jyapayne/langflow
1
0
Fork 0
Code Issues Pull requests Projects Releases 1 Packages Wiki Activity Actions

docs: mcp integration claude path (#7409)

Browse source 
* clarify-path-instructions

* will

* Apply suggestions from code review

Co-authored-by: KimberlyFields <46325568+KimberlyFields@users.noreply.github.com>

* paths-numbered-steps-not-bullets

---------

Co-authored-by: KimberlyFields <46325568+KimberlyFields@users.noreply.github.com>
This commit is contained in:
Mendon Kissling 2025-04-03 13:15:32 -04:00 • committed by GitHub
commit 225eb8c7d7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 15 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

23
docs/docs/Integrations/MCP/integrations-mcp.md
View file

@ -5,6 +5,7 @@ slug: /integrations-mcp
import Tabs from '@theme/Tabs'; import Tabs from '@theme/Tabs';
import TabItem from '@theme/TabItem'; import TabItem from '@theme/TabItem';
import Icon from "@site/src/components/icon";
Langflow integrates with the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction). This allows you to use your Langflow flows as tools in client applications that support the MCP, or extend Langflow with the [MCP server component](/components-tools#mcp-tools-stdio) to access MCP servers. Langflow integrates with the [Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction). This allows you to use your Langflow flows as tools in client applications that support the MCP, or extend Langflow with the [MCP server component](/components-tools#mcp-tools-stdio) to access MCP servers.
@ -12,7 +13,7 @@ You can use Langflow as an MCP server with any [MCP client](https://modelcontext
For configuring interactions between Langflow flows and MCP tools, see [Name and describe your flows for agentic use](#name-and-describe-your-flows-for-agentic-use). For configuring interactions between Langflow flows and MCP tools, see [Name and describe your flows for agentic use](#name-and-describe-your-flows-for-agentic-use).
To connect [MCP Inspector](https://modelcontextprotocol.io/docs/tools/inspector) to Langflow for testing and debugging flows, see [Install MCP Inspector to test and debug flows](#install-mcp-inspector-to-test-and-debug-flows) To connect [MCP Inspector](https://modelcontextprotocol.io/docs/tools/inspector) to Langflow for testing and debugging flows, see [Install MCP Inspector to test and debug flows](#install-mcp-inspector-to-test-and-debug-flows).
## Access all of your flows as tools ## Access all of your flows as tools
@ -53,7 +54,7 @@ This example assumes the default Langflow server address of `http://127.0.0.1:78
4. Save the `mcp.json` file, and then click the **Reload** icon. 4. Save the `mcp.json` file, and then click the **Reload** icon.
5. Your Langflow server is now available to Cursor as an MCP server, and all of its flows are registered as tools. 5. Your Langflow server is now available to Cursor as an MCP server, and all of its flows are registered as tools.
You can now use your flows as tools in Cursor. You can now use your flows as tools in Cursor.
Cursor determines when to use tools based on your queries, and will request permissions when necessary. Cursor determines when to use tools based on your queries, and requests permissions when necessary.
</TabItem> </TabItem>
@ -67,12 +68,12 @@ For example, on the MacOS menu bar, click **Claude**, and then select **Settings
2. In the **Settings** dialog, click **Developer**, and then click **Edit Config**. 2. In the **Settings** dialog, click **Developer**, and then click **Edit Config**.
This creates a `claude_desktop_config.json` file if you don't already have one. This creates a `claude_desktop_config.json` file if you don't already have one.
3. Add the following code to `claude_desktop_config.json`. 3. Add the following code to `claude_desktop_config.json`.
Your args may differ for your `uvx` and `Python` installations. To find the correct paths:
* For `uvx`: Run `which uvx` in your terminal Your `args` may differ for your `uvx` and `Python` installations. To find your system paths, do the following:
* For Python: Run `which python` in your terminal
4. To find the `uvx` path, run `which uvx` in your terminal. Replace `PATH/TO/UVX` with the `uvx` path from your system.
5. To find the `python` path, run `which python` in your terminal. Replace `PATH/TO/PYTHON` with the Python path from your system.
Replace `PATH/TO/PYTHON` with the Python path from your system.
This command assumes the default Langflow server address of `http://127.0.0.1:7860`. This command assumes the default Langflow server address of `http://127.0.0.1:7860`.
```json ```json
@ -80,7 +81,7 @@ This command assumes the default Langflow server address of `http://127.0.0.1:78
"mcpServers": { "mcpServers": {
"langflow": { "langflow": {
"command": "/bin/sh", "command": "/bin/sh",
"args": ["-c", "uvx --python PATH/TO/PYTHON mcp-sse-shim@latest"], "args": ["-c", "PATH/TO/UVX --python PATH/TO/PYTHON mcp-sse-shim@latest"],
"env": { "env": {
"MCP_HOST": "http://127.0.0.1:7860", "MCP_HOST": "http://127.0.0.1:7860",
"DEBUG": "true" "DEBUG": "true"
@ -92,13 +93,17 @@ This command assumes the default Langflow server address of `http://127.0.0.1:78
This code adds a new MCP server called `langflow` and starts the [mcp-sse-shim](https://github.com/phact/mcp-sse-shim) package using the specified Python interpreter and uvx. This code adds a new MCP server called `langflow` and starts the [mcp-sse-shim](https://github.com/phact/mcp-sse-shim) package using the specified Python interpreter and uvx.
4. Restart Claude for Desktop. 6. Restart Claude for Desktop.
Your new tools are available in your chat window. Click the tools icon to see a list of your flows. Your new tools are available in your chat window, and Langflow is available as an MCP server.
* To view your tools, click the <Icon name="Hammer" aria-label="Tools" /> icon.
* To view a list of connected MCP servers, which includes **langflow-mcp-server**, click the <Icon name="Unplug" aria-label="Connector" /> icon.
You can now use your flows as tools in Claude for Desktop. You can now use your flows as tools in Claude for Desktop.
Claude determines when to use tools based on your queries, and will request permissions when necessary. Claude determines when to use tools based on your queries, and will request permissions when necessary.
For more information, see [Debugging in Claude for Desktop](https://modelcontextprotocol.io/docs/tools/debugging#debugging-in-claude-desktop).
</TabItem> </TabItem>
</Tabs> </Tabs>