What is the key difference between DAG Studio MCP and Discovery Engine?

DAG Studio MCP belongs to the Data Science Tools category with cloud HTTP/SSE execution, while Discovery Engine belongs to the Data Science Tools category with local stdio execution.

How do I install DAG Studio MCP or Discovery Engine in Claude Desktop or Cursor?

Copy the mcpServers JSON configuration snippet provided on this page into your claude_desktop_config.json or ~/.cursor/mcp.json file and restart your AI client.

Are DAG Studio MCP and Discovery Engine free or paid?

DAG Studio MCP operates under a Free / Open Source model (No auth required). Discovery Engine operates under a Freemium model (API Key required).

Which MCP server has more tools and community activity?

DAG Studio MCP lists 9 tools with 2 views and 0 GitHub stars. Discovery Engine lists 6 tools with 4 views and 7 GitHub stars.

Can I use both DAG Studio MCP and Discovery Engine together in the same MCP host?

Yes! MCP hosts like Claude Desktop, Cursor, Windsurf, Cline, and VS Code support configuring multiple servers under the mcpServers object simultaneously.

Side-by-Side Model Context Protocol Comparison

DAG Studio MCP vs Discovery Engine

In-depth architectural comparison of the DAG Studio MCP and Discovery Engine MCP servers. Compare execution transports, security boundaries, tool capabilities, quality scores, and ready-to-paste client installation snippets for Claude, Cursor, Windsurf, and VS Code.

At a Glance & Executive Verdict

DAG Studio MCP

Data Science Tools · Remote HTTP/SSE

Quality: 49/100 (Fair) | Auth: No auth required

Discovery Engine

Data Science Tools · Local stdio

Quality: 52/100 (Good) | Auth: API Key required

Verdict Summary: Choose DAG Studio MCP if you need specialized Data Science Tools tools running via a hosted cloud SSE transport. Choose Discovery Engine if your workspace requires Data Science Tools integration with local subprocess execution. Both servers can be configured concurrently in your client's mcpServers manifest.

Which MCP Server Should You Choose?

Choose DAG Studio MCP when:

You need dedicated capabilities in the Data Science Tools domain.
You prefer remote streaming HTTP/SSE transport architecture.
Your security boundary fits: No auth required (Free / Open Source).
Primary tools included: analyze_dag, parse_dagitty, generate_code.

Explore DAG Studio MCP Details

Choose Discovery Engine when:

You need dedicated capabilities in the Data Science Tools domain.
You prefer local stdio subprocess transport architecture.
Your security boundary fits: API Key required (Freemium).
You have access to required keys: DISCOVERY_API_KEY.
Primary tools included: Feature interaction and subgroup discovery, Hold-out validation with FDR-corrected p-values, Effect sizes, support counts, and novelty classifications.

Feature & Specification Comparison

Specification	DAG Studio MCP Data Science Tools	Discovery Engine leap-laboratories Data Science Tools
Summary	Causal DAG analysis: backdoor paths, adjustment sets, bias simulation. Validated against dagitty.	Superhuman exploratory data analysis that finds the feature interactions and subgroup effects that LLMs and manual exploration miss — with p-values, effect sizes, and literature citations. Data goes in, validated insights come out. Free for public data.
Category & Scope	Data Science Tools

Tools & Capabilities Breakdown

DAG Studio MCP Tools (9)

analyze_dag

Backdoor paths, minimal sufficient adjustment sets, identifiability

parse_dagitty

Parse dagitty DSL (raw or R-wrapped) into the structured DAG model

generate_code

R / Python analysis code for a DAG, plus a one-click DAG Studio URL

check_overadjustment

Detect adjustment for mediators, colliders, and descendants of exposure

simulate_data

Simulate data from a DAG under user-specified structural coefficients

compute_bias

Empirical bias of an adjustment strategy against the simulated truth

Ready-to-Paste Client Configurations

Paste either (or both) of these JSON server blocks into your client config file (e.g. claude_desktop_config.json or ~/.cursor/mcp.json).

DAG Studio MCP Configuration

mcpServers (Claude Desktop / Cursor)

{
  "mcpServers": {
    "dag-studio-mcp": {
      "url": "https://dagstudio-mcp.blackswancausallabs.com/mcp"
    }
  }
}

Discovery Engine Configuration

mcpServers (Claude Desktop / Cursor)

{
  "mcpServers": {
    "leap-laboratories-discovery-engine": {
      "command": "uvx",
      "args": [
        "discovery-engine-api"
      ],
      "env": {
        "DISCOVERY_API_KEY": "YOUR_DISCOVERY_API_KEY_HERE"
      }
    }
  }
}

Frequently Asked Questions

DAG Studio MCP is categorized under Data Science Tools and uses a remote streaming HTTP/SSE transport. In contrast, Discovery Engine belongs to Data Science Tools using local stdio subprocess. Select DAG Studio MCP when you need capabilities focused on data science tools and Discovery Engine when you require tools for data science tools.

More alternatives to DAG Studio MCP More alternatives to Discovery Engine Data Science Tools category hub