DAG Studio MCP vs Jacobian
A side-by-side look at the DAG Studio MCP and Jacobian MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose DAG Studio MCP for data science tools work over a hosted endpoint; choose Jacobian for data science tools as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose DAG Studio MCP when
- You need dedicated capabilities in the Data Science Tools domain.
- You prefer a remote HTTP/SSE transport.
- You want tools like
analyze_dag, parse_dagitty, generate_code.
Choose Jacobian when
- You need dedicated capabilities in the Data Science Tools domain.
- You prefer a local stdio subprocess transport.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Data Science Tools | Data Science Tools |
| Quality signal | 47/100 · Fair | 49/100 · Fair |
| Install command | Confirmed | Confirmed |
| Transport | Remote HTTP/SSE | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 0 | 322 |
| Directory activity | 2 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 9 | Not listed |
| Full listing | View DAG Studio MCP | View Jacobian |
Tools & capabilities
DAG Studio MCP tools 9
analyze_dagBackdoor paths, minimal sufficient adjustment sets, identifiabilityparse_dagittyParse dagitty DSL (raw or R-wrapped) into the structured DAG modelgenerate_codeR / Python analysis code for a DAG, plus a one-click DAG Studio URLcheck_overadjustmentDetect adjustment for mediators, colliders, and descendants of exposuresimulate_dataSimulate data from a DAG under user-specified structural coefficientscompute_biasEmpirical bias of an adjustment strategy against the simulated truthclassify_effect_modificationClassify effect-modifier structure (direct, indirect, proxy, common-cause, pure interaction)get_canonical_exampleCanonical teaching DAGs (confounding, M-bias, frontdoor, and others)validate_engineRun the full canonical validation suite and report engine version
Jacobian tools
No tool names declared yet. Check the project README from the listing page.
Ready-to-paste client configs
Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
DAG Studio MCP
{
"mcpServers": {
"dag-studio-mcp": {
"url": "https://dagstudio-mcp.blackswancausallabs.com/mcp"
}
}
}
Jacobian
{
"mcpServers": {
"jacobian": {
"command": "npx",
"args": [
"-y",
"jacobian@latest"
]
}
}
}
Frequently asked questions
DAG Studio MCP is categorized under Data Science Tools and uses a remote HTTP/SSE transport. Jacobian belongs to Data Science Tools and uses a local stdio subprocess. Pick DAG Studio MCP for data science tools work and Jacobian for data science tools.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
DAG Studio MCP has no declared pricing — check the project's own site. Jacobian has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add dag-studio-mcp and jacobian as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, DAG Studio MCP has a quality signal of 47/100 (Fair) with 2 views, 0 installs and 0 GitHub stars. Jacobian has 49/100 (Fair) with 1 views, 0 installs and 322 GitHub stars.