mirror of
https://github.com/block/goose.git
synced 2026-05-01 04:59:37 +00:00
119 lines
4 KiB
Markdown
119 lines
4 KiB
Markdown
---
|
|
title: Cognee Extension
|
|
description: Add Cognee MCP Server as a goose Extension
|
|
---
|
|
|
|
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/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 Quick Install
|
|
**Command**
|
|
```sh
|
|
uv --directory /path/to/cognee-mcp run python src/server.py
|
|
```
|
|
**Environment Variables**
|
|
```
|
|
LLM_API_KEY: <YOUR_OPENAI_API_KEY>
|
|
```
|
|
:::
|
|
|
|
## Configuration
|
|
|
|
:::info
|
|
Note that you'll need [uv](https://docs.astral.sh/uv/#installation) installed on your system to run this command, as it uses `uv`.
|
|
:::
|
|
|
|
<Tabs groupId="interface">
|
|
<TabItem value="cli" label="goose CLI" default>
|
|
|
|
**Install Cognee:**
|
|
|
|
```bash
|
|
# Clone and install Cognee
|
|
git clone https://github.com/topoteretes/cognee
|
|
cd cognee/cognee-mcp
|
|
uv sync --dev --all-extras --reinstall
|
|
|
|
# On Linux, install additional dependencies
|
|
sudo apt install -y libpq-dev python3-dev
|
|
```
|
|
|
|
**Configure the extension:**
|
|
|
|
<CLIExtensionInstructions
|
|
name="Cognee"
|
|
description="Knowledge graph memory capabilities with 30+ data source connections"
|
|
command="uv --directory /path/to/cognee-mcp run python src/server.py"
|
|
envVars={[
|
|
{ key: "LLM_API_KEY", value: "▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪▪" }
|
|
]}
|
|
commandNote={
|
|
<>
|
|
Replace <code>/path/to/cognee-mcp</code> with the actual path to your cloned cognee-mcp directory.
|
|
</>
|
|
}
|
|
infoNote={
|
|
<>
|
|
Obtain an API key for your LLM provider and paste it in. By default, this is an <a href="https://platform.openai.com/api-keys" target="_blank" rel="noopener noreferrer">OpenAI API key</a>.
|
|
</>
|
|
}
|
|
/>
|
|
</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.
|
|
|
|
### goose Prompt
|
|
|
|
> _goose, please cognify this information: "I prefer Python for data analysis and use pandas extensively. My current project involves analyzing customer behavior data." Then search for information about my programming preferences._
|
|
|
|
### goose Output
|
|
|
|
:::note CLI
|
|
|
|
<details>
|
|
<summary>Tool Calls</summary>
|
|
|
|
─── cognee_cognify | abcdefgh ──────────────────────────
|
|
|
|
data: I prefer Python for data analysis and use pandas extensively. My current project involves analyzing customer behavior data.
|
|
|
|
|
|
─── cognee_search | abcdefgh ──────────────────────────
|
|
|
|
search_query: programming preferences Python data analysis
|
|
|
|
search_type: GRAPH_COMPLETION
|
|
|
|
</details>
|
|
|
|
I'll help you store that information in the knowledge graph and then search for your programming preferences.
|
|
|
|
First, let me cognify the information about your preferences:
|
|
|
|
**Cognify Status:**
|
|
Background process launched due to MCP timeout limitations. The information about your Python and pandas preferences for data analysis has been added to the knowledge graph.
|
|
|
|
Now let me search for information about your programming preferences:
|
|
|
|
**Search Results:**
|
|
Based on the knowledge graph, I found information about your programming preferences:
|
|
|
|
- **Language Preference**: You prefer Python for data analysis
|
|
- **Key Libraries**: You use pandas extensively for data manipulation
|
|
- **Current Focus**: Your current project involves analyzing customer behavior data
|
|
- **Domain**: Data science and analytics workflows
|
|
- **Technical Stack**: Python + pandas for data analysis tasks
|
|
|
|
The knowledge graph has successfully stored and can now retrieve your programming preferences and project context for future conversations.
|
|
|
|
:::
|