Use Biosimulant from ChatGPT, Claude Code or Codex

Connect your account, then ask. Your assistant finds a model or lab, explains its assumptions, and runs it when you approve the plan.

Free during the beta. Nothing runs without your say-so.

Using ChatGPT or looking for the packaged integration? Get the Biosimulant plugin.

Set up ChatGPT

You need a Biosimulant account and a ChatGPT account with Developer mode available. The public directory listing is awaiting submission and OpenAI review; use this direct connection in the meantime.

  1. In ChatGPT, open Settings → Security and login → Developer mode and enable it. Availability depends on your plan and workspace policy.
  2. Open ChatGPT Plugins, select the + or Create app button, and name the connection Biosimulant. You can upload the Biosimulant logo in the optional Icon field.
  3. Choose Server URL, paste the address below, and select OAuth authentication.
https://api.biosimulant.com/mcp
  1. Expand Advanced OAuth settings. Set Registration method to Dynamic Client Registration (DCR). Keep the discovered endpoints. To stay signed in for up to 30 days, add offline_access to Base scopes.
  2. Review the selected scopes and the unreviewed-server notice, then select Create. Choose Sign in with Biosimulant, check that the consent screen shows your own Biosimulant account, review access, and select Connect.
  3. In Settings → Plugins → Biosimulant, select Refresh to load the actions. Open the plugin and choose Try in chat, or select Biosimulant in a new chat.

Check the connection with this read-only request:

Find a published glycolysis lab and explain what it simulates and any important limitations. Do not run or change anything.

A successful response names a published lab and explains what it can and cannot tell you. Missing scientific checks do not mean the connection failed.

Troubleshoot ChatGPT setup
“Only public PKCE clients are supported”
Create the connection using DCR in Advanced OAuth settings. ChatGPT's default CIMD registration is incompatible with this endpoint.
“No app actions available yet”
Finish Biosimulant sign-in, then select Refresh in the plugin's settings. If your session has expired, reconnect and start a new chat.
Wrong account or expired consent request
Use Switch account on the consent screen, or restart sign-in from ChatGPT for a fresh request.
Developer mode is missing
Check your ChatGPT plan and workspace policy. A workspace administrator may need to make it available.
A model search returns no results
Ask for models and labs, or browse without a package-type filter. Published simulations may be packaged as labs.

You can revoke access in Biosimulant Settings → Connections. See the full connection guide for permissions and workflow examples.

Connect Claude Code or Codex

Sign in once, from inside the agent. It sends your authorization on every call after that. The beta is free and there is no balance to top up.

$ claude mcp add --transport http biosimulant https://api.biosimulant.com/mcp
/mcp

Run this inside Claude Code to sign in.

What you are agreeing to

  • Read the Hub and the biological sources we support
  • Make and edit private workspaces of your own
  • Start runs, after you have approved them
  • Publish releases, after you have approved them
  • Stay signed in for up to 30 days, or disconnect sooner

What you would actually ask it

Three things people do on the first day. The replies below come from a real session, shortened to fit.

Find a model and work out what it is

Searches the Hub, pins the exact release, then goes and reads the paper behind it.

Nobody asked it for that last line. It tells you what the package has not been checked for.

Find the Bexkens 2024 S. mansoni glycolysis lab on the Hub and explain what it models.

Founddemi/bexkens2024-schistosoma-mansoni-glycolysis@1.0.0

SHA-256ea0fed3fd767794455b514a2d8a5d74200c595b38850b3e01b34367158ac4843

A kinetic model of glycolysis in S. mansoni, focused on how allosteric regulation of lactate dehydrogenase affects glycolytic behaviour.

Paper10.1016/j.ijpara.2024.03.005 · PMID 38492780

Qualification: schema_valid: true, but runtime_valid: false. Treat it as a package with a valid schema, not a domain-validated reproduction.

Fork it and run it

Copies the release into a private workspace of yours, gets a compute session ready, and stops.

It can set the whole thing up. It cannot start the run.

Fork it into a workspace and run it with the default inputs.

Waiting for your approval

Once you allow it:

Runcompleted · duration 10.0 · step 1.0

Resultsresults/default_run_results.json

Of the selected observables, AMP moved most across the window. ATP, ADP, pyruvate, NAD and NADH were reported too.

Check two models fit together

Reads both ports and compares the profile each one declares.

Two ports connect when both sides name the same profile. Otherwise it stops early, rather than giving you a number that means nothing.

Can I feed this protein sequence into the Boltz affinity model?

protein_sequence declares protein.sequence/v1. So does the port you want to wire it to, so the connection holds.

ligand_smiles declares chemical.smiles/v1. Wiring a sequence into that one fails the check before anything runs.

Nothing runs until you say so.

Every tool that would change something, spend compute or publish comes in two halves. The agent can only reach the first one on its own.

  1. prepare

    The agent works out exactly what it wants to do. Nothing changes yet.

  2. You read it

    You get the exact plan and the digest it is pinned to, not a summary of one.

  3. You approve

    Or you do not, and it stops there.

  4. apply

    Only now does anything run, save or publish.

If approving one step at a time gets tiring, hand over a grant instead. It covers a set of actions you name, it expires on its own, and you can pull it whenever you want.

What it can reach

Find
Search the Hub, pin an exact release by digest, and pull records from the biological sources we support.
Build
Make a private workspace, fork a release into it, and change models and compositions inside it.
Run
Prepare a run, start it once you approve, watch it, cancel it, and fetch what it produced.
Prove
Read the signed Passport for any run: the digests, the runtime version and the inputs that made the result.
Publish
Release your work to the Hub, privately or publicly, and only when you have said so.

Keeping files off the cloud

Use the local CLI when your files have to stay on your own machine. Local work is not saved as a revision and gets no managed run or Passport.

Install the CLI

Skills

Two specification documents, for writing formal model requirements and a technical plan before you build. They are instructions, not tools: no extra access, no extra permissions. Most people never need them.

Download skills

The endpoint is https://api.biosimulant.com/mcp. Something not working? Read the Gateway guide (opens in a new tab)