Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 7 additions & 13 deletions documentation/docs/mcp/cognee-mcp.md
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem';
import CLIExtensionInstructions from '@site/src/components/CLIExtensionInstructions';

This tutorial covers how to add the [Cognee MCP Server](https://github.com/topoteretes/cognee) as a Goose extension to enable knowledge graph memory capabilities, connecting to over 30 data sources for enhanced context and retrieval.
This tutorial covers how to add the [Cognee MCP Server](https://github.com/topoteretes/cognee/tree/main/cognee-mcp) as a Goose extension to enable knowledge graph memory capabilities, connecting to over 30 data sources for enhanced context and retrieval.

:::tip TLDR
**Command**
Expand All @@ -17,7 +17,6 @@ uv --directory /path/to/cognee-mcp run python src/server.py
**Environment Variables**
```
LLM_API_KEY: <YOUR_OPENAI_API_KEY>
EMBEDDING_API_KEY: <YOUR_OPENAI_API_KEY>
```
:::

Expand All @@ -34,7 +33,7 @@ Note that you'll need [uv](https://docs.astral.sh/uv/#installation) installed on
```bash
# Clone and install Cognee
git clone https://github.com/topoteretes/cognee
cd cognee-mcp
cd cognee/cognee-mcp
uv sync --dev --all-extras --reinstall

# On Linux, install additional dependencies
Expand Down Expand Up @@ -153,7 +152,7 @@ goose configure

8. Add the required environment variables:
:::info
You'll need OpenAI API keys for both LLM and embedding models. [Get your API keys here](https://platform.openai.com/api-keys).
You'll need an API key for your LLM provider. By default, this is an [OpenAI API key](https://platform.openai.com/api-keys).
:::

```sh
Expand Down Expand Up @@ -188,15 +187,6 @@ You'll need OpenAI API keys for both LLM and embedding models. [Get your API key
│ ▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪
◇ Add another environment variable?
│ Yes
◇ Environment variable name:
│ EMBEDDING_API_KEY
◇ Environment variable value:
│ ▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪
◇ Add another environment variable?
│ No
// highlight-end
└ Added Cognee extension
Expand All @@ -205,6 +195,10 @@ You'll need OpenAI API keys for both LLM and embedding models. [Get your API key
</TabItem>
</Tabs>

:::info
See the [Cognee MCP documentation](https://docs.cognee.ai/how-to-guides/deployment/mcp) for supported configuration options.
:::

## Example Usage

Cognee provides knowledge graph memory capabilities for Goose, allowing it to remember and connect information across conversations and documents.
Expand Down
24 changes: 2 additions & 22 deletions documentation/docs/mcp/mbot-mcp.md
Original file line number Diff line number Diff line change
Expand Up @@ -13,18 +13,12 @@ import GooseDesktopInstaller from '@site/src/components/GooseDesktopInstaller';
This tutorial will get you started with [deemkeen's MQTT MCP server](https://github.com/deemkeen/mbotmcp) for the [MakeBlock mbot2 rover](https://www.makeblock.com/products/buy-mbot2), and outline some code changes we made along the way.

:::tip TLDR
<Tabs groupId="interface">
<TabItem value="ui" label="Goose Desktop" default>
[Launch the installer](goose://extension?cmd=/path/to/java&arg=-jar&arg=/path/to/mbotmcp-0.0.1-SNAPSHOT.jar&name=mbot2&description=mbot2&env=MQTT_SERVER_URI%3Dtcp://1.2.3.4:1883&env=MQTT_USERNAME%3Dyour_username&env=MQTT_PASSWORD%3Dyour_password)
</TabItem>
<TabItem value="cli" label="Goose CLI">
**Command**
```sh
/path/to/java -jar /path/to/mbotmcp-0.0.1-SNAPSHOT.jar
```
</TabItem>
</Tabs>
**Environment Variable**

**Environment Variables**
```
MQTT_SERVER_URI: tcp://1.2.3.4:1883
MQTT_PASSWORD: <string or blank>
Expand All @@ -35,20 +29,6 @@ This tutorial will get you started with [deemkeen's MQTT MCP server](https://git
## Configuration

<Tabs groupId="interface">
<TabItem value="ui" label="Goose Desktop" default>
<GooseDesktopInstaller
extensionId="mbot2"
extensionName="mbot2"
description="mbot2"
command="/path/to/java"
args={["-jar", "/path/to/mbotmcp-0.0.1-SNAPSHOT.jar"]}
envVars={[
{ name: "MQTT_SERVER_URI", label: "tcp://1.2.3.4:1883" },
{ name: "MQTT_USERNAME", label: "your_username" },
{ name: "MQTT_PASSWORD", label: "your_password" }
]}
/>
</TabItem>
<TabItem value="cli" label="Goose CLI">
1. Run the `configure` command:
```sh
Expand Down
49 changes: 37 additions & 12 deletions documentation/static/servers.json
Original file line number Diff line number Diff line change
Expand Up @@ -130,13 +130,20 @@
{
"id": "cognee-mcp",
"name": "Cognee",
"description": "Knowledge graph and cognitive AI capabilities",
"command": "uvx cognee-mcp",
"description": "Knowledge graph and cognitive AI capabilities (requires local server setup)",
"command": "uv --directory /path/to/cognee-mcp run python src/server.py",
"link": "https://github.com/topoteretes/cognee",
"installation_notes": "Install using uvx package manager.",
"installation_notes": "This is a local extension. You must first clone and install the Cognee MCP server locally before using this extension. Update the placeholder path before running the 'goose session' command.",
"is_builtin": false,
"endorsed": false,
"environmentVariables": []
"endorsed": true,
"show_install_link": false,
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Copy link
Contributor

@blackgirlbytes blackgirlbytes Oct 14, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

uvx i think should work for that command! do you think so

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

similar to npm / npx

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I got this errror trying to install from the link: Failed to install extension: Invalid command: /path/to/java. Only cu, docker, jbang, npx, uvx, goosed, npx.cmd, i-ching-mcp-server are allowed.

"environmentVariables": [
{
"name": "LLM_API_KEY",
"description": "API key for your LLM provider",
"required": true
}
]
},
{
"id": "computercontroller",
Expand Down Expand Up @@ -298,10 +305,11 @@
{
"id": "jetbrains",
"name": "JetBrains",
"description": "Integrate Goose with any JetBrains IDE",
"command": "npx -y @jetbrains/mcp-proxy",
"description": "Integrate with any JetBrains IDE (requires local setup, dependent on your IDE version)",
"url": "http://localhost:<PORT>/sse",
"type": "remote",
"link": "https://github.com/JetBrains/mcp-jetbrains",
"installation_notes": "Install using npx package manager. Requires the MCP Server plugin to be installed in your JetBrains IDE.",
"installation_notes": "IDE v2025.2 and later: Enable SSE configuration from Settings > Tools > MCP Server, then update the placeholder SSE URL in the following command. If installing from the link, you must update the URL from the Extensions page before activating the extension. For earlier IDE versions, you must install the MCP Server plugin and use npx package manager to install the extension.",
"is_builtin": false,
"endorsed": true,
"environmentVariables": []
Expand All @@ -320,13 +328,30 @@
{
"id": "mbot-mcp",
"name": "MBot",
"description": "Chatbot and conversational AI integration",
"command": "npx -y mbot-mcp",
"description": "Control a MakeBlock mbot2 rover through MQTT (requires local setup)",
"command": "/path/to/java -jar /path/to/mbotmcp-0.0.1-SNAPSHOT.jar",
"link": "https://github.com/deemkeen/mbotmcp",
"installation_notes": "Install using npx package manager.",
"installation_notes": "This is a local extension. You must first download the JAR file from the repository, install Java, and update the placeholder paths before running the 'goose session' command.",
"is_builtin": false,
"endorsed": false,
"environmentVariables": []
"show_install_link": false,
"environmentVariables": [
{
"name": "MQTT_SERVER_URI",
"description": "MQTT server URI (example: tcp://1.2.3.4:1883)",
"required": true
},
{
"name": "MQTT_USERNAME",
"description": "MQTT username (empty string if no auth required)",
"required": true
},
{
"name": "MQTT_PASSWORD",
"description": "MQTT password (empty string if no auth required)",
"required": true
}
]
},
{
"id": "memory",
Expand Down