Simba MCP Server
OfficialRelated Servers
Alternatives to Simba MCP Server
No user-submitted related servers found.
Related Servers
- -licenseNot gradedqualityBmaintenanceConnects AI assistants to marketing mix models, enabling natural language data upload, performance modeling, budget optimization, and scenario testing.-
- AlicenseBqualityBmaintenanceProvides a controlled interface for Bayesian Marketing Mix Modeling, letting AI agents validate datasets, fit and diagnose MMMs, analyze channel contributions and ROI, simulate and optimize budgets, calibrate with lift tests, and cross-validate models—all with statistical verification, uncertainty reporting, and full provenance.333Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables marketing optimization tasks such as copywriting, campaign analysis, social media planning, audience segmentation, and KPI tracking through natural language.MIT

Orphex MCPofficial
AlicenseNot gradedqualityBmaintenanceEnables AI assistants to query advertising spend, ROAS, campaigns, pacing and anomalies across many ad, analytics and commerce platforms, and to make approval-first changes such as pausing campaigns or adjusting budgets after a preview.2Apache 2.0- AlicenseNot gradedqualityCmaintenanceEnables AI agents to query campaign performance, metrics, audiences, and geography, and to analyze budgets, wasted spend, and account health through natural language.1MIT
- AlicenseBqualityCmaintenanceEnables AI assistants and agents to read analytics and manage advertising across Google Ads, Google Analytics 4, and Meta Ads through natural language, with preview-confirm guardrails and configurable account and budget limits.21MIT
TDQS
Scored across 94 tools
Most tools have clearly distinct purposes and descriptions are unusually detailed, but several families overlap subtly: create_incrementality_test vs save_incrementality_test_design vs import_incrementality_tests vs design_incrementality_test, recipe/study authoring tools, and get_model_results vs the show_* chart wrappers. With 94 tools, an agent can still misselect within these clusters even though descriptions help.
Tool names follow a consistent snake_case verb_noun pattern throughout (e.g. create_model, get_model_results, list_study_runs, run_optimizer), with only minor stylistic variants like show_* and diff_*. No camelCase or chaotic mixing is present.
94 tools is far beyond a well-scoped set; even for a complex MMM platform this imposes a very large selection surface and constant risk of wrong-tool choice. The rubric treats 50+ tools as an extreme mismatch.
The surface covers the full lifecycle: data upload/pipelines, model creation, results, diagnostics, optimization, scenarios, studies/recipes/quality policies, campaign mapping, incrementality tests and designs, run history, projects and sharing. CRUD/lifecycle coverage is broad with very few obvious dead ends.