CC Workflow Studio AI Editor
breaking-brake/cc-wf-studio
Creates and edits visual agent workflows in CC Workflow Studio through conversation, with the agent reading and writing the canvas over MCP.
Connects the OpenWork MCP Gateway to Claude Code, Codex, Gemini CLI, OpenCode and other clients so the agent can use your organization's skills, plugins and connections.
Install OpenWork MCP Gateway Setup
$ npx skills add different-ai/openwork --skill connect-openwork-mcp -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install different-ai/openwork connect-openwork-mcp --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .claude/skills && cp -r skills-src/ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcp .claude/skills/connect-openwork-mcp && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "connect-openwork-mcp" agent skill from https://github.com/different-ai/openwork/tree/dev/ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcp into .claude/skills/connect-openwork-mcp/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "connect-openwork-mcp", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/different-ai/openwork/tree/dev/ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcpType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add different-ai/openwork --skill connect-openwork-mcp -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install different-ai/openwork connect-openwork-mcp --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .agents/skills && cp -r skills-src/ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcp .agents/skills/connect-openwork-mcp && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "connect-openwork-mcp" agent skill from https://github.com/different-ai/openwork/tree/dev/ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcp into .agents/skills/connect-openwork-mcp/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "connect-openwork-mcp", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add different-ai/openwork --skill connect-openwork-mcp -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install different-ai/openwork connect-openwork-mcp --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcp .cursor/skills/connect-openwork-mcp && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "connect-openwork-mcp" agent skill from https://github.com/different-ai/openwork/tree/dev/ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcp into .cursor/skills/connect-openwork-mcp/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "connect-openwork-mcp", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/different-ai/openwork.git --path ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcp--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add different-ai/openwork --skill connect-openwork-mcp -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install different-ai/openwork connect-openwork-mcp --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcp .gemini/skills/connect-openwork-mcp && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "connect-openwork-mcp" agent skill from https://github.com/different-ai/openwork/tree/dev/ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcp into .gemini/skills/connect-openwork-mcp/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "connect-openwork-mcp", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install different-ai/openwork connect-openwork-mcpInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add different-ai/openwork --skill connect-openwork-mcp -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .github/skills && cp -r skills-src/ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcp .github/skills/connect-openwork-mcp && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "connect-openwork-mcp" agent skill from https://github.com/different-ai/openwork/tree/dev/ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcp into .github/skills/connect-openwork-mcp/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "connect-openwork-mcp", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add different-ai/openwork --skill connect-openwork-mcp -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install different-ai/openwork connect-openwork-mcp --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/different-ai/openwork.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcp .opencode/skills/connect-openwork-mcp && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "connect-openwork-mcp" agent skill from https://github.com/different-ai/openwork/tree/dev/ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcp into .opencode/skills/connect-openwork-mcp/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "connect-openwork-mcp", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
connect-openwork-mcp- GitHub stars
- 24k
- Token cost
- ~661 tokens
- SKILL.md length
- 256 words
- Files
- 1
- Skills in repo
- 33
- Repo updated
- First seen
- Licence
- Custom licence
At a glance
Connects the OpenWork MCP Gateway to Claude Code, Codex, Gemini CLI, OpenCode and other clients so the agent can use your organization's skills, plugins and connections.
- Works in 3 steps: Add the server → Sign in → Verify
- Adding the OpenWork MCP server to Claude Code or Codex
- SKILL.md covers 1. Add the server, 2. Sign in, 3. Verify and If it fails
- Calls codex, opencode and claude; reaches api.openworklabs.com
What it does
The agent points a client at the Streamable HTTP server at `https://api.openworklabs.com/mcp/agent`, which signs in with OAuth using PKCE and dynamic client registration and needs no API key. The skill gives the exact add command for Claude Code (`claude mcp add --transport http`), Codex, Gemini CLI and OpenCode, and says to add it as a remote MCP server by URL for Cursor, VS Code, Claude Desktop, ChatGPT, Windsurf and Zed. An existing `openwork` entry is reused rather than duplicated.
You then sign in through the browser and pick an organization, which is pinned to the token. Verification means seeing `openwork` in the client's MCP list, restarting the session, confirming that the `search_capabilities` and `execute_capability` tools exist and asking which organization you are connected to; success is not claimed before that. Troubleshooting covers 401 and `invalid_grant` errors, headless agents and self-hosted Den API origins. An OpenWork Cloud account is required.
When your agent uses it
- Adding the OpenWork MCP server to Claude Code or Codex
- Fixing a 401 or invalid_grant error from the OpenWork gateway
- Switching which OpenWork organization a client is signed in to
- Pointing a client at a self-hosted OpenWork deployment
Example prompts
- “Connect OpenWork's MCP gateway to Claude Code for all my projects.”
- “Add the openwork server to Codex and walk me through the login.”
- “I get invalid_grant from the openwork MCP server, so help me fix it.”
Requirements
- An OpenWork Cloud account
- A browser for the OAuth sign-in
- An MCP-capable client such as Claude Code or Codex
Workflow steps
3 steps, taken from the step headings in SKILL.md.
- Add the server
- Sign in
- Verify
What it can do on your machine
Read from SKILL.md and the folder at commit 4ccc9e9. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
codexopencodeclaudegemini
From the folder's file list and the shell code blocks in SKILL.md.
Network
Hosts in commands or code, which the agent is likely to contact:
api.openworklabs.com
Also links to:
openworklabs.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
OpenWork MCP Gateway Setup loads about 661 tokens when it runs. Until then it costs about 65 tokens; SKILL.md has 256 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 256 words (~661 tokens).
“Server URL: https://api.openworklabs.com/mcp/agent Transport: Streamable HTTP. Auth: OAuth (PKCE, dynamic client registration); the client opens a browser for sign-in. No API key is needed.”
- name
- connect-openwork-mcp
Files
Just SKILL.md in ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcp of different-ai/openwork.
Open the folder on GitHubat commit 4ccc9e9
Compare with similar skills
OpenWork MCP Gateway Setup next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| OpenWork MCP Gateway Setup this skilldifferent-ai/openwork | 24k | — | ~661 | Automated safety check: Pass | Custom licence | |
| CC Workflow Studio AI Editorbreaking-brake/cc-wf-studio | 5.4k | — | ~561 | Automated safety check: Pass | Custom licence | |
| Cao MCP Appsawslabs/cli-agent-orchestrator | 1.4k | — | ~1.9k | Automated safety check: Pass | Apache-2.0 | |
| Agnixagent-sh/agnix | 446 | — | ~874 | Automated safety check: Pass | Apache-2.0 | |
| Claude Docs Consultantcentminmod/my-claude-code-setup | 2.7k | — | ~959 | Automated safety check: Pass | MIT | |
| Agnixagent-sh/agnix | 446 | — | ~563 | Automated safety check: Pass | Apache-2.0 |
Similar skills
- Official
Cao MCP Apps
awslabs/cli-agent-orchestrator
Enable, operate, and extend CAO's MCP Apps surface — the host-rendered fleet dashboard visible inside MCP App hosts (Claude Desktop, ChatGPT, VS Code Copilot, Goose, Postman).
Agnix
agent-sh/agnix
A skill your agent uses when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'.
Claude Docs Consultant
centminmod/my-claude-code-setup
Consult official Claude Code documentation from code.claude.com using selective fetching.
Agnix
agent-sh/agnix
A skill your agent uses when user asks to 'lint agent configs', 'validate skills', 'check CLAUDE.md', 'validate hooks', 'lint MCP'.
Setup MCP Server
nesquikm/mcp-rubber-duck
Add mcp-rubber-duck MCP server to an AI coding tool (Claude Desktop, Cursor, VS Code, Windsurf, etc.)
More from different-ai/openwork
All 33 skills in this repoOpenWork Desktop CDP Driver
different-ai/openwork
Drives a running OpenWork desktop window over CDP from the shell to evaluate JS, take screenshots, start sessions and send prompts for hand checks.
Fake Model Provider Faults
different-ai/openwork
Makes the desktop app's model provider fail on demand, with refused connections, resets, stalls and HTTP 4xx and 5xx errors, so error and retry states can be reproduced.
OpenWork Model Alias Manager
different-ai/openwork
Manages OpenWork's inference model aliases, discounts and overlays over the upstream OpenRouter catalog, and triggers the GitHub workflow that refreshes base models.
Reproduce Chat States
different-ai/openwork
Fires known chat states in the running OpenWork desktop app, such as provider errors, retries and tool steps, so you can check how each renders.
OpenWork Electron Browser Automation
different-ai/openwork
Attaches OpenCode browser tools to the OpenWork Electron dev app through CDP to explore its UI, send a composer task and debug, not to give test verdicts.
Daytona Sandbox Operations
different-ai/openwork
Covers Daytona CLI setup, sandbox debugging, keeping a sandbox alive and which credentials the CLI uses, for when Daytona itself is the problem rather than the tests.
Related
Works with
Categories
Questions about OpenWork MCP Gateway Setup
What does OpenWork MCP Gateway Setup do?
Connects the OpenWork MCP Gateway to Claude Code, Codex, Gemini CLI, OpenCode and other clients so the agent can use your organization's skills, plugins and connections. com/mcp/agent`, which signs in with OAuth using PKCE and dynamic client registration and needs no API key. The skill gives the exact add command for Claude Code (`claude mcp add --transport http`), Codex, Gemini CLI and OpenCode, and says to add it as a remote MCP server by URL for Cursor, VS Code, Claude Desktop, ChatGPT, Windsurf and Zed.
When should I use OpenWork MCP Gateway Setup?
OpenWork MCP Gateway Setup fits situations like: adding the OpenWork MCP server to Claude Code or Codex; fixing a 401 or invalid_grant error from the OpenWork gateway; switching which OpenWork organization a client is signed in to; pointing a client at a self-hosted OpenWork deployment.
How do I install OpenWork MCP Gateway Setup in Claude Code?
Run `npx skills add different-ai/openwork --skill connect-openwork-mcp -a claude-code`. Or copy the skill folder (ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcp in different-ai/openwork) into .claude/skills/connect-openwork-mcp in your project. Claude Code loads it when a task matches its description.
How do I install OpenWork MCP Gateway Setup in Codex?
Run `npx skills add different-ai/openwork --skill connect-openwork-mcp -a codex`. Or copy the skill folder (ee/apps/landing/public/.well-known/agent-skills/connect-openwork-mcp in different-ai/openwork) into .agents/skills/connect-openwork-mcp in your project. Codex loads it when a task matches its description.
Can I use OpenWork MCP Gateway Setup in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add different-ai/openwork --skill connect-openwork-mcp -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/connect-openwork-mcp, .gemini/skills/connect-openwork-mcp, .github/skills/connect-openwork-mcp and .opencode/skills/connect-openwork-mcp in your project.
What does OpenWork MCP Gateway Setup need to run?
Going by SKILL.md and its folder, OpenWork MCP Gateway Setup needs the command-line tools its instructions call (codex, opencode, claude and gemini). Our summary lists: An OpenWork Cloud account; A browser for the OAuth sign-in; An MCP-capable client such as Claude Code or Codex.
Does OpenWork MCP Gateway Setup access the network?
SKILL.md names 2 domains. In commands or code: api.openworklabs.com; the agent is likely to contact it when it follows the instructions. As links in the text: openworklabs.com. This is read from the text; nothing was executed.
Is OpenWork MCP Gateway Setup safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does OpenWork MCP Gateway Setup use?
OpenWork MCP Gateway Setup has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.
How many tokens does OpenWork MCP Gateway Setup use?
About 661 tokens (SKILL.md is roughly 2.6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to OpenWork MCP Gateway Setup?
Skills that share tags, products or a category with OpenWork MCP Gateway Setup: CC Workflow Studio AI Editor (breaking-brake/cc-wf-studio, 5.4k stars), Cao MCP Apps (awslabs/cli-agent-orchestrator, 1.4k stars), Agnix (agent-sh/agnix, 446 stars) and Claude Docs Consultant (centminmod/my-claude-code-setup, 2.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains OpenWork MCP Gateway Setup?
different-ai (a GitHub organization) maintains it in different-ai/openwork, which has 23,967 GitHub stars. The repository holds 33 skills in this directory. The repository was last updated on October 9, 2026.
Source: different-ai/openwork on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.