Jev Integration for AI Agents

TypeSafe's Jev model for typed decisions — ask yes/no, multiple-choice or rubric-score questions about a block of state and get calibrated probabilities back instead of prose. Built for classification, routing and scoring steps inside a workflow

v1.0.02 toolsAPI KeyGitHub Report an issue

Open in ChatGPTChatGPT

Open in ClaudeClaude

Playground

VS Code

Connected to Jev via MewCP.

Encrypted at rest, isolated from the model

Resolved from an AES-256-GCM vault at the moment of the call and attached to the request — the model never sees the secrets.

Try asking

Everything Jev can do

Tools2

evaluate_state

read

Evaluates the given state against a map of typed questions and returns one structured answer per question, keyed by the same ids used in the request. Every question is evaluated independently and in parallel against the same state, and noul (yes/no), choice (single-select), and score (rubric) questions can be freely mixed within a single call.

list_models

read

Lists the model names and aliases this account can pass in the evaluate-state `model` field, with a description and release date for each. This list currently only surfaces aliases such as `jev-latest` and `jev-preview` — a versioned model ID (e.g. `jev-1.13.0`) is still accepted by the evaluate-state `model` field even when it does not appear here.

Missing a tool, or found a bug?

Jev MCP Server is open source. Tell the MewCP maintainers.

Open GitHub Issues

Built for AI agents

Jev runs through a gateway that holds the credentials, scopes the access and records every call.

Managed credentials

Jev API keys are encrypted at rest and never shown again after you save them.
One credential per end user, not one shared key across your users.
Rotate a key without touching your agent's config.

Credentials stay out of context

Jev credentials are resolved at the gateway and attached to the outbound call.
The agent sees tool results, never a token.
Revoke an account and the next call stops working — no redeploy.

Scoped access, fully logged

Choose exactly which Jev tools an agent is allowed to call.
Every call is logged with its outcome, latency and which account it ran as.
Catalog changes are reviewed before they ship, so tool descriptions cannot shift under you.

One endpoint for every server

Reach Jev through the same MCP endpoint as the rest of your toolset.
Tools are discovered on demand, so 2 tools do not fill the context window.
Stateless: no sessions to keep alive and no reconnect logic.

Connect Jev to your agent

One endpoint, the same key, whichever client you use.

Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json (Mac) · %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "mewcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://gateway.mewcp.com/personal/mcp",
        "--header",
        "Authorization: Bearer API_KEY"
      ]
    }
  }
}

Replace API_KEY with your own key.

Already have an "mcpServers" section in your config? Just add the server entry inside it.

01Open Claude Desktop → Settings → Developer → "Edit Config"
02Paste the snippet inside the outer { } of the config file (merge with your existing "mcpServers" section if you have one)
03Save the file and restart Claude Desktop
04Start a new conversation — your tool will be available

Ready to connect Jev?

Managed auth, hosted MCP servers, and every Gmail tool your agent needs.

Free to start.

Everything Jev can do

Tools2

evaluate_state

read

list_models

read

Built for AI agents

Jev runs through a gateway that holds the credentials, scopes the access and records every call.

Managed credentials

Jev API keys are encrypted at rest and never shown again after you save them.
One credential per end user, not one shared key across your users.
Rotate a key without touching your agent's config.

Credentials stay out of context

Jev credentials are resolved at the gateway and attached to the outbound call.
The agent sees tool results, never a token.
Revoke an account and the next call stops working — no redeploy.

Scoped access, fully logged

Choose exactly which Jev tools an agent is allowed to call.
Every call is logged with its outcome, latency and which account it ran as.
Catalog changes are reviewed before they ship, so tool descriptions cannot shift under you.

One endpoint for every server

Reach Jev through the same MCP endpoint as the rest of your toolset.
Tools are discovered on demand, so 2 tools do not fill the context window.
Stateless: no sessions to keep alive and no reconnect logic.

Connect Jev to your agent

One endpoint, the same key, whichever client you use.

Claude Desktop

~/Library/Application Support/Claude/claude_desktop_config.json (Mac) · %APPDATA%\Claude\claude_desktop_config.json (Windows)

{
  "mcpServers": {
    "mewcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://gateway.mewcp.com/personal/mcp",
        "--header",
        "Authorization: Bearer API_KEY"
      ]
    }
  }
}

Replace API_KEY with your own key.

Already have an "mcpServers" section in your config? Just add the server entry inside it.

01Open Claude Desktop → Settings → Developer → "Edit Config"
02Paste the snippet inside the outer { } of the config file (merge with your existing "mcpServers" section if you have one)
03Save the file and restart Claude Desktop
04Start a new conversation — your tool will be available