Live probe refreshed Nov 21, 2026 · Endpoint host mcp.mcpbundles.com
Domain knowledge for TypeSafe — workflow patterns, data models, and gotchas for your AI agent.
Jev evaluates state (text, JSON object, or array of strings) and returns typed answers with probabilities — not long-form generation. Use it when software needs a decision: route a ticket, score frustration, or gate an action with a yes/no likelihood (noul).
| Type | Use when | Response highlights |
|---|---|---|
| choice | Pick one route or category | choice, probabilities, confidence |
| score | Rate along ordered levels | score, legend, probabilities |
| noul | Yes/no or likelihood 0–1 | noul |
Ask several questions in one call by passing multiple entries in the questions map on evaluate. Keys are yours; answers return under the same keys.
Connect TypeSafe to any MCP client in minutes
https://mcp.mcpbundles.com/bundle/typesafeThis server may ask you to sign in when your AI client connects.
Prefer the browser? Open in MCPBundles Studio
Sign in to connect your credentials and start running tools from the chat.
Connect to your AI clientMCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms
Add to your AI client, then sign in once when you connect.
TypeSafe Jev is a System One decision model: structured choice, score, and noul answers with probabilities for routing, moderation, triage, and agent guardrails — not open-ended text generation.
This listing identifies a third-party integration. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
https://mcp.mcpbundles.com/bundle/typesafeThis server may ask you to sign in when your AI client connects.
Prefer the browser? Open in MCPBundles Studio
Choose your AI client below. When you connect, sign in to MCPBundles once — we store your service credentials for every client.
Browse all toolsTypesafe Classify
Pick one label from your criteria map for state using a choice question.
Typesafe Evaluate
Run Jev (System One) structured decisions on state: typed answers with probabilities for choice and score questions, no…
Typesafe List Models
List Jev model names and aliases your account may send on evaluate calls (for example jev-latest and jev-preview).
Schemas and invoke metadata: Directory API
TypeSafe Jev is a System One decision model: structured choice, score, and noul answers with probabilities for routing, moderation, triage, and agent guardrails — not open-ended text generation. It provides 3 tools that AI agents can use through the Model Context Protocol (MCP).
Add the MCPBundles server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL format is: https://mcp.mcpbundles.com/bundle/typesafe. Authentication is handled automatically.
TypeSafe provides 3 tools that can be called by AI agents, along with a SKILL.md that gives your AI agent domain knowledge about when and how to use them.
TypeSafe uses API Key. TypeSafe requires credentials. Connect via MCPBundles and authentication is handled automatically.
© 2026 ThinkChain Inc. All rights reserved.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.
Other MCP servers in this category from the directory index