MCP Integration

Connect AI Tools

Give Claude Desktop, ChatGPT, Cursor, and other AI tools direct access to your Baseline Labs data.

What is MCP?

The Model Context Protocol lets AI assistants call tools on your behalf. Instead of copy-pasting between apps, your AI searches, generates reports, and manages projects through your account — using the same credits and permissions as your browser session.

Setup

Connect in 2 minutes

You need an API key. Create one in your developer console, then paste the config below into your MCP client.

Claude Desktop (claude_desktop_config.json) Recommended

{
  "mcpServers": {
    "baseline-labs": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://baselinelabs.ai/mcp/",
        "--header",
        "Authorization:${AUTH_HEADER}"
      ],
      "env": {
        "AUTH_HEADER": "Bearer bl_your_key"
      }
    }
  }
}

Claude Desktop doesn't speak HTTP MCP natively — mcp-remote is a small npx shim that bridges stdio to our HTTPS endpoint. Requires Node.js installed locally. The token goes in env (not the header string directly) to dodge Claude Desktop's arg-quoting bug with spaces.

Claude.ai (web) & other URL-based clients

{
  "mcpServers": {
    "baseline-labs": {
      "url": "https://baselinelabs.ai/mcp/",
      "headers": {
        "Authorization": "Bearer bl_your_key"
      }
    }
  }
}

ChatGPT, Cursor, etc.

Server URL:  https://baselinelabs.ai/mcp/
Auth:        Bearer bl_your_key

Interactive setup: The MCP tab in your console generates the config with your actual key pre-filled and shows live tool status.

Tools

28 tools available

Once connected, your AI tool can call any of these. Read-only tools are free; tools that trigger new work cost credits (your AI will see the cost before executing).

Category	Tools	Description
Projects	`list_saves` `get_save` `create_save`	Manage analysis projects
Search	`search` `get_search_result` `list_saved_queries` `get_ranked_keywords` `parse_business_info`	Query across Google, GPT, Perplexity, Gemini
Reports	`list_report_templates` `create_report_template` `run_report` `get_report` `get_report_queries` `list_reports`	Track keyword rankings
Brand	`create_mention_scan` `get_mention_scan` `list_mention_scans` `get_mention_records` `list_brand_templates` `run_brand_report` `get_brand_report`	Sentiment and mention monitoring
Analytics	`get_backlinks` `get_referring_domains` `get_analytics`	Link graph and usage data
Schema	`generate_schema` `list_rolling_domains` `get_domain_schema`	JSON-LD schema generation
Account	`get_account`	Balance and account info

Programmatic

Use from Python

You can also call the MCP server programmatically using any MCP client library:

python

from mcp import ClientSession
from mcp.client.streamable_http import streamablehttp_client

async def main():
    async with streamablehttp_client(
        "https://baselinelabs.ai/mcp/",
        headers={"Authorization": "Bearer bl_your_key"}
    ) as (read, write, _):
        async with ClientSession(read, write) as session:
            await session.initialize()

            # List your projects
            result = await session.call_tool("list_saves", {})
            print(result)

Or skip MCP entirely and use the REST API directly — no library required.

Connect AI Tools

Hi, I'm George.