Taichu MCP

What it does

Today, Taichu acts as an MCP client: it connects out to third-party MCP servers (Notion, Linear, Atlassian, and others you add under mcpServers in GWC Studio's daemon config) the same way Claude Code or Cursor would. Taichu does not yet run as an MCP server that other hosts can call into — the tools below describe that planned mode.

Five tools are planned to ship by default:

Setup in 90 seconds

1. Get a GWC API key. Sign in at gwc-corp.com/app/settings/api-keys and click Generate Key. Copy the gwc_live_… token shown once.

2. Run the setup wizard. If you have GWC Studio installed, the taichu CLI is already on your PATH. There is no standalone npm package.

# One-time setup. Opens an interactive wizard.
$ taichu setup

# Or step-by-step:
$ taichu login                      # paste your gwc_live_ token
$ taichu config --set defaultModel=claude-opus-5
$ taichu mcp                        # starts the MCP server (stdio)
$ taichu whoami                     # confirm sign-in
$ taichu logout                     # remove local credentials

3. Restart your AI CLI. Claude Code, Codex, and Cursor scan their MCP config at startup. New tools appear under the taichu_* prefix.

Manual configuration

Not yet available — Taichu doesn't run as an MCP server these hosts could connect to. The configs below show the shape that connection will take once server mode ships.

Claude Code

// ~/.claude.json
{
  "mcpServers": {
    "taichu": {
      "command": "taichu",
      "args": ["mcp"],
      "env": {
        "GWC_API_KEY": "gwc_live_..."
      }
    }
  }
}

Codex CLI

// ~/.codex/config.json
{
  "mcpServers": {
    "taichu": {
      "command": "taichu",
      "args": ["mcp"],
      "env": {
        "GWC_API_KEY": "gwc_live_..."
      }
    }
  }
}

Cursor

Cursor stores MCP config in its settings DB, not a file. Once available, you'll open Settings → MCP → Add Custom Server, then paste:

// Cursor → Settings → MCP → "Add Custom Server"
{
  "taichu": {
    "command": "taichu",
    "args": ["mcp"],
    "env": {
      "GWC_API_KEY": "gwc_live_..."
    }
  }
}

What a real call will look like

Once server mode ships, from Claude Code (not yet available):

> use taichu to make a hero image for my landing page
  and a 5s loading animation, and translate the headline
  "Move money like data" into Spanish, French, and Japanese.

[Claude Code calls taichu_image, taichu_video, taichu_chat ×3 in parallel]

✓ Image: https://gwc-corp.com/m/abc123.png
✓ Video: https://gwc-corp.com/m/def456.mp4
✓ es: "Mueve el dinero como los datos"
✓ fr: "Bouge l'argent comme les données"
✓ ja: "データのようにお金を動かす"

Cost: $0.034 (deducted from your monthly allowance — $1 on Basic, $15 on Standard)

Picking the main AI model

Once server mode ships, taichu_chat and any agentic loop that doesn't specify a model will resolve it three ways, in order:

1. Per call — pass { model: "gemini-3.1-pro-preview" } in the tool arguments. Highest priority. Not yet available.
2. Per host — set TAICHU_DEFAULT_TEXT_MODEL in your MCP config env block. Not yet available.
3. Per account — set the default at gwc-corp.com/app/settings. Syncs across web, mobile, and Studio today.

Billing & cost transparency

Every MCP tool call is charged the same way as a call from the GWC web or mobile app — your monthly allowance first, then USD balance. Text responses include a [model: …, tokens: in→out, cost: N¢] suffix so the host can see what each call cost.

If you'd rather route through your own provider keys, add them via BYOK (Bring Your Own Key) in GWC Studio's settings (desktop app) and Taichu will pass-through at provider cost (no markup).

Security

• API keys are stored locally in ~/.taichu/credentials.json with file mode 0600.
• Tokens are validated against api.gwc-corp.com on every call — no offline acceptance.
• When server mode ships, it will use stdio only — no inbound network port will open on your machine.
• Each token can be revoked from the keys page; revocation is enforced within seconds.
• Rotate tokens by issuing a new one and revoking the old.

Troubleshooting

The first entry below covers the planned server mode and will apply once it ships. The token and billing errors are real today — they come from api.gwc-corp.com and you can hit them from any client.

Tools don't appear in Claude Code (planned server mode)

Claude Code reads MCP config on startup only. Restart it after changing ~/.claude.json. Once server mode ships, verify with:

$ taichu mcp        # should print "Taichu MCP server starting (api=...)" to stderr
                    # if you see "No GWC auth token", run taichu login first

"HTTP 401: Invalid token"

The token was revoked or never valid. Re-mint at /app/settings/api-keys, then run taichu login.

"HTTP 402: Insufficient balance"

You ran out of allowance and have no USD balance. Top up at /app/billing or wait for the next monthly refresh.

Slow first call

Cold-start on the GWC API can be ~1s for the first request after idle. Subsequent calls reuse the warm instance.

Related

• GWC SDK — programmatic access from Node/Python/Go
• REST API — raw HTTP endpoints
• MCP overview — what MCP is, and how GWC exposes other servers
• Studio Guide — the desktop IDE that ships taichu