Local Agentic Editing with Jumper and LM Studio

​

Before you begin

• Jumper is installed and running locally
• You have media analyzed in Jumper if you want to test a real search right away
• You want the model and Jumper tool calls to stay on your machine

​

Step-by-step

1

Download LM Studio

Go to lmstudio.ai and download the build for your operating system.

2

Check which Gemma size fits your machine

Before downloading a large model, search for gemma 4 on canirun.ai and see which sizes are realistic for your hardware.The little red eye icon marks models with Vision support, which is required for the Jumper workflow.

3

Open LM Studio's model search

Open LM Studio and click the robot icon in the left sidebar (Model Search).

4

Search for a Gemma 4 model and download it

Search for gemma 4 and pick a model that shows the capabilities you want. For Jumper, Tool Use and Vision are the key capabilities.

5

Choose load parameters

Once the download finishes, open the model picker, turn on Manually choose model load parameters, and then click the model you want to load.

6

Confirm the load settings

In the load settings view, you will most likely want to increase Context Length. In this example it is set to the maximum value, and Remember settings is enabled so you do not have to repeat this every time you load the model.

If the model is too slow, runs out of memory, or fails to load, lower the Context Length or move to a smaller model.

When you are happy with the settings, click Load Model.

7

Open the MCP configuration

In LM Studio chat, open Integrations, click the + menu, and choose Edit mcp.json.

8

Add the Jumper MCP server

Add the Jumper server to mcp.json and save the file:

{
  "mcpServers": {
    "jumper": {
      "url": "http://127.0.0.1:6699/mcp"
    }
  }
}

9

Enable the Jumper integration

After saving, LM Studio reloads its MCP servers. Open Integrations and turn on mcp/jumper.

10

Make sure Jumper is active in the chat

Open or start a chat and confirm that jumper is attached in the composer before you send a prompt.

11

Start LM Studio's local server

Open the menu bar icon and choose Start Server on Port 1234.This step is required for a good Jumper workflow. LM Studio can talk to Jumper through MCP, but because of a current LM Studio limitation it cannot reliably inspect Jumper’s result thumbnails directly inside the agent chat unless those images are manually pasted into the conversation.With the local server running, Jumper can ask the loaded model to describe candidate frames in the background and pass those descriptions back to the chat. In practice, that means the agent can actually validate whether the returned shots are good matches instead of guessing from filenames, metadata, or search scores alone.

12

Add an API token if the server requires one

LM Studio 0.4 and newer can require an API token for every request to its local server. This is off by default.To check, click Model Server in LM Studio’s left sidebar, then Server Settings. If Require Authentication is off, skip this step.If it is on, Jumper needs a token to ask the model to describe frames. Click Manage Tokens, then Create new token.Give the token a name, such as Jumper token. The default permissions are enough for Jumper. Click Create token.Click Copy. LM Studio does not show the token again.Open mcp.json again. The mcp.json button next to Server Settings opens it. Add a headers block to the jumper entry, with Bearer in front of your token:

{
  "mcpServers": {
    "jumper": {
      "url": "http://127.0.0.1:6699/mcp",
      "headers": {
        "Authorization": "Bearer sk-lm-QpJCzCk6:38ufowmeZ9VziV22QmwJ"
      }
    }
  }
}

Use your own token, not the one shown here, then save the file.The token has to come from LM Studio. Jumper passes it on to LM Studio’s server on port 1234, which rejects any value it did not create.

13

Verify that LM Studio can use Jumper

Ask a simple question like Can you use Jumper? or give it a real search request. A healthy setup should answer using the available Jumper tools instead of acting like it has no integration.

​

Timeline workflows

​

Troubleshooting

• mcp/jumper does not appear in Integrations: Check that your mcp.json is valid JSON and that Jumper is running locally on http://127.0.0.1:6699.
• The model behaves like it has no tools: Make sure mcp/jumper is enabled in Integrations and that jumper is attached in the current chat composer.
• The agent can search but does a poor job judging which shots are the best matches: Make sure LM Studio’s local server is running on http://127.0.0.1:1234.
• The agent reports “LM Studio requires an API token”: The local server requires authentication, and mcp.json has no token. Follow the Add an API token if the server requires one step above.
• The agent reports “LM Studio rejected the API token”: The token in mcp.json is wrong or was deleted. Create a new one under Manage Tokens and replace the old value, keeping Bearer in front of it.
• The model is too slow or does not load: Choose a smaller Gemma 4 variant or lower the context length in LM Studio’s load settings.

​

Related

Bionic

The same setup in Bionic, our recommended agent app

All local agent guides

Other agent apps you can use with Jumper

Agentic editing

Overview of how AI agents use Jumper through MCP

Agentic editing and data privacy

What stays local and what the model actually receives