server.py
|
||||
fastmcp install gemini-cli server.py
|
||||
fastmcp install goose server.py
|
||||
fastmcp install mcp-json server.py
|
||||
fastmcp install stdio server.py
|
||||
```
|
||||
|
|
@ -384,6 +386,9 @@ fastmcp install cursor server.py --env API_KEY=secret --env DEBUG=true
|
|||
# Install with environment file
|
||||
fastmcp install cursor server.py --env-file .env
|
||||
|
||||
# Install in Goose (uses uvx deeplink)
|
||||
fastmcp install goose server.py --with pandas
|
||||
|
||||
# Install with specific Python version
|
||||
fastmcp install claude-desktop server.py --python 3.11
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue