Integrations

MCP Server URL: https://mcp.daloopa.com/server/mcp

Claude.ai

Go to Settings > Connectors and click Organization connectors to manage connectors. If you are part of an organization, an admin may need to set up the connector first.

Click Browse connectors, find Daloopa, and click on it.

Click Connect.

You'll be redirected to the Daloopa MCP Login Page. Enter your Daloopa email and password. On success, you'll be redirected back to Claude with the connection established.

Verify that all Daloopa tools are enabled:

You can also manage your connectors in the custom connectors page

You're ready to use Daloopa with Claude.

ChatGPT

Go to Settings > Apps & Connectors:

Click Daloopa under Browse apps:

You'll be redirected to the Daloopa MCP Login Page. Enter your Daloopa email and password.

In a new chat, click the Add icon, go to More, and select Daloopa:

You're ready to use Daloopa with ChatGPT.

📘

GPT-5-Thinking produces more thorough answers than GPT-5-Instant but takes longer.

Claude Desktop

The Claude Desktop app has three tabs — Chat, Code, and Cowork. All three can access Daloopa via the connectors you set up on claude.ai (they sync automatically).

Chat tab: Same as claude.ai but running natively.

Code tab: Claude Code with a graphical interface. Also picks up MCP servers configured via the Claude Code CLI.

📘

Available on macOS (Apple Silicon) and Windows.

Claude Cowork

Cowork is the agentic knowledge-work tab in Claude Desktop — built for research, analysis, and document creation rather than coding. It has access to your Daloopa connector (same setup as claude.ai above) and also supports plugins, including the Daloopa plugin.

Daloopa's Plugin is currently getting reviewed to be added to Anthropic's marketplace. In the meantime, you can add our plugin using the steps below.

To install the plugin in Cowork, click on the + icon on the left of the input prompt and hit Add plugin:

Go to personal, click on the + icon, click 'Add marketplace from github' and add daloopa/plugin

This gives you access to all 11 analysis skills (e.g., /daloopa:earnings AAPL) directly in Cowork.

Claude Code

Claude Code is Anthropic's agentic coding tool that runs in your terminal. It's also available as the Code tab in Claude Desktop.

Setup via CLI:

Using OAuth:

claude mcp add --transport http --scope user daloopa https://mcp.daloopa.com/server/mcp

Using a bearer token:

claude mcp add --transport http --scope user daloopa https://mcp.daloopa.com/server/mcp \
  --header "Authorization: Bearer YOUR_DALOOPA_MCP_TOKEN"

Using an API key:

claude mcp add --transport http --scope user daloopa https://mcp.daloopa.com/server/mcp \
  --header "X-API-KEY: YOUR_DALOOPA_API_KEY"

📘

The --scope user flag makes Daloopa available across all your projects. Without it, the default local scope requires re-adding the server per project.

Verify: Run claude mcp list to confirm daloopa is listed. Inside Claude Code, type /mcp to check connection status.

Setup via Desktop:

Click on the + icon on the left of the input prompt and hit Manage connectors:

Click on the + icon in the top center of the screen and hit Browse connectors

Search Daloopa, and click on it.

Click Connect.

You'll be redirected to the Daloopa MCP Login Page. Enter your Daloopa email and password. On success, you'll be redirected back to Claude with the connection established.

Verify that Daloopa is enabled:

Codex

Codex is OpenAI's agentic coding tool. Available as both a CLI and a desktop app.

CLI setup:

Using OAuth:

codex mcp add daloopa --url https://mcp.daloopa.com/server/mcp
codex mcp login daloopa

Using a bearer token:

export DALOOPA_MCP_TOKEN="YOUR_DALOOPA_MCP_TOKEN"
codex mcp add daloopa --url https://mcp.daloopa.com/server/mcp \
  --bearer-token-env-var DALOOPA_MCP_TOKEN

Verify: Run codex mcp list to confirm daloopa is listed.

Desktop app: MCP servers configured in the CLI are available in the Codex desktop app automatically.

Cursor

Add to your Cursor MCP config (~/.cursor/mcp.json for global, or .cursor/mcp.json per project):

{
  "mcpServers": {
    "daloopa": {
      "url": "https://mcp.daloopa.com/server/mcp"
    }
  }
}

With authentication:

{
  "mcpServers": {
    "daloopa": {
      "url": "https://mcp.daloopa.com/server/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_DALOOPA_MCP_TOKEN"
      }
    }
  }
}

VS Code + Copilot

Add to .vscode/mcp.json in your workspace (requires VS Code 1.101+ with GitHub Copilot):

{
  "servers": {
    "daloopa": {
      "type": "http",
      "url": "https://mcp.daloopa.com/server/mcp"
    }
  }
}

⚠️

VS Code uses "servers" (not "mcpServers") and requires an explicit "type": "http" field.

Windsurf

Add to your Windsurf MCP config (~/.codeium/windsurf/mcp_config.json):

{
  "mcpServers": {
    "daloopa": {
      "serverUrl": "https://mcp.daloopa.com/server/mcp"
    }
  }
}

⚠️

Windsurf uses "serverUrl" (not "url").

Anthropic API

Integrate Daloopa into your own applications using the Anthropic API. Requires an Anthropic API key and a Daloopa bearer token.

from anthropic import Anthropic

client = Anthropic(api_key="YOUR_ANTHROPIC_API_KEY")

response = client.beta.messages.create(
    model="claude-sonnet-4-5-20250929",
    max_tokens=2048,
    messages=[],  # Add your messages here
    mcp_servers=[
        {
            "type": "url",
            "url": "https://mcp.daloopa.com/server/mcp",
            "name": "daloopa",
            "authorization_token": "YOUR_DALOOPA_MCP_TOKEN",
        }
    ],
    tools=[
        {
            "type": "mcp_toolset",
            "mcp_server_name": "daloopa",
            "default_config": {"enabled": False},
            "configs": {
                "discover_companies": {"enabled": True},
                "discover_company_series": {"enabled": True},
                "get_company_fundamentals": {"enabled": True},
                "search_documents": {"enabled": True},
            },
        }
    ],
    betas=["mcp-client-2025-11-20"],
)

OpenAI API

Integrate Daloopa using the OpenAI Responses API. Requires an OpenAI API key and a Daloopa bearer token.

from openai import OpenAI

client = OpenAI(api_key="YOUR_OPENAI_API_KEY")

response = client.responses.create(
    model="gpt-5.4",
    input=[],  # Add your messages here
    tools=[
        {
            "type": "mcp",
            "server_label": "Daloopa",
            "server_url": "https://mcp.daloopa.com/server/mcp",
            "headers": {
                "Authorization": "Bearer YOUR_DALOOPA_MCP_TOKEN"
            },
            "allowed_tools": [
                "discover_companies",
                "discover_company_series",
                "get_company_fundamentals",
                "search_documents"
            ],
            "require_approval": "never"
        }
    ],
)

Feedback and Support

If you have any feedback, suggestions, or questions, please contact us.