DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to run and deploy Sim workflows from your coding agent with Sim

Connect Claude Code or Codex to the Sim MCP server so your agent can manage workspaces and run workflows for you.

Short answer: For Claude Code run claude mcp add --transport http sim https://mcp.sim.ai/mcp, then open /mcp to sign in; then For Codex run codex mcp add sim --url https://mcp.sim.ai/mcp; sign in with OAuth or use an API key. All steps.

permissions. The connected agent can deploy workflows and change tables and files in your workspace, so review what it plans before letting it act.

Who it is forA developer who lives in a coding agent and wants it to trigger business workflows.

The problemSwitching to a web UI to run or check a workflow breaks flow.

The outcomeA coding agent that can run and deploy workflows and read tables, knowledge bases, files and logs.

What you need first

  • Node.js 20+ and Docker for self-hosting
  • A Chat API key for the model provider, or local models via Ollama or vLLM
  • Or the hosted cloud at sim.ai

Steps

  1. For Claude Code run claude mcp add --transport http sim https://mcp.sim.ai/mcp, then open /mcp to sign in
  2. For Codex run codex mcp add sim --url https://mcp.sim.ai/mcp
  3. Sign in with OAuth or use an API key
  4. Ask your agent to list workspaces and run a workflow

Prompt for your agent

Connect my Claude Code to simstudioai/sim with `claude mcp add --transport http sim https://mcp.sim.ai/mcp`, then list my workspaces and run <workflow name>, reporting the result.

Caveat. The URL shown connects to Sim Cloud; the README says self-hosted URLs are in the MCP docs.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for simstudioai/sim and "Run and deploy Sim workflows from your coding agent"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer