# Claude Code, Desktop, and Cowork + Jev

> Wire Jev into Claude Code and Cowork with typesafe-ai/skills, jev-judge-mcp, typesafe-mcp, and jevwire. Keys, install commands, and Cowork notes.

Plugins, MCP connectors, and TypeSafe skills on Anthropic's agent stack.

## Answer

Claude products already support MCP connectors and skills. Jev fits where Claude would otherwise guess a label in prose: moderation, routing, verification, and pre-tool gates. TypeSafe publishes an official agent skill; community MCP servers expose evaluate or judge tools.

## What this stack is

Claude Code is Anthropic's terminal agent for software work. Claude Desktop includes Cowork, an agentic workspace that shares Claude Code's architecture for multi-step knowledge work on local files. Cowork loads connectors (MCP), skills, and plugins from Customize on claude.ai, synced at session start. It does not read Claude Code's ~/.claude directory unless you add the same capability in Customize.

## Official TypeSafe agent skill

typesafe-ai/skills is the maintained skill for designing System One workflows. Claude Code can install it as a marketplace plugin; other agents use npx skills add.

```bash
claude plugin marketplace add typesafe-ai/skills
claude plugin install typesafe@typesafe-ai

# Other agents:
npx skills add typesafe-ai/skills --skill typesafe-ai
```

## jev-judge-mcp (single judge tool)

gecm0/jev-judge-mcp registers one MCP tool, judge, for narrow typed questions over evidence you supply. Claude Code can install marketplace + plugin typesafe@jev in one step (server and skill bundled). Also supports generic stdio MCP config for Desktop.

```bash
claude plugin marketplace add gecm0/jev-judge-mcp
claude plugin install typesafe@jev

npx skills add gecm0/jev-judge-mcp --skill jev
npx skills add typesafe-ai/skills --skill typesafe-ai
```

## typesafe-mcp evaluate (Go MCP server)

itsmostafa/typesafe-mcp exposes an evaluate tool and can register with Claude Code, Claude Desktop, and Codex via evaluate setup mcp. It targets POST /v1/systemone (or OpenRouter decisions when configured).

```bash
curl -fsSL https://raw.githubusercontent.com/itsmostafa/typesafe-mcp/main/install.sh | sh
TYPESAFE_API_KEY=your-key evaluate setup mcp
```

## jevwire hooks (Brainwires)

Brainwires/jevwire ships MCP tools (jev_evaluate, jev_rank, jev_verify, jev_gate_action, and others) plus a Claude Code plugin whose hooks run at harness boundaries. Install via /plugin marketplace add Brainwires/jevwire and set TYPESAFE_API_KEY in plugin settings.

## Cowork-specific notes

Cowork supports the same connectors and skills model as other Claude products: add MCP servers in Customize, enable skills, or install role plugins from Anthropic's knowledge-work-plugins repo. Pair a Jev MCP connector with typesafe-ai/skills the same way Canva or Notion ship connector plus skill playbooks. Cowork changelog documents on-demand MCP tool loading (toolSearchEnabled) to reduce context from large tool schemas.

## Environment keys

Create a key at https://console.typesafe.ai/ (or route through Vercel AI Gateway / OpenRouter where the integration documents it). Export TYPESAFE_API_KEY in the environment for Claude Code, Desktop, and Cowork sessions. Some MCP clients accept AI_GATEWAY_API_KEY when using gateway-hosted Jev models; follow that integration's README. Never commit keys into repos or paste them into chat logs.

```bash
export TYPESAFE_API_KEY="tsk_..."
# Optional pin:
export TYPESAFE_MODEL="jev-latest"
```

## Pitfalls

Do not install jev-judge-mcp twice (plugin plus manual claude mcp add) or you will duplicate servers. Codex config may embed literal keys in TOML; prefer exporting TYPESAFE_API_KEY in the launching shell when possible. jev-judge-mcp does not load .env files. For Cowork, skills that exist only under ~/.claude must be added in Customize to appear in Cowork sessions.

## In the directory

- [All agent guides](https://jev.aitools.fyi/guides/jev-with-ai-agents)
- [System One primer](https://jev.aitools.fyi/learn/system-one)
- [Agent tooling](https://jev.aitools.fyi/categories/agent-tooling)
- [TypeSafe agent skills](https://jev.aitools.fyi/sdks/typesafe-ai-skills)
- [typesafe-mcp](https://jev.aitools.fyi/tools/itsmostafa-typesafe-mcp)
- [jevwire](https://jev.aitools.fyi/tools/brainwires-jevwire)
- [jev-mcp (rashedInt32)](https://jev.aitools.fyi/tools/rashedint32-jev-mcp)
- [typesafe-mod](https://jev.aitools.fyi/tools/belazy167-typesafe-mod)
- [jev-skill-gate](https://jev.aitools.fyi/tools/shivampansuriya-jev-skill-gate)

## FAQ

### Does Cowork use Claude Code MCP config on disk?

Cowork syncs enabled connectors and skills from Customize on your claude.ai account at session start, not from ~/.claude automatically.

### Which MCP should I pick?

jev-judge-mcp if you want one opinionated judge tool and skill. typesafe-mcp if you want a single evaluate tool with multi-client setup script. jevwire if you want hook-based gates plus multiple tools.

### Can Desktop use the same plugin marketplace entries as Code?

MCP connectors are supported across Claude products; exact UI paths differ. Follow each README for Claude Code vs Desktop registration.

### Where is Claude MCP documentation?

See code.claude.com/docs for MCP quickstart and connector patterns.

### Does the TypeSafe skill call the API by itself?

The skill teaches workflow design and points to docs. You still need an SDK, gateway, or MCP tool for live inference.

## Sources

Directory copy checked 2026-09-30. Primary sources:

- [typesafe-ai/skills README](https://github.com/typesafe-ai/skills?ref=jev.aitools.fyi)
- [TypeSafe agent skill docs](https://docs.typesafe.ai/agent-skill?ref=jev.aitools.fyi)
- [jev-judge-mcp README](https://github.com/gecm0/jev-judge-mcp?ref=jev.aitools.fyi)
- [typesafe-mcp README](https://github.com/itsmostafa/typesafe-mcp?ref=jev.aitools.fyi)
- [Cowork overview](https://claude.com/docs/cowork/overview?ref=jev.aitools.fyi)
- [Claude MCP quickstart](https://code.claude.com/docs/en/mcp-quickstart?ref=jev.aitools.fyi)

Canonical: https://jev.aitools.fyi/guides/jev-with-ai-agents/claude-code-desktop-cowork
Markdown: https://jev.aitools.fyi/guides/jev-with-ai-agents/claude-code-desktop-cowork.md