Side-by-Side Model Context Protocol Comparison
Stella MCP vs Growthbook MCP
In-depth architectural comparison of the Stella MCP and Growthbook MCP 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
Stella MCP
Data Science Tools · Local stdio
Quality: 57/100 (Good) | Auth: No auth required
Growthbook MCP
Data Science Tools · Local stdio
Quality: 67/100 (Great) | Auth: API Key required
Verdict Summary: Choose Stella MCP if you need specialized Data Science Tools tools running via a local process. Choose Growthbook MCP 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 Stella MCP when:
- You need dedicated capabilities in the Data Science Tools domain.
- You prefer local stdio subprocess transport architecture.
- Your security boundary fits: No auth required (Free / Open Source).
- Primary tools included: create_model, build_model, add_variables.
Choose Growthbook MCP 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 (Free / Open Source).
- You have access to required keys:
GB_API_KEY, GB_API_URL, GB_MCP_TRANSPORT, GB_MCP_PORT, GB_MCP_HOST, GB_MCP_URL, GB_OAUTH_ISSUER, GB_SKILLS_ENABLED. - Primary tools included: growthbook_api_read, growthbook_api_write, growthbook_list_skills.
Feature & Specification Comparison
Tools & Capabilities Breakdown
Stella MCP Tools (42)
create_model
Create a new Stella model with specified time settings
build_model
Create and populate a model in one call: sim specs, stocks, auxiliaries, flows, connectors, and modules. All-or-nothing — on any item error nothing is registered and the error names the failing item (stage + index). Connector sync and validation run by default, so the response doubles as an inspection.
add_variables
Add multiple stocks, auxiliaries, flows, connectors, and/or modules to an existing model in one call. All-or-nothing — on any item error the model is left unchanged and the error names the failing item (stage + index).
set_sim_specs
Update simulation time settings on an existing model
add_stock
Add a stock (reservoir) to the current model
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).
Stella MCP Configuration
Growthbook MCP Configuration