mcp.json, local models

Use Forkmate in LM Studio

LM Studio adds remote MCP servers, with headers, in mcp.json. Your model runs locally; Forkmate’s tools are called over the internet with your key.

Needs a key. LM Studio runs on your computer, so it connects with a personal key instead of a sign-in. Make a key in Forkmate · How keys work

No Forkmate account yet? Create one free first. It takes under a minute. You make your key there.

Example: in LM Studio, with Forkmate connected

I had two eggs and toast for breakfast.

Logged to Forkmate229 kcal

Egg, whole, cooked, hard-boiled · 2 large eggs (100 g)Bread, white · 1 slice (28 g)

Logged. Want me to total today so far?

Set up Forkmate in LM Studio

Forkmate’s server URL

https://mcp.forkmate.ai/

Streamable HTTP, with your personal key in the Authorization header.

Make a keyIn Forkmate, open Settings → Keys for local apps (https://app.forkmate.ai/#keys), name the key after LM Studio, pick when it expires and click Make key. Copy it: Forkmate shows it once. How keys work: forkmate.ai/connect/keys/.
Add the serverOpen the Program tab in the right sidebar → Install → Edit mcp.json and add the forkmate entry below, with your key in place of fmk_your_key_here.
Pick a model that can call toolsLoad a model with tool-calling support, then enable Forkmate in the chat.
Give your OK onceThe first time you log, Forkmate asks once for your OK to store your food diary. Agree the way it asks, in the chat or through the link it gives you to agree on the web, then log the meal again if it wasn’t saved.
Log your first mealIn LM Studio, say “I had two eggs and toast for breakfast.” It logs the meal with calories and macros to your Forkmate diary.

mcp.json

{
  "mcpServers": {
    "forkmate": {
      "url": "https://mcp.forkmate.ai/",
      "headers": {
        "Authorization": "Bearer fmk_your_key_here"
      }
    }
  }
}

What you need

A free Forkmate account (sign up). There is no paid plan.
LM Studio 0.3.17 or later (MCP support).
The model runs on your computer, but Forkmate doesn’t: you need an internet connection, and what you log goes to your Forkmate diary.
Small local models call tools less reliably. If a meal doesn’t log, try a larger tool-capable model.

Checked October 9, 2026 against the vendor’s documentation: LM Studio docs: MCP. LM Studio changes its menus often; if yours looks different, trust what it shows.

What to say first

Talk to LM Studio the way you’d tell a friend:

“I had two eggs and toast for breakfast.”
“How many calories have I had today?”
“Make the toast two slices.”
“What did I eat this week?”

It logs the meal with calories, protein, carbs and fat to your diary at app.forkmate.ai.

Good to know in LM Studio

LM Studio shows a confirmation for each tool call, where you can check and edit the arguments first.
LM Studio’s mcp.json follows Cursor’s format, so a Cursor config pastes straight in.

If something goes wrong in LM Studio

Frequent context overflows with a local model: MCP tools add tokens, which LM Studio warns can overload a small model. Load a model with a longer context.
mcp.json breaks after pasting a config: Paste only the forkmate entry, not the outer mcpServers wrapper.

Checked October 8, 2026 against LM Studio 0.3.17 release notes, LM Studio docs: MCP.

Forkmate shortcuts

Forkmate comes with ready-made requests for the everyday jobs: log a meal, fix the last entry, see what’s left today, log your usual, hit your protein, a weekly check-in. We haven’t found MCP shortcuts (prompts) in LM Studio’s menus or documentation, so type or paste the request instead.

Log a meal (log-meal)
“Log this to my Forkmate diary: two eggs and toast with butter”
Fix my last entry (fix-last-entry)
“Fix the last thing I logged in Forkmate: it was 2 eggs, not 3”
What's left today (today-so-far)
“Show me today so far in Forkmate: my calories, protein, carbs and fat.”
Log my usual (log-my-usual)
“Log my usual breakfast to Forkmate.”
Hit my protein today (hit-protein)
“How much protein have I had today in Forkmate, and how far am I from my target of 120 g? Suggest a few foods for my remaining meals and snacks that would close the gap, using my food profile and the foods I usually eat.”
Weekly check-in (week-review)
“Give me a check-in on my last 7 days in Forkmate (get_range): calories, protein, carbs and fat per day and on average, how many days I logged, and the foods I ate most.”
Move my MyFitnessPal history (import-myfitnesspal)
“How do I move my food diary history from MyFitnessPal to Forkmate? Walk me through exporting my data for free and importing it with the guided importer described at https://forkmate.ai/migrate-from-myfitnesspal/. Don't log anything yet.”
Give Forkmate feedback (give-feedback)
“I'd like to send feedback to Forkmate. Here is what I want to say, in my own words: "the oatmeal said 900 calories for one bowl" 1. If it isn't clear yet, ask me what it is about: a bug, a feature I'd like, a food or nutrition figure that looked wrong (or a food that was matched wrongly), or something else. 2. If something important is missing (for a wrong figure: which food and what looked wrong), ask me, and add my answer in my own words. 3. Show me the note exactly as it will be sent, with its category, and wait for me to confirm. Use my words, not a summary or a rewrite. Leave out health details I didn't ask to include. 4. Once I confirm, send it with send_feedback: `message` is my words (at most 4000 characters) and `category` is one of `bug`, `feature_request`, `food_data`, `other` (`food_data` for a wrong food or figure). 5. Then just tell me it was sent. Sending it changes nothing in my diary; if I also want a logged meal fixed, help me with that separately.”

Shortcut or not, Forkmate sends LM Studio the same logging rules when it connects: log your own words, keep your amounts, and look foods up before estimating.

Start logging from LM Studio

Create your free account, connect once, and your next meal is one sentence away. No card, no paid plan.

All assistants Start free