Skip to main content

Configure your AI Agent

You can tell your ChatGPT Codex / Claude agent how to connect to Medatarun via the Model Context Protocol (MCP)

Depending on the agents, configuration will vary. Refer to your agent documentation to know how to configure it. This is often referred as MCP or "tools" in their documentation.

The thing to remember is that the URL your agent needs is http://localhost:8080/mcp, it means http(s)://<yourhost>:<yourport>/mcp, always /mcp at the end.

Note that we are only compatible with the Streamable Http version of the protocol.

Example and test with ChatGPT's Codex​

Be sure that in your environment you have a variable containing an authentication token.

In your ~/.codex/config.toml add your server address and the token variable name.

[mcp_servers.medatarun]
url = "http://localhost:8080/mcp"
bearer_token_env_var = "MEDATARUN_AUTH_TOKEN"

When you will launch codex, be sure that this variable is set. See Authenticating with CLI or use the API.

Try to import something in Medatarun using UI's Import Button, or using CLI.

You can try this URL (it's from France public Open Data): https://gitlab.com/opendatafrance/scdl/plats-menus-collectifs/-/raw/master/schema.json

./medatarun model Import --from="https://gitlab.com/opendatafrance/scdl/plats-menus-collectifs/-/raw/master/schema.json"

You don't know what it is? neither do I.

Open Codex and ask this question

I'm a business user from United States, I don't understand french. Using Medatarun MCP,
tell me what the model "plats-menus-collectifs" is and what it means,
what's inside, what it is used for

Answer

For a US business user: the plats-menus-collectifs model is a standardized data
schema for “collective catering” dishes (meals served by public institutions and large
cafeterias). It defines a consistent way to publish what dishes are served,
where they come from, and what they contain.

What it means

- A shared data dictionary for dish composition, sourcing, labels, allergens,
  and publication metadata.
- Makes datasets comparable and auditable across organizations.

What’s inside

- One dataset/entity with fields covering:
  - Who publishes the data (organization name + official identifier).
  - Who produced the dish (establishment name + identifier).
  - Dish identity (dish code, dish name).
  - Ingredients/products and suppliers (names, supplier IDs, location codes).
  - Quality labels (e.g., organic, protected origin), additives, allergens.
  - GMO/irradiation flags.
  - Nutrition info (e.g., fat, carbs, salt per 100g).
  - Publication and last-updated timestamps.

What it’s used for

- Publishing and validating open data for collective catering menus.
- Compliance reporting on sourcing and quality.
- Transparency for stakeholders (citizens, auditors, regulators).
- Analytics across suppliers, regions, and time (sourcing, nutrition, sustainability).

Optional: update your AI AGENTS.md​

Some AI Agents (like ChatGPT Codex) do not support what is named MCP Instructions. (You can check the "Instructions" column of this table).

MCP Instructions teach your agent how to functionally (not technically) use Medatarun.

Therefore, agents without this compatibility may not act accordingly.

To compensate that, you can create an AGENTS.md file, containing those instructions, in one of the locations known from your agents. Often, you can place this file in the directory where you launch the agent.

You can fill this file with contents coming from Medatarun's API or command line.

echo "# AGENTS.md" > AGENTS.md
curl -s http://localhost:8080/api/config/AIAgentsInstructions >> AGENTS.md

Another way to do that is to copy/paste instructions in your agent software

curl http://localhost:8080/api/config/AIAgentsInstructions
# or
medatarun config AIAgentsInstructions
# or use the button in UI to get the text