For AI agents: a documentation index is available at https://docs.plungeai.com/llms.txt. Append .md to any page URL, or send Accept: text/markdown, to get markdown. Setup instructions for agents are at https://docs.plungeai.com/agents.md. Execution planes take an ozk_ key; the models plane takes an sk-ocean- key.

Documentation Index: fetch the complete documentation index at /llms.txt. Use this file to discover all available pages before exploring further.

Connect VS Code (GitHub Copilot agent mode) to PlungeAI (Ocean Studio) over MCP — the code --add-mcp CLI command, a committed-safe .vscode/mcp.json with an input-prompted key, the 128-tools-per-request cap, and a plungeai_whoami + plungeai_list_agents verify. Use when the user is in VS Code/Copilot and says connect / install / set up PlungeAI, mentions mcp.json or code --add-mcp, or plungeai_* tools aren't appearing in agent mode. For another editor use its plungeai-in-<tool> skill; for an unlisted but MCP-capable client use plungeai-mcp-setup's generic client config.

Download zip (opens in a new tab) · View raw SKILL.md (opens in a new tab)

VS Code talks to PlungeAI over the Streamable HTTP MCP server at https://mcp.plungeai.com/v1. One ozk_ bearer key authenticates it (and the One API, if generated code calls PlungeAI directly).

Prerequisites

Connect (once)

From a terminal (simplest working path)

code --add-mcp '{"name":"plungeai","type":"http","url":"https://mcp.plungeai.com/v1","headers":{"Authorization":"Bearer ozk_YOUR_KEY"}}'

(PowerShell/cmd: double-quote the JSON and escape inner quotes with \".)

By hand — the committed-safe pattern

.vscode/mcp.json in the workspace. The inputs block makes VS Code prompt for the key once and store it encrypted — the file never holds the key, so it is safe to commit:

{
  "inputs": [
    {
      "id": "plungeai-key",
      "type": "promptString",
      "password": true,
      "description": "PlungeAI ozk_ key"
    }
  ],
  "servers": {
    "plungeai": {
      "type": "http",
      "url": "https://mcp.plungeai.com/v1",
      "headers": { "Authorization": "Bearer ${input:plungeai-key}" }
    }
  }
}

Machine-wide instead: MCP: Open User Configuration (the mcp.json in your user profile), or MCP: Add Server → choose the user scope — same fields, outside any repo.

The install page's "Add to VS Code" button emits one URL-encoded JSON object (vscode:mcp/install?{"name":"plungeai","type":"http","url":…}) — matching VS Code's documented deeplink shape. If it ever fails to parse, code --add-mcp or the file above works unconditionally.

Verify

  1. MCP: List Servers shows plungeai running; the Tools picker lists plungeai_*.
  2. In Copilot agent chat: "use plungeai_whoami to confirm my identity" → an identity card.
  3. "use plungeai_list_agents to search 'web search'" → live results from the active agent catalog.

Quirks

  • MCP tools run in agent mode (Chat view → mode picker → Agent). The plungeai_* tools appear in the chat Tools picker once the server starts.
  • 128 tools max per chat request, across all sources. Over the limit: deselect other servers/tools in the Tools picker, or rely on virtual tools — github.copilot.chat.virtualTools.threshold auto-groups tools beyond the threshold and lets the model expand a group on demand.
  • Mistyped key: MCP: List Servers → plungeai → Show Output shows the 401. Restart the server from the same menu; if it doesn't re-prompt for the stored input, remove and re-add the server.
  • Locked-down setups: chat.mcp.access governs which MCP servers can be used; org policies (ChatAllowedMcpServers / ChatDeniedMcpServers / ChatAllowManagedMcpServersOnly) allow- or deny-list servers — a missing MCP section in settings usually means one of these.
  • Trust: VS Code asks you to confirm you trust the server before first start — except when it's started directly from mcp.json.
  • Money-verb PlungeAI operations still pause with a structured needs_approval outcome (relay it, then plungeai_continue) regardless of any trust/confirmation setting.

Where next

  • Operating the plungeai_* tools once connected: plungeai-mcp-setup.
  • Writing code that calls https://api.plungeai.com directly: plungeai-api-setup.
  • Picking MCP vs the One API for a given job: choose-your-plungeai-door.
  • An unlisted but MCP-capable client, or the shared connect concepts (native remote vs. stdio bridge, key hygiene): plungeai-mcp-setup.
  • Full guide: https://mcp.plungeai.com/docs#3-connecting-clients (opens in a new tab)

Planned: TI-33

Search is not available yet. Until it ships, use the page index or browse the sidebar.

Planned: TI-34

The docs assistant is not available yet. You can hand these docs to your own assistant instead.