Models
list_modelsList the Jev models your key can use. jev-latest is the default. Bills nothing.
TypeSafe MCP connector
TypeSafe API key · Available
TypeSafe MCP Connector for AI Agents
Connect Claude, ChatGPT and other AI agents to TypeSafe over MCP: score search terms, ads and leads with typed yes/no, score and choice answers from Jev.
Connect your TypeSafe account once in ApexGenius with an API key, then ask Jev typed yes/no, score and choice questions about any text or record from compatible AI agents and act on calibrated answers. Each AI agent needs its own ApexGenius setup.
1,000 free credits · No card required
TypeSafe
App connector
Bring TypeSafe’s Jev model and its reusable skill to compatible AI agents. Ask typed yes/no, score and choice questions about search terms, ads and leads.
- 2
- Operations
- 2
- Read
- 0
- Write
- 3
- In context
- Authorization
- TypeSafe API key
- Cataloged tools
- 2 discoverable
- Connection scope
- One TypeSafe account per saved connection
- Accounts
- Connected account
Reviewed Oct 26, 2026
Claude / ChatGPT
MCP client
ApexGenius route
Gateway context
TypeSafe
Authorized session
Why the gateway is here
It keeps the TypeSafe authorization, tools, and activity behind the same managed route you use for your other supported systems.
Ask it
What people ask TypeSafe.
These questions use the TypeSafe tools below. Start with a read after connecting your channel or account.
- List the TypeSafe models available to my connection. Do not evaluate anything yet.Read
- Score these ten search terms for whether the searcher wants to hire a Salesforce consultant, and tell me which ones to add as negatives.Read
- Is this inbound lead a fit for a Salesforce consulting engagement? Give me a yes or no with the probability.Read
- Rate each of these three headlines from weak to strong for a paid search ad, and pick the best one.Read
Tools
What TypeSafe can do through ApexGenius.
The reviewed catalog contains these 2 TypeSafe tools. Search by tool name, job, or access type.
Open the generated tool referenceTyped answers
evaluateAsk yes/no, score or choice questions about a text or record and get typed answers with probabilities.
Connection model
How to connect TypeSafe.
The TypeSafe connection belongs to your signed-in account. Any TypeSafe-native resources stay inside that provider.
Read connection detailsBefore you start
- A TypeSafe account at console.typesafe.ai.
- An API key created in the TypeSafe console.
1. Connect TypeSafe to ApexGenius
- Open TypeSafe in Connections. Choose Connect or Add connection.
- Enter the API key. Paste the key from console.typesafe.ai. ApexGenius supplies the API address and checks the key against the model list.
Paste the API key from console.typesafe.ai and choose Connect. ApexGenius checks it against the model list before saving.Open full-size image (opens in a new tab) - Check the saved connection. Save after validation succeeds. Review the Tools tab. Evaluations are reads that bill input tokens to your account.
2. Choose your AI and finish setup
Each guide includes the AI setup and a first question for TypeSafe.
Current governance
Know the account, tools, and result.
ApexGenius keeps the selected context and current tool surface visible, then records supported write activity for review.
Authorized context
One connection covers one TypeSafe account and its API key.
Current tool surface
Both operations are reads. Nothing at TypeSafe changes, so an AI agent set to Read only can use them.
Reviewable activity
Each evaluation bills input tokens to the connected TypeSafe account. Listing models bills nothing.
The key goes only to api.typesafe.ai, as a bearer token. ApexGenius encrypts it.
Why a gateway
2 operations. Three tool definitions.
Your AI starts with three ApexGenius gateway tools. It discovers the TypeSafe operations available to its authorization when a task needs them, then runs the selected operation through the gateway.
One saved provider connection
Connect TypeSafe to ApexGenius, then authorize each AI client to use the saved connection with its own tool permissions.
Scoped per agent
Give one client read-only and the write operations never appear in its tool list at all.
Every call on the record
Which agent asked, what ran, and whether it succeeded, kept per connection for review.
Use TypeSafe with your AI.
Choose your AI client for setup steps and examples using TypeSafe.
FAQ
Questions people ask before connecting TypeSafe.
- How do I connect TypeSafe?
- Create an API key in the TypeSafe console at console.typesafe.ai and paste it into the TypeSafe connection in ApexGenius. ApexGenius checks the key against the model list before saving.
- What does Jev return?
- Typed answers, not text. A yes/no question returns a probability, a score returns a number with confidence, and a choice returns the pick with confidence and probabilities.
- Does it cost anything?
- Each evaluation bills input tokens to your TypeSafe account. Listing models bills nothing. ApexGenius does not add a TypeSafe charge.
- Can my AI change anything at TypeSafe?
- No. Both operations are reads. Evaluations compute and return answers, and nothing at TypeSafe changes.
- What can I score with it?
- Any text or record: search terms, ad copy, inbound leads or support tickets. Put the business definition inside the question so Jev knows who counts as a fit.
More connectors
Explore the directory.
MCP-compatible AI agents
Codex starts in Plugins in the ChatGPT desktop app. ChatGPT Chat and Work also use Plugins, with personal setup where Developer Mode is permitted. Each AI client has its own guide and authorization requirements.
App connections
Salesforce keeps connection context. Other providers use your signed-in account.
Connect TypeSafe. Start with a safe read.
Use the AI you already work in while ApexGenius keeps the app route visible.
Connect TypeSafe1,000 free credits · No card required
Compatibility does not imply partnership.