Data Science & Analytics MCP servers let an AI assistant work directly with the systems where metrics, experiments, forecasts, charts, and research workflows already live. Instead of copying CSVs into chat or manually describing a dashboard, you can have the assistant query product analytics, inspect Grafana dashboards, generate charts, run forecasting workflows, search database documentation, or produce publication-ready plots through a standard MCP connection. The result is faster analysis with less context loss: the assistant can pull the data, reason over it, and return something usable like a chart, a summary, a SQL fix, or an experiment readout.
This category is most useful for data scientists, analytics engineers, product teams, ML researchers, and backend developers who regularly move between dashboards, notebooks, databases, and reporting tools. It's also useful for engineers who need operational visibility into metrics without becoming dashboard librarians. If your team tracks feature adoption in PostHog, monitors systems in Grafana, works with warehouse data in Fabric, or builds forecasts and plots in Python, these servers turn the assistant from a text-only helper into something that can actually inspect the numbers and produce analysis artifacts.
“Pull the last 30 days of activation, retention, and feature adoption trends from PostHog, break them down by signup cohort, and summarize the biggest drop-offs using mcp-posthog.”
viamcp-posthog“Query the Grafana dashboards for API latency, error rate, and p95 response time after the latest deploy, then identify which service regressed using mcp-grafana.”
viamcp-grafana“Generate a dual-axis line chart of weekly revenue and active users from this dataset and return the chart config and image using mcp-server-chart.”
viamcp-server-chart“Run a 12-week forecast on daily order volume, compare the top candidate models, and report the most accurate projection with confidence bands using autots.”
viaautots| # | Server | Stars |
|---|---|---|
| 1 | Labelhead Artist Momentum This MCP server is a thin wrapper around the Paperclip REST API, exposing Paperclip data and actions through MCP tools without talking directly to the database or reimplementing business logic. It supports read and write operations for entities like issues, documents, approvals, projects, goals, comments, agents, and inbox data. | 73.6k |
| 2 | PostHog MCP Server PostHog MCP is a Model Context Protocol server for interacting with PostHog projects and data. It exposes tools for tasks like feature flag management, analytics queries, experiments, error tracking, dashboards, and other PostHog features, with optional feature-based filtering. |
It can query analytics systems, inspect dashboards, generate charts, run forecasting tools, search technical documentation, and return concrete outputs like summaries, SQL changes, plots, or anomaly reports. The assistant uses the server's tools directly instead of relying on pasted screenshots or manually copied data.
No. Product engineers, analytics engineers, SREs, and founders use them to answer metric questions, inspect dashboards, validate releases, and produce quick visualizations without switching between five tools. They are useful anywhere a developer needs facts from data during a conversation.
An MCP server gives the assistant live access to the source system or analysis tool. That means it can pull fresh data, rerun queries, inspect dashboards, and generate repeatable outputs instead of reasoning over a one-off file snapshot.
Usually several. Teams often combine one server for product analytics, one for dashboards, one for chart generation, and one for forecasting or research workflows so the assistant can move from raw metrics to visualization to interpretation in a single thread.
1,255 servers
paperclipai
Trending hip-hop artist momentum scores across four cultural dimensions.
posthog
Official PostHog MCP Server for product analytics, feature flags, experiments, and more.
open-metadata
Official OpenMetadata MCP: governed context and business semantics for AI assistants and agents.
antvis
A Model Context Protocol server for generating charts using AntV.
grafana
An MCP server giving access to Grafana dashboards, data and more.
microsoft
MCP tools for interacting with Microsoft Fabric
nteract
Render React data visualizations from JSON. 43 chart types; validate, diagnose, suggest tools.
dgunning
SEC filing intelligence — insider sentiment, material events, financial ratios, disclosure search.
llmsresearch
Generate academic diagrams and statistical plots from text using multi-agent AI.
timescale
Comprehensive PostgreSQL documentation and best practices, including ecosystem tools
nowork-studio
Google Ads MCP - analyze performance, manage keywords, bids, and campaigns.
mims-harvard
1000+ scientific tools for AI scientists: life science, reserach, literature, and more.
winedarksea
Automated time series forecasting with model search, anomaly detection, and event risk analysis
yifancong
An MCP server that provides build analysis and optimization recommendations for Rspack projects.
SonoTommy
AI-powered OSINT agent & MCP server. 16 tools: email, breach, IP, WHOIS, DNS, Shodan, GitHub & more.
marmotdata
Open-source data catalog. Search assets, explore lineage, and find ownership.
samvallad33
Local-first cognitive memory server for AI agents with SQLite, smart ingest, and portable sync.
levnikolaevich
Research graph MCP for hypotheses, goals, runs, source quality, audits, and generated maps.
r-huijts
MCP server for accessing Strava API
koreal6803
Quantitative trading toolkit with 900+ data columns, backtesting, and 60+ strategy examples.
maxanatsko
Power BI MCP server (Supports Windows and macOS)
surendranb
An MCP server that provides [describe what your server does]
SepineTam
Let LLM help you achieve your regression analysis with Stata
xiaojiou176-open
Read-only MCP server for CortexPilot workflows, queue state, proof, replay, and incident summaries.
opendatalab
Parse PDFs, images, doc, docx, ppt, pptx, xls, xlsx, html into Markdown using MinerU API.
xquik-dev
Real-time X (Twitter) data: 120+ API endpoints, search, bulk extraction, writes
shashankswe2020-ux
MCP server for WHOOP health data — recovery, sleep, workouts, cycles, and trends.
wso2
MCP server providing seamless access to FHIR APIs for AI tools and healthcare applications
benseverndev-oss
Find duplicate records in 30 seconds. Zero-config entity resolution, 97.2% F1 out of the box.
pouyahasanamreji
Shared memory + orchestration for your coding agents. Local-first MCP, vector RAG.
yuvalsuede
Persistent memory + git snapshots for Claude Code. Never lose context or code.
ai.smithery
Map text into knowledge graphs to create a structured representation of conceptual relations and t…
kunwar-shah
Persistent memory + FTS5 search MCP server for Claude Code conversation history.
astrogilda
Read-only time-series bootstrap server: diagnose a series and compute confidence intervals.
ai.smithery
Search arXiv and ACL Anthology, retrieve citations and references, and browse web sources to accel…
keboola
Connect your AI assistants to Keboola and expose your data, transformations, SQL queries, ...
yuna0x0
AniList MCP server for accessing AniList API data
NameetP
PDF-to-Markdown router. Per-page backend selection + confidence scoring for RAG ingestion.
tocharianou
Kibana MCP Server with dynamic API discovery and comprehensive Elastic Stack integration
dnotitia
Git-backed org memory for AI agents — hybrid search, tables, files & a URI graph over MCP.
ralfbecher
API-first semantic layer MCP server compiling YAML models into dialect-specific SQL
Battam1111
Agent-first cognitive substrate: 20 verbs + 50 lint dims over a self-validating graph.
“Create a publication-quality box plot and regression figure for this experiment dataset and export both as clean vector graphics using paperbanana.”
viapaperbanana“Search the PostgreSQL and TimescaleDB docs for the right pattern to speed up this window-function query and rewrite the SQL with an index recommendation using pg-aiguide.”
viapg-aiguide“Analyze the latest Rspack build report, find the largest bundle growth since last week, and point to the loaders or modules causing it using rsdoctor.”
viarsdoctor| 3 | Openmetadata Mcp OpenMetadata is a unified metadata platform for data discovery, data observability, and data governance. It centralizes metadata storage and APIs, and ingests metadata from many data sources through connectors. | 14.5k |
| 4 | Mcp Server Chart TypeScript MCP server for generating charts and simple tabular visualizations from data using AntV. It exposes tools for many chart types, including common charts, maps, diagrams, and spreadsheet/pivot table rendering. | 4.2k |
| 5 | Mcp Grafana The Grafana MCP server provides access to a Grafana instance and its ecosystem, enabling various operations such as querying dashboards, managing datasources, and handling alerts. | 3.2k |
| 6 | Microsoft Fabric MCP Server Model Context Protocol (MCP) is an open protocol that standardizes how applications provide context to large language models (LLMs), allowing AI applications to connect with various data sources and tools in a consistent manner. | 2.9k |
| 7 | Semiotic Semiotic is a React data visualization library that includes charts, network graphs, geographic maps, realtime charts, and coordinated views. It also provides an MCP server and schema/validation tooling so AI assistants can generate and render chart code reliably. | 2.7k |
| 8 | edgar.tools SEC Intelligence EdgarTools is a Python library for accessing SEC EDGAR filings as structured data, allowing users to parse various filing types into Python objects. | 2.5k |
| 9 | Paperbanana PaperBanana is an agentic framework for generating publication-quality academic diagrams and statistical plots from text descriptions, supporting multiple AI providers. It allows batch generation of diagrams and plots from manifest files. | 2.1k |
| 10 | Pg Aiguide pg-aiguide enhances AI coding tools by providing semantic search and AI-optimized best practices for PostgreSQL, TimescaleDB, and PostGIS documentation. | 1.8k |