Claude Inductive Bio connectorWhat Claude can do in your Inductive Bio account.
The Claude Inductive Bio connector exposes 2 tools, both of them read tools. 0 write, 0 undocumented: Claude lists the prediction models you can run and applies them to your molecules. Below: what it computes, what it leaves out, and who decides.
Verified Trustpilot reviews · AI, automation & growth agency
What the Claude Inductive Bio connector changes for chemists
Instead of leaving the chat to run a model, you paste structures as SMILES (the text notation for a molecule) and Claude fetches predicted LogD, the lipophilicity, and pKa, the acid or base ionization, on its own. Then it talks the numbers through with you so you can triage which ideas to make.
See what you can compute. list_available_models returns the models open to your account, each with its ID, assay name and units. Everything starts there.
Rank a set of analogs. You want LogD for a list of reported NSAIDs: predict_properties returns the predicted value for each, and Claude helps you spot the ones most likely to reach the brain, the publisher's own example.
Read ionization before a design meeting. Predicted pKa values, which the publisher ties to solubility and permeability, give you a basis to discuss a series.
What Claude does not do here: the connector covers LogD and pKa only. Microsomal stability, efflux, CYP or hERG inhibition belong to Inductive Bio's full suite, which you request from the publisher. Nothing runs by itself either: Claude only computes when you ask. For a pipeline that runs without you, you need an automation tool, a different job; the Integrations hub covers that side.
The vocabulary in one minute
Five words you will meet while connecting Inductive Bio.
- Connector
- The link you set up once between Claude and a service, so Claude can work with it while it answers you.
- Tool
- One named capability the connector opens to Claude. Claude picks the ones it needs, and the directory sheet lists them all.
- Authorization
- The service's own sign-in screen, where you hand Claude the access it will use from then on. Granted once, and taken back the same way.
- Directory
- Claude's official catalogue: every connector gets a sheet with its publisher, its purpose and the full list of its tools.
- MCP
- The shared standard behind connectors: it is what lets an assistant like Claude talk to an outside service.
Connect Inductive Bio to Claude in three steps
- 01
Find Inductive Bio in your settings
Open Claude's settings, go to Customize then Connectors, and locate Inductive Bio in the list. On a Team or Enterprise workspace, an Owner or Primary Owner has to enable it before you can sign in.
- 02
Start the connection
Hit Connect on its row, then sign in through the window that the service opens on its own side. If the link ever breaks, use Disconnect and connect it again.
- 03
Review the authorization screen
Read the authorization screen before you accept: it belongs to the service, and it sets what the access covers. You can also revoke that access later from your Inductive Bio account.
The 2 tools in the Inductive Bio connector
Inductive Bio gives Claude 2 tools: 2 that read your account, 0 that change something in it.
Two tools, both read tools: they query models and return predictions without storing anything in your account. Names stay as Claude shows them.
- 2 read
What Claude reads (2)
2 toolsTwo tools that query Inductive Bio's models without changing anything.
list_available_models
Builds the roster of prediction models you are allowed to run, giving each one's ID, the assay it mirrors and its units. Claude carries those IDs into the next call.
predict_properties
Runs one or more models over a list of molecules supplied as SMILES and returns a predicted value for every molecule-model pair. Claude can then rank or discuss the output.
What Claude asks before it acts
By default, Claude stops and asks for your go-ahead before each action it takes on an account for you. Both Inductive Bio tools only read and compute, but the rule still holds.
On a Team or Enterprise workspace, owners decide whether a member may let some actions through without confirmation. They can also cap what a connector may do across the organization, and that setting binds everyone with no way around it from a personal account. Claude also works with your access and nothing beyond it: a model your account does not open stays closed to it, however you phrase the request.
Which plans it is available on
None of the 819 sheets in the directory shows availability by plan. Connector by connector, that information is not published anywhere: a genuine gap in the catalogue.
The general rule is published: remote connectors are open to all users on Claude, Cowork, Claude Desktop and mobile. On Team and Enterprise, an Owner or Primary Owner turns the connector on for the organization before members can connect. For the current state, check the Inductive Bio sheet in the official directory.
Where this connector stops
A connector is not an automation. Claude calls these tools while it answers you: nothing fires when a molecule is registered somewhere.
By default the sheet exposes only reads, but that is an observed floor: an admin can open actions that appear on no public sheet. The partner badge is not a security audit, and Anthropic says so on every sheet: it does not choose the publisher's tools and does not vouch for their behavior. This connector is documented only by its sheet and the publisher's own page. To compare with another connector's page, see the Claude affinity connector.
Need help connecting Inductive Bio to Claude?
A person reads every message.
