MCP App Store
by KeenEthics

Category Hub

Data Exploration apps and integrations

Data Exploration apps connect AI assistants to databases, warehouses, lakehouses, data catalogs, and analytics platforms for natural-language search, querying, analysis, and visualization. Depending on the app, they can surface governed definitions, metadata, lineage, and data-quality context, while access controls and audit trails limit what users can view or change.

262 apps

Top data exploration apps

Open full directory →
Data-Analytics
Solo Cloud

Solo Cloud

By Rogii Inc.

Solo Cloud by Rogii is a cloud platform that connects geologists, geosteerers and drilling teams around shared well data. This connector lets Claude read and update Solo projects through the Solo Public API, acting as the signed-in user and seeing only the projects and objects that user can already access. What Claude can do: - Browse projects and virtual projects; find wells (laterals), typewells and nested wells by project, API number or well list - Read and edit trajectories (replace or extend surveys), uncertainty ellipses, well metadata, attributes and attached files - Work with logs, mudlogs and image logs: list by log family, read curves, upload, replace or extend data - Manage formation tops, topsets and zones; link typewells to laterals - Review and edit geosteering interpretations: segments, horizons, earth models, auto-typewell shifts, target lines and bit projection - Pull real-time drilling data: time- and depth-indexed traces, rig activity and KPIs, slide sheet intervals - Use map context: grids, polygons, well sticks, nearby wells and multi-well trajectories - Manage completions and stages, production curves and tool codes - Collaborate: comments, starred objects, locks, project history and recently changed objects Typical uses: load survey or log data from files, QC logs and surveys, build a dashboard from Solo well data, draft a geosteering or drilling performance summary, or see what changed in a project today. Units follow each project's settings (feet, meters or mixed). Create calls are safe to retry without duplicates, and all access follows existing Solo permissions.

Tools: 221

View details →
Business & Operations
Monask

Monask

By Recipeon

Monask helps users inspect read-only ERP data from their authenticated organization, including inventory, lots, sales orders, wholesale sales, purchases, customers, vendors, warehouses, promotions, tax invoices, transaction statements, and accounting closings.

Tools: 195

View details →
Data-Analytics
Omniscope

Omniscope

By Visokio

Data to insight. Yours to own. Omniscope connects Claude to data preparation, analytics and interactive reporting in Omniscope. Connect and prepare data, build and run visual workflows, analyse results and create interactive reports, all through conversation. Inspect every step, verify the outputs, and keep a project you can edit and reuse. What will you build? - Interactive reports from scattered files: combine Excel or CSV data, join tables, add KPIs and filters. - A clearer view of your business: analyse sales, renewals, campaigns or operations, and compare segments. - Repeatable data preparation: clean, blend, reshape, aggregate and validate data in reusable visual workflows. - Advanced analytics: forecasting, clustering, statistical and machine learning blocks. - Explanations for unexpected results: trace a field to its source and find which step drops rows. - Improvements to existing projects: change a formula, filter or join, then rerun and inspect the output. From conversation to a project you control Start with your own data, an existing project or a template. Claude can add small data files directly; larger files are uploaded in Omniscope. Open the project in Omniscope to explore the report and refine the workflow. Secure and in your control - Sign in with your Omniscope Cloud account using OAuth. Claude works only within your permissions; revoke access any time. - Every tool is labelled read-only or making changes, and changes need editor permission: a viewer can only read. The connector cannot set passwords or other credentials; connections use credentials set up in Omniscope. Running a workflow executes its output blocks, which may write files, update databases, publish data or send email. Built by Visokio, the creators of Omniscope. Requires an Omniscope Cloud account enabled for AI-agent access; contact support@visokio.com.

Tools: 128

View details →
Productivity
Softr

Softr

By Softr

Softr is an AI app builder that turns your data into apps, portals, and automations. This connector gives ChatGPT direct access to your Softr workspace, so you can go from an idea to a working, published app in a single conversation. Databases: create tables and the fields to match your project, structure and import records, and browse data sources you have already connected. Applications: generate an app on top of your data, add and arrange pages and blocks, configure sign-up and login, set user groups and page permissions, and manage app users. Extend any page with a custom code block that ChatGPT writes for you, with every version saved so you can roll back. Workflows: build multi-step automations with triggers, actions, and branching logic, test each step against real data, and publish when it works. ChatGPT can preview the result and, when you ask it to, publish live. Everything it makes appears in Softr Studio exactly like work done by hand, so you and your team keep editing in the visual builder afterward - nothing is locked into the chat. Day to day, ChatGPT can also work with your data directly: search, filter, and aggregate records, and create or update them in bulk. Every action runs with your own permissions, and you choose the access level per workspace when you connect: read-only, edit, or full access.

Tools: 125 · Prompts: 3

View details →
Productivity
OSO

OSO

By OSO

OSO (Open Source Observer) is an AI-native data platform that centralizes an organization's strategic data on one secure platform, accessible to teams of humans and agents alike, so decisions and insights happen in minutes instead of months. OSO isn't a data warehouse replacement. It's a strategic problem-solving layer that sits on top of your existing data warehouses, BI tools, and notebooks, turning scattered raw data into trustworthy, actionable insight.

Tools: 119

View details →
Productivity
Moonwalk

Moonwalk

By Monorail Inc.

Moonwalk is where you write boards: pages that hold text alongside live tables, charts and interactive widgets, which you can keep private or publish as a public page. This connector lets Claude write and maintain those boards with you, and build the data and machinery behind them. What Claude can do with it: - Boards: read, search and write pages, reorganize them, and publish a board as a public page. - Data for your boards: create tables, read and write rows, and run read-only SQL queries whose results show live on a board. - Widgets: build interactive screens (charts, forms, dashboards) that sit on a board, and see a picture of what it built. - Automations: create workflows in Python that keep a board's data current, running on a schedule, from a webhook or by hand, and read each run's results. - Files: browse, search, read and edit the files in your base, and upload new ones. - Connections: see which third-party accounts and keys your base holds, and ask you to add one. Claude never sees or types a secret; you enter it in Moonwalk. Safe to hand to an agent: - Everything Claude changes is recorded as yours, with Claude noted as the agent. - Deleted boards, tables, widgets, automations and files go to a 30-day trash and can be restored. - Edits are versioned, and a batch of row changes can be undone in one step. - Tools are labeled read-only or destructive, so Claude asks before it changes anything. Requires a Moonwalk account (sign up at moonwalk.now). You sign in and approve access on Moonwalk's own screen, and can revoke it at any time from Moonwalk's Agents page.

Tools: 112 · Prompts: 3

View details →
Business & Operations
Pendo

Pendo

By Pendo

The Pendo connector for product analytics and behavioral data to AI environments. Access visitor and account metadata, query user behavior, and analyze pages, features, and events. Supports real-time product data integration for tasks like customer call preparation, adoption analysis, churn investigation, and support ticket enrichment.

Tools: 100 · Prompts: 1

View details →
Data-Analytics
Qlik

Qlik

By Qlik

Connect to your Qlik Cloud tenant to work with trusted, governed data and analytics. Search and explore apps, datasets, and data products; inspect schemas, profiles, and trust scores; query and filter data with natural language; and build dashboards by creating sheets, charts, and KPIs. Manage governed assets like glossary terms, master dimensions and measures, and trace lineage end-to-end. Qlik MCP combines Claude's reasoning with Qlik's analytics engine so decisions are grounded in your organization's approved data.

Tools: 93

View details →
Productivity
Fibery

Fibery

By Fibery Inc.

Fibery is an operating system for orgs run by nerds: a modular work platform where you build the tools your team runs on. Startups, agencies, enterprises and non-profits use it for everything from product roadmaps and customer feedback to sales CRM, hiring, OKRs and client projects. Everything can link to everything else, so work never gets lost between teams. This plugin connects Claude to your workspace and teaches it how to build in Fibery. Describe how your team works, and Claude builds it. Sprints and bug tracking, a content calendar, a company wiki, or a process no template covers: explain it in your own words, or start from a process doc or a ready-made recipe like Shape Up. Claude asks what it needs to know, then sets up the databases, workflows, views and automations, with sample data to try it on. Want a priority field or a board grouped by stage? Just ask. Happy with the result? Save it as a recipe for the next team. When views aren’t enough, ask for an app. Claude can build a custom app on your Fibery data, like a step-by-step intake form or a dashboard your CEO actually reads. Your data stays in Fibery, with its permissions and history intact. Ask the way you’d ask a colleague. “Which customers asked for the features we shipped last month?” “What happened with the Acme deal this week?” “Who’s still waiting on interview feedback?” Claude searches records, documents, comments and activity history to answer, and turns the answers worth keeping into live reports. Let routine work run itself. Set up rules and buttons in plain words: when a deal is won, create the onboarding project; when a bug turns critical, assign it and set a due date. Put your data to work. Draft release notes from what shipped this month, write a client update from open tasks, turn meeting notes into assigned tasks, or update a hundred records at once.

Tools: 83

View details →
Developer-Tools
Lathe

Lathe

By John Opera

Lathe runs your app, PostgreSQL database and auth on one dedicated machine, with one flat monthly bill. This connector lets Claude inspect instances and billing, deploy apps, read logs, manage engine settings, storage buckets and auth users, within your account role. Destructive actions require action-specific confirmation values. Eight tools return a confirmation string bound to the instance, action, resource and submitted values. Deletes, resets and restores keep their existing typed confirmations. Paid upgrades are financial transactions. The first call returns approval_required with old and new monthly prices, estimated amount invoiced now, downtime and a portal link. The person approves the price there; a repeat call within ten minutes commits only while terms still match. New paid instances use a checkout page the person opens and pays. Redis and PostgreSQL console write enablement also requires portal approval, scoped to the instance, engine and database. Free costs $0 with no card, 1000 GB monthly traffic and no daily backups. Paid plans are $15-$89 per month, billed in USD.

Tools: 87

View details →
Productivity
Weld

Weld

By Weld Technologies

Weld connects your AI agents directly to your data warehouse and the tools your business runs on. Claude can provision, monitor, and adjust real ETL infrastructure: ingesting data from source systems, transforming it with SQL, and syncing clean, current data back out to the tools your team uses, all on schedules Claude can create and manage itself. Ingest (ELT): Create and manage syncs that pull data from source connections into the warehouse, monitor sync health, and trigger refreshes or on demand runs. Transform: Write, publish, and version SQL transforms against warehouse tables, with view and table materialization and independent scheduling. Orchestrate: Chain syncs and transforms into scheduled workflows so pipelines run end to end without manual intervention. Activate (Reverse ETL): Push modeled data back into downstream tools such as CRMs and ad platforms, with configurable insert, update, upsert, and mirror logic and field level mapping. Query: Run ad hoc SQL against the warehouse for exploration, validation, or answering data questions in real time. Because every stage of the pipeline is exposed as a tool rather than a dashboard, Claude does not just report on your data, it can act on it: investigating a failed sync, adjusting a transform when logic changes, or extending a workflow to a new destination, all within the same conversation where the need came up.

Tools: 83

View details →
Data-Analytics
Conjointly

Conjointly

By Conjointly

The Conjointly MCP server lets AI assistants work with your Conjointly data. Once connected, you can ask about your experiments in plain language: list your studies, read reports and analysis results, check respondent quality, start analyses and request exports, without writing any code. The Conjointly MCP server is safe: i.e. it prevents Claude from interfering with your research. The MCP server cannot create, change or delete your experiments, reports, settings or respondent data.

Tools: 77

View details →
Productivity
Bonsai Solutions

Bonsai Solutions

By Bonsai Solutions

Bonsai is the analytics workspace for marketplace and Amazon brands and agencies. This connector lets Claude read the same dashboards you already use in Bonsai — Vendor, Advertising, Rank & Price, Seller, FBA, Feedback, and catalog health — without a database password or a free choice of tenant. Connect once with OAuth. Company users sign in to their Bonsai account; agencies sign in to Bonsai Agency, pick an allowed tenant, then query. Tools are read-only except switching the active agency tenant. Dates use YYYY-MM-DD. Ask for a KPI summary first, then the product/SKU table if you need rows. You need an active Bonsai account with the relevant marketplace and Amazon analytics modules enabled and data already in the workspace. Claude does not call Amazon SP-API directly and does not write Vendor, Ads, or Seller data.

Tools: 70

View details →
Data-Analytics
BEEM

BEEM

By BEEM

Browse, query, and analyze your BEEM data directly from Claude. Connect Claude to your BEEM workspaces and datasets to explore data, run natural language queries, and surface insights without leaving the conversation. Make BEEM a native part of your AI workflow — an intelligent data layer that lets you investigate pipeline performance, ad metrics, and operational data faster, with no SQL required.

Tools: 69

View details →
Developer Tools
Embrasure

Embrasure

By Embrasure

Embrasure helps ChatGPT and Codex investigate silent data failures without querying arbitrary warehouse rows. Inspect table health and Scout evidence, trace table- and column-level lineage, identify downstream services and owners, and understand blast radius before a change. Reads respect workspace permissions. Scout changes always require preview and explicit approval.

Tools: 68 · Prompts: 3

View details →
Developer Tools
Upstash Redis

Upstash Redis

By Upstash

Manage your Upstash resources from ChatGPT through the hosted Upstash MCP server (OAuth on first use): create and inspect Redis databases and run commands on them, publish QStash messages and manage schedules, build Vector and Search indexes, and drive Box sandboxes and Blob storage. Credentials stay on the server and are returned only when you ask for them.

Tools: 63 · Prompts: 3

View details →
Productivity
Vasco

Vasco

By Vasco

Vasco is the revenue context graph that sits under your AI. It connects the systems that already hold most of your revenue context. It gives them one schema, one set of identities, and one set of definitions. This connector opens that graph to Claude. Claude reasons well on what it can read. It cannot know what an SQL means at your company. It cannot know that a Stripe customer and a HubSpot company are the same account. It cannot know your target for the quarter. It cannot know that the last four deals with this pattern were lost. None of that lives in your data, so no model will infer it. Vasco holds it. Identities are resolved, so one account is one account. Definitions are authored by you, so a metric means the same thing every time. The plan is loaded, so every number arrives with its target and its variance. Outcomes are tagged, so today's deal is compared against the ones that already closed. This connector hands all four to Claude. Every metric Claude returns carries a source and a definition you wrote. Claude traces a number back to the signal that moved it. It reads and writes your ICPs, your source mappings, and your go-to-market team model. You stay the author. Claude reasons on what you defined, not on what it inferred.

Tools: 62

View details →
Data-Analytics
DecisionRules

DecisionRules

By DecisionRules

This MCP server exposes the authoring and execution surface for decision tables, lookup tables, and scripting rules directly to AI agents. With it, an agent can: Create and update decision tables, lookup tables, and scripting rules, including folder structure, tags, and versioning. Evaluate (solve) any published or draft rule against real input data and get the decision output back. Run and manage automated test suites against rules before publishing. Check dependencies between rules, find duplicate decision-table rows, and lock rule versions to prevent accidental edits. Use a built-in AI-authoring tool to generate a decision table, lookup table, or scripting rule from a plain-language description. This makes it possible to go from "describe the business logic" to "a tested, versioned, live rule" without leaving the chat.

Tools: 60

View details →
Developer Tools
dbt

dbt

By dbt Labs, Inc.

Discover, query, run, and manage your dbt projects directly from Claude. Browse models, sources, and lineage; query metrics from the semantic layer; and trigger jobs on the dbt platform. Make dbt a native part of your AI workflow that helps you understand your project, ship changes, and answer questions from your data faster, with full context and less friction.

Tools: 60

View details →
Developer Tools
Aiven

Aiven

By Aiven Oy

Aiven official plugin to provision and manage PostgreSQL, Kafka, and other data services on Aiven. Includes the Aiven MCP Server for project, service, and database management, Kafka topics and connectors, PostgreSQL queries, integrations, and application deployment directly from your AI assistant.

Tools: 58

View details →
Ultipa

Ultipa

By Ultipa

Model Context Protocol server for Ultipa Cloud and any self-managed Ultipa GQLDB instance. Provision and operate instances, run GQL queries and graph algorithms, manage backups and firewall rules, and view metrics and billing — all through natural language.

Tools: 57

View details →
Data & Analytics
Querypanel

Querypanel

By CSABA IVÁNCZA

QueryPanel lets an AI agent configure analytics for a SaaS product without bypassing workspace permissions. Connect data sources, inspect schema context, generate and execute SQL, train business knowledge, and create charts or dashboards through one OAuth-protected MCP server. The workspace identity comes from the validated OAuth token, so tool arguments cannot switch organizations. Database credentials and private SDK keys are not returned by read tools.

Tools: 56 · Prompts: 3

View details →
Data & Analytics
GIS Cloud

GIS Cloud

By GIS Cloud

GIS Cloud is an AI-native, cloud GIS platform. Instead of clicking through a desktop GIS, you describe what you want and Claude does it across your whole account, covering the full lifecycle from field data capture to maps, analysis, apps, and reports. The GIS Cloud MCP server lets Claude create and style maps and layers, add, edit, and query features, run spatial analysis and structured SQL over your data, build Mobile Data Collection forms for field teams, import files into PostGIS tables, manage tables, datasources, and bookmarks, render live interactive maps, and generate PDF and Excel reports. It works through a propose-confirm model, so you approve every write and destructive actions are clearly flagged, with account-scoped OAuth access. ISO 27001 certified, serving organizations in 60+ countries. Where GIS Cloud fits your workflow: In the field: "Create a Mobile Data Collection form for pothole inspections with severity, surface type, and photo fields, then bind it to a new layer so my crew can start collecting today." On the map: "Import this CSV of asset locations, put it on a new layer, and color the points by condition rating." Through analysis: "Find every parcel within 200 meters of the flood zone, then list the ten largest by area." End to end, in one ask: "Map last month's bridge inspections, flag anything rated poor, and generate a PDF report with the inspector photos and notes."

Tools: 55 · Prompts: 3

View details →
Developer-Tools
Aiven MCP

Aiven MCP

By Aiven

Manage your Aiven cloud data platform in plain language. The Aiven MCP connects Claude to your fully managed PostgreSQL, Apache Kafka, and application infrastructure, so you can provision, query, and operate services through conversation instead of the console or CLI. Managed PostgreSQL: Provision and configure Postgres services, run read and write SQL, manage PgBouncer connection pooling, inspect pg_stat query statistics, and tune slow queries with AI-powered query optimization. Apache Kafka & streaming: Create and manage topics, produce and consume messages, set up Kafka Connect source and sink connectors, and browse Schema Registry subjects, full event-streaming workflows from a chat. Application deployment: Deploy your Dockerized apps to Aiven directly from your connected GitHub repositories, and rebuild or redeploy in a single request. Observability & operations: Fetch service and application metrics, stream service logs, view live query activity and project event logs, and power services on or off across your projects, clouds, and VPCs. Documentation search: Query the official Aiven documentation in natural language, without leaving Claude. Built for safe, scoped access: - Read-only mode exposes only non-destructive tools. - Service scoping limits the toolset to PostgreSQL, Kafka, applications, or integrations. - Connection credentials are redacted by default.

Tools: 52

View details →

Need a custom data exploration integration built?