> ## Documentation Index > Fetch the complete documentation index at: https://usefulai.com/llms.txt > Use this file to discover all available pages before exploring further. # Best Data Analytics Plugins, Skills, and MCP Servers in 2026 > Research-backed data and analytics plugins, skills, and MCP servers with platform availability and direct setup routes.
Updated July 25, 2026
These extensions let agents reach real databases, warehouses, BI platforms, and product-analytics tools, then run queries and follow repeatable analysis workflows. The main decision is how much access to grant: broad exploration is convenient, but production data usually deserves scoped, read-only credentials.
| # | Name | Best for | Est. installs About install estimates | | ----------------------------------------: | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | :-------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------: | | 1 | MongoDB | MongoDB and Atlas with current practice | **160K** | | 2 | Google Analytics | Read-only GA4 reporting | **150K** | | 3 | DBHub | Guardrailed SQL across five engines | **110K** | | 4 | Neon | Branching serverless Postgres | **100K** | | 5 | Redis | Live Redis data plus app patterns | **85K** | | 6 | Power BI | DAX and Power BI semantic models | **65K** | | 7 | MCP Toolbox for Databases | One gateway to many SQL and NoSQL DBs | **60K** | | 8 | BigQuery | SQL on BigQuery under Google IAM | **60K** | | 9 | PostHog | Product analytics and feature flags | **55K** | | 10 | Snowflake | Governed Snowflake SQL and Cortex | **45K** | | 11 | Chroma | Vector store for RAG and memory | **45K** | | 12 | Tableau | Governed Tableau analytics access | **45K** | | 13 | ClickHouse | ClickHouse schemas, queries, and costs | **40K** | | 14 | DuckDB | Local DuckDB analytics guidance | **40K** | | 15 | Databricks | Governed lakehouse data and AI assets | **35K** | | 16 | Metabase | Governed analytics via your Metabase | **30K** | | 17 | Amplitude | Funnels, experiments, and replays | **30K** | | 18 | Pinecone | Search and RAG on Pinecone indexes | **25K** | | 19 | dbt | dbt models, tests, and MetricFlow | **25K** | | 20 | Mixpanel | Funnels, retention, and taxonomy | **25K** | | 21 | OpenAI Data Analytics | Question-to-dashboard analysis flows | **20K** | | 22 | Looker | Semantic-model-aware BI on Looker | **20K** | | 23 | MotherDuck | Cloud DuckDB queries and Dives | **15K** |
***
MongoDB logo
## [MongoDB](https://www.mongodb.com/docs/agent-skills/)
MongoDB and Atlas with current practice
160Kestimated installs
**What it is** The official MongoDB package brings together the MongoDB MCP Server and reusable skills for schemas, queries, aggregations, indexes, connections, and Atlas workflows, giving an agent both live database access and current MongoDB practice.
**When to use** The result is an agent that inspects and works with MongoDB while grounding its code and database advice in MongoDB's current guidance rather than generic patterns. Keep access read-only and least-privilege until a task clearly needs writes.
**What you need** A MongoDB deployment or Atlas account to connect to.
Install PluginPluginPluginMCP
Google Analytics logo
## [Google Analytics](https://github.com/googleanalytics/google-analytics-mcp) by Google
Read-only GA4 reporting
150Kestimated installs
**What it is** Google's official, experimental local MCP server for the Google Analytics Admin and Data APIs. It exposes read-only tools to list accounts and properties, inspect custom dimensions and metrics, and run core, funnel, and realtime GA4 reports.
**When to use** Use it to answer analytics questions - traffic, conversions, funnels, and realtime activity - directly against GA4 instead of exporting reports by hand. Access is read-only by scope, so it reports on data but cannot change GA configuration. Marketers who reach it from the Marketing & SEO guide land here, where it is ranked among data and analytics extensions.
**What you need** A Google Cloud project with the GA APIs enabled and an account with access to the GA4 properties; the server runs locally.
Install MCP
DBHub logo
## [DBHub](https://dbhub.ai/)
Guardrailed SQL across five engines
110Kestimated installs
**What it is** A local MCP gateway for PostgreSQL, MySQL, MariaDB, SQL Server, and SQLite. It deliberately exposes just two core tools, schema and object search plus SQL execution, alongside optional parameterized custom tools.
**When to use** One token-efficient interface covers several database engines, and the guardrails are the real draw: read-only mode, row limits, query timeouts, and TLS/SSH support. Use a dedicated least-privilege account regardless, and keep the server off untrusted networks.
**What you need** A local gateway process plus a least-privilege account on the database it queries.
Install MCP
Neon logo
## [Neon](https://neon.com/docs/ai/ai-agents-tools)
Branching serverless Postgres
100Kestimated installs
**What it is** An integration that pairs Neon's Serverless Postgres skill with the Neon MCP Server for live project and database work. The agent can provision databases, create branches, run queries and migrations, and validate connections while following current Neon patterns instead of generic Postgres advice.
**When to use** Reach for it when an agent needs to build against or manage a Neon database. Neon positions the MCP as a development and testing tool, and with write access it can perform destructive database and project operations, so favor read-only and project-scoped restrictions for casual work.
**What you need** A Neon account and project.
Install PluginPluginPluginMCP
Redis logo
## [Redis](https://redis.io/docs/latest/integrate/redis-mcp/)
Live Redis data plus app patterns
85Kestimated installs
**What it is** Redis gives agents live database access through its official MCP server plus coding guidance through official skills. The MCP covers data structures, keys, and query, search, and vector operations with read and write access; the skills carry Redis application patterns.
**When to use** Use the MCP for operational work against a real instance and the skills for correct Redis application design. Because the server can write, connect it with tightly scoped ACL credentials and prefer read-only or narrow permissions until a task clearly needs more.
**What you need** A Redis connection URI; scope it with a least-privilege ACL user.
Install PluginMCP
Power BI logo
## [Power BI](https://github.com/microsoft/powerbi-modeling-mcp) by Microsoft
DAX and Power BI semantic models
65Kestimated installs
**What it is** Microsoft's Power BI Modeling MCP for working with semantic models through an agent: inspecting and editing model structure, running DAX queries, and operating across PBIP, Fabric, and Power BI Desktop workflows. It ships as a Public Preview npm package that runs locally.
**When to use** Use it for supervised semantic-model development, where DAX and model work go through structured tools instead of brittle UI automation. It is Public Preview software with write access that can modify models, so work against backups with limited permissions rather than casually against production models.
**What you need** A Windows/local runtime and access to a Power BI model (Desktop, Fabric, or PBIP).
Install MCP
MCP Toolbox for Databases logo
## [MCP Toolbox for Databases](https://mcp-toolbox.dev/) by Google
One gateway to many SQL and NoSQL DBs
60Kestimated installs
**What it is** A server framework that connects agents to a wide range of SQL, NoSQL, analytics, and cloud databases. It can expose ready-made exploration tools for quick work, or narrowly defined production queries where you control exactly which operations an agent can invoke.
**When to use** The same server works across Claude, Codex, Cursor, and custom frameworks, handling connections, pooling, auth, and observability in one place. The trade-off worth respecting: prebuilt SQL tools are broad and convenient, but sensitive production data should stay behind read-only accounts and scoped, purpose-built tools.
**What you need** A local Toolbox server plus connection credentials for the databases you point it at.
Install MCP
BigQuery logo
## [BigQuery](https://docs.cloud.google.com/bigquery/docs/use-bigquery-mcp)
SQL on BigQuery under Google IAM
60Kestimated installs
**What it is** Google's warehouse offered through three routes: a managed remote MCP endpoint, a managed Claude connector, and a local path via MCP Toolbox for Databases. Agents can discover datasets and tables, inspect metadata, and run SQL.
**When to use** Access runs through existing Google Cloud OAuth, IAM, audit, and billing controls, so data stays inside current governance. Prefer the read-only SQL tool. The managed endpoint caps queries at three minutes and 3,000 returned rows and skips Drive external tables, so large pulls need another path.
**What you need** A Google Cloud account - access runs through your existing IAM, audit, and billing.
Install ConnectorMCP
PostHog logo
## [PostHog](https://posthog.com/docs/model-context-protocol)
Product analytics and feature flags
55Kestimated installs
**What it is** An official integration that combines a hosted MCP connection with more than 30 skills covering product analytics, feature flags, experiments, error tracking, surveys, dashboards, and LLM analytics.
**When to use** It gives an agent live product and production context, then lets it investigate trends and errors or manage PostHog workflows without switching tools. Note that the MCP can write, changing flags, experiments, dashboards, and surveys, so grant that access deliberately.
**What you need** A PostHog account and project.
Install PluginPluginPluginMCP
Snowflake logo
## [Snowflake](https://github.com/Snowflake-Labs/snowflake-ai-kit)
Governed Snowflake SQL and Cortex
45Kestimated installs
**What it is** An official integration that takes two forms. The Claude and Codex plugins delegate Snowflake prompts to Cortex Code, while the Cursor plugin connects to a Snowflake-managed MCP server. Both give agents governed access plus Snowflake-specific skills.
**When to use** Those skills cover SQL, governance, ML, dynamic tables, semantic views, cost, performance, and Cortex services, so an agent works with Snowflake instead of guessing. The two routes share the name but not the same architecture, and queries and Cortex features may consume paid compute.
**What you need** A Snowflake account; Claude and Codex prompts route through Cortex Code.
Install PluginPluginPluginMCP
Chroma logo
## [Chroma](https://docs.trychroma.com/integrations/frameworks/anthropic-mcp)
Vector store for RAG and memory
45Kestimated installs
**What it is** Chroma's official MCP server lets an agent create, query, update, and delete vector-database collections and documents, with vector-similarity, full-text, and metadata-filtered search. It runs self-hosted in ephemeral, persistent-local, self-hosted-HTTP, or Chroma Cloud modes.
**When to use** Reach for it when an agent needs semantic retrieval, a project knowledge base, or explicit persistent memory backed by Chroma. The default ephemeral client loses data on restart, so choose the mode deliberately, and note that collection and document tools can write and delete.
**What you need** A local runtime for the server, or a Chroma Cloud account for the hosted mode.
Install MCP
Tableau logo
## [Tableau](https://tableau.github.io/tableau-mcp/)
Governed Tableau analytics access
45Kestimated installs
**What it is** Tableau MCP gives agents governed access to Tableau content and analytics. It comes two ways: a Tableau-managed remote MCP service for eligible Cloud or Server accounts, and an official open-source server you host yourself.
**When to use** Use it when Tableau already holds your organization's governed analytics and you want the agent to query it while preserving platform permissions. Prefer the managed MCP when your account SKU supports it; use the self-hosted server for self-managed or unsupported environments.
**What you need** A Tableau Cloud or Server account; the managed route depends on account SKU and admin entitlement.
Install MCP
ClickHouse logo
## [ClickHouse](https://clickhouse.com/ai)
ClickHouse schemas, queries, and costs
40Kestimated installs
**What it is** An official agent stack that pairs ClickHouse-specific skills with live, read-only access to ClickHouse Cloud through MCP. The skills carry current database knowledge; the connection lets an agent inspect real services and data.
**When to use** Instead of generic SQL advice, an agent can design schemas, optimize queries and ingestion, troubleshoot clients, and inspect actual Cloud services, schemas, costs, and pipelines. The general Cloud MCP is read-only, so it analyzes rather than changes your data.
**What you need** A ClickHouse Cloud account for the live, read-only connection.
Install PluginPluginMCP
DuckDB logo
## [DuckDB](https://duckdb.org/)
Local DuckDB analytics guidance
40Kestimated installs
**What it is** DuckDB Skills are the project's official, portable agent instructions for the embedded analytical engine - nine skills covering SQL, performance, data formats, extensions, and workflows. They are guidance, deliberately not a live-database MCP.
**When to use** Use them for local analytical work where DuckDB is already the execution engine, so an agent writes correct, performant DuckDB SQL without a hosted account. Keep them distinct from MotherDuck's hosted MCP, which is the cloud service rather than the local engine.
**What you need** Nothing beyond your existing local DuckDB or project - the skills add no service.
Install Skill
Databricks logo
## [Databricks](https://docs.databricks.com/aws/en/agents/mcp/connect-clients)
Governed lakehouse data and AI assets
35Kestimated installs
**What it is** Databricks connects agents to governed lakehouse data and AI assets - Unity Catalog objects, tables, functions, vector search, and Databricks apps - while also shipping an official collection of development skills. Live access runs through Databricks-managed MCP services.
**When to use** Reach for it for Databricks-centric analytics, data engineering, and AI development, where the agent should work against real catalog data without bypassing governance. Distinguish the live MCP access from the portable skills, which carry development knowledge but do not themselves grant workspace access.
**What you need** A Databricks workspace with OAuth or a personal access token; exposed objects follow Unity Catalog permissions.
Install ConnectorPluginPluginMCP
Metabase logo
## [Metabase](https://www.metabase.com/)
Governed analytics via your Metabase
30Kestimated installs
**What it is** An MCP server built into each enabled Metabase instance. It lets an agent search tables and metrics, inspect fields and sample values, build and run queries, create or update Metabase content, and return interactive charts.
**When to use** This gives an agent governed analytics context instead of a raw database connection: results and actions stay scoped to the signed-in user's permissions. Worth knowing that content tools can write, so the same permissions can create or change dashboards, not just read them.
**What you need** A Metabase instance with the MCP enabled; actions stay scoped to your signed-in permissions.
Install ConnectorMCP
Amplitude logo
## [Amplitude](https://amplitude.com/docs/amplitude-ai/amplitude-mcp)
Funnels, experiments, and replays
30Kestimated installs
**What it is** An authenticated product-analytics MCP paired with vendor-authored plugins and skills for analysis, dashboards, experiments, session replay, feedback, taxonomy, and instrumentation, giving an agent governed access to Amplitude projects.
**When to use** It lets an agent query and edit analytics objects, investigate funnels and experiments, analyze replay and feedback, and plan instrumentation, using repeatable workflows instead of generic prompting. One limit worth remembering: the MCP is not an event-ingestion endpoint, so production events still go through the SDK or HTTP API.
**What you need** An Amplitude account and project.
Install PluginPluginPluginMCP
Pinecone logo
## [Pinecone](https://www.pinecone.io)
Search and RAG on Pinecone indexes
25Kestimated installs
**What it is** An official toolkit that pairs vector-database tools with guided skills for semantic search, RAG, full-text search, and Pinecone Assistant. An agent can create and inspect indexes, upsert and search records, and rerank results.
**When to use** This is the integration to reach for when building or operating search, RAG, recommendation, or document-Q\&A features on Pinecone, since the agent both follows the workflow and acts on real indexes and data. The MCP centers on integrated-index operations; the CLI and packaged scripts cover broader or batch work.
**What you need** A Pinecone account and API key.
Install PluginPluginPluginSkillMCP
dbt logo
## [dbt](https://github.com/dbt-labs/dbt-agent-skills)
dbt models, tests, and MetricFlow
25Kestimated installs
**What it is** An official stack that combines analytics-engineering skills with the dbt MCP Server, giving an agent project, semantic-layer, CLI, job, and documentation context for work in a dbt project.
**When to use** With it, an agent can build and test models, use MetricFlow, troubleshoot jobs, work with Mesh, and run dbt commands using current product guidance. The skills help even without live access, though many assume an existing dbt project, and CLI/SQL tools can change models and warehouse state.
**What you need** An existing dbt project; job and semantic-layer routes need a dbt Cloud account.
Install PluginPluginMCP
Mixpanel logo
## [Mixpanel](https://docs.mixpanel.com/docs/mcp)
Funnels, retention, and taxonomy
25Kestimated installs
**What it is** Mixpanel's official hosted MCP connects an agent to product-analytics work: queries, funnels, retention, dashboards, taxonomy, experiments, feature flags, session replays, and data quality. Claude presents it as a connector; Codex has a Mixpanel plugin.
**When to use** Reach for it when an agent needs conversational read and write access to Mixpanel product analytics. MCP access must be enabled by an organization admin, and the server can write data and is not covered for HIPAA at research time, so scope it deliberately.
**What you need** A Mixpanel account with MCP enabled by an admin.
Install ConnectorPluginMCP
OpenAI Data Analytics logo
## [OpenAI Data Analytics](https://openai.com/index/codex-for-every-role-tool-workflow/) by OpenAI
Question-to-dashboard analysis flows
20Kestimated installs
**What it is** A first-party bundle for moving from a business question and authorized data to a validated analysis, chart, dashboard, notebook, report, or recommendation. The live package currently holds 15 skills, 20 optional apps, and 3 app templates.
**When to use** Instead of jumping straight to a confident chart, it routes work through business context, data-quality checks, KPI design, metric diagnosis, validation, and visualization. It draws on uploaded files or connected warehouses, but it cannot make weak or mismatched data trustworthy, so validate definitions, joins, and time windows first.
**What you need** Authorized access to the data you analyze. Currently a Codex-only bundle.
Install Plugin
Looker logo
## [Looker](https://cloud.google.com/looker) by Google Cloud
Semantic-model-aware BI on Looker
20Kestimated installs
**What it is** Looker connects agents to governed analytics through Google's managed MCP service, delivered as an official Claude plugin and as a Preview managed MCP endpoint for other clients. The agent works with Looker's semantic model and analytics tools rather than a raw database.
**When to use** Use it for organizations already standardized on Looker that want semantic-model-aware business intelligence - governed metrics and Explores - instead of raw SQL access. It requires admin enablement, and the managed MCP is a Preview service, so confirm its status before relying on it.
**What you need** A Looker instance with the managed MCP enabled by an admin.
Install PluginMCP
MotherDuck logo
## [MotherDuck](https://motherduck.com/docs/sql-reference/mcp/)
Cloud DuckDB queries and Dives
15Kestimated installs
**What it is** MotherDuck's official integration lets an agent query, prepare, visualize, and manage cloud DuckDB data - reading schemas, running SQL, working with views, and creating shareable Dives. Claude presents it as a connector; Codex has a MotherDuck plugin and app.
**When to use** Use it when an agent should behave like an iterative analyst over MotherDuck data, moving from schema to SQL to a shareable Dive. It is the hosted cloud service rather than the local DuckDB engine, and queries and writes can change data and incur warehouse usage.
**What you need** A MotherDuck account.
Install ConnectorPluginMCP
## Choose by use case

Want one connection that covers many databases?

→ MCP Toolbox for Databases - the broad gateway, with production-grade control over which operations an agent can run

→ DBHub - the deliberately small alternative: two core tools, read-only mode, row limits

Living inside one database product?

→ Official packs ground the agent in your live service - ClickHouse, MongoDB, Snowflake, BigQuery, Redis, Neon

→ Pinecone or Chroma when the job is vector search, RAG, or memory

Prefer the vendor pack over a generic gateway when you are on that product.

Analytical SQL - local engine or cloud warehouse?

→ DuckDB - official skills for the embedded engine, no account needed

→ MotherDuck - the hosted cloud version, with shareable Dives

Product analytics questions to answer?

→ PostHog - analytics plus flags, experiments, and error tracking in one surface

→ Amplitude - funnels, experiments, session replay, and taxonomy work

→ Mixpanel - funnels, retention, taxonomy, and experiments through a hosted MCP

Governed dashboards and semantic models?

→ Metabase - governed BI over your warehouse, scoped to each user's permissions

→ Looker - semantic-model-aware BI on the Google-managed service

→ Power BI - supervised DAX and semantic-model development (Public Preview)

→ Tableau - governed Tableau content through a managed or self-hosted MCP

Web and marketing analytics?

→ Google Analytics - read-only GA4 traffic, conversion, and funnel reporting

Arriving from Marketing & SEO? It is mentioned there and ranked here.

Transforming data, or starting from a business question?

→ dbt - models, tests, MetricFlow, and job troubleshooting with current guidance

→ Databricks - governed lakehouse data, functions, and vector search for analytics and AI work

→ OpenAI Data Analytics - routes work through data-quality checks, KPI design, and validation before the chart

## Related categories Prisma, Supabase, and the database tooling developers wire into an app while building. Cloud platforms, deployment, and the production systems your data sits on. Search performance, ad reporting, and where Google Analytics is cross-referenced.