Install a business-data playbook
Six reusable skills for MCP setup, customer context, revenue analysis and reliable cross-app queries.
THE COMBINED FIELD GUIDE
Give your agents
better data.
Practical tutorials, working examples and decisions worth getting right before your agent answers a business question. Combined syncs selected business records into managed storage first, then gives your agent read-only SQL through MCP. Query CRM, billing and support data together with the latest successful sync visible.
Find your app. Connect your agent.
Browse hundreds of source-specific setup guides, dataset references and MCP query prompts. Combined offers 1,125 connectors, including connections generated through desktop automation.
What is Combined? Business data for the AI agents you already use
How Combined connects SaaS data, keeps it queryable, and gives external AI agents scoped access through SQL, MCP and SDKs.
Business data for forward deployed engineers: deliver agents with Combined
Use Combined to deliver customer agents with managed business data, Source grants and SQL. A practical plan for schemas, mappings, freshness and client handoff.
Composio review: tools, account scope and repeatable business-data answers
A practical Composio review covering sessions, direct tools, account scope, exports and cost units. See when to choose Combined for managed business-data SQL.
Export business data with Composio: HubSpot contacts to CSV and JSON
Download a bounded HubSpot export example using Composio Proxy, with pagination, CSV, JSONL and completion checks. Choose Combined for maintained business-data SQL.
Composio alternatives: 5 picks for business-data agents
Choose a Composio alternative for your workload. Compare Combined, Nango, Pipedream Connect, Arcade and Paragon, with a migration checklist and evaluation worksheet.
Composio vs Nango: which fits your business-data agent?
Compare Composio and Nango on agent sessions, authorization, syncs, records and cost inputs. See when Combined's managed SQL is the better starting point.
Query business data in Claude Desktop with Combined MCP
Connect Claude Desktop to Combined and build a customer brief from HubSpot, Stripe and support records. Includes current connector steps and a downloadable assignment.
Connect CrewAI to HubSpot and Stripe business data with MCP
Give a CrewAI agent queryable HubSpot and Stripe data through Combined. Download the Python example, pinned dependencies and a local MCP check.
Query HubSpot and Stripe from LangGraph with MCP
Build a LangGraph business-data agent with Combined MCP. Download the graph, authenticated client setup and a local test that preserves structured query results.
Query HubSpot and Stripe from Cursor with Combined MCP
Add business data to Cursor with a ready-to-edit MCP configuration. Discover your HubSpot and Stripe datasets, ask a cross-source question and inspect the SQL.
HubSpot Developer MCP or CRM MCP? Choose for the question you need answered
Choose the right HubSpot MCP connection for app development, CRM access or HubSpot–Stripe analysis. Includes a decision table and a free SQL exercise.
Fix MCP authentication errors when connecting business data
Diagnose MCP 401, 403, missing tools and empty datasets in Cursor or Claude. Follow the connection stages and download a reusable diagnostic worksheet.
Verify your AI agent's business-data answer.
Debug incorrect AI totals, missing business sources and unsupported citations. Inspect twelve cases and download the free Python checker, examples and recorded results.
7 platforms for giving AI agents business data and tools
Choose Combined for synced CRM, billing and SQL context. Compare six agent-tool alternatives, plan your apps and download the business-data selection worksheet.
6 AI agent context platforms: memory and business data
Choose Combined for business-data context, then compare Supermemory, Mem0, Zep, Letta and Cognee for conversational memory and persistent agent context.
Your apps. One useful plan for your agent.
Choose your business apps and get an MCP connection plan, matched SQL tutorials and a ready-to-copy agent prompt. Free Markdown and JSON downloads; no signup needed.
HubSpot–Stripe reconciliation: stop double-counting.
Map HubSpot companies to Stripe customers, fix duplicated totals and inspect missing invoice matches. Try the free lab and download both SQL examples.
Best MCP servers for business data: choose by the job
Compare business-data MCP servers by workload, then choose a Claude Desktop, Cursor, CrewAI or LangGraph setup. Start with Combined for cross-app SQL and a free planning worksheet.
Query HubSpot and Stripe together with your AI agent
Connect CRM and billing context through Combined. Use a customer mapping, a copyable agent prompt and runnable SQL to compare open pipeline with paid invoices without duplicate totals.
Find Salesforce renewal accounts with overdue Chargebee invoices
Give your AI agent a renewal-risk view across Salesforce and Chargebee, with explicit term dates, customer mapping and a runnable overdue-balance example.
Measure paid customer retention with PostHog and Stripe
Join product activation to paid service coverage with an account-level cohort, explicit identity rules and a tested PostHog–Stripe SQL example.
Prioritize valuable Salesforce customers with Zendesk support context
Compare closed-won customer value with unresolved Zendesk tickets using account mappings, distinct ticket counts and a runnable SQL fixture.
Find HubSpot deals that need Intercom support context
Connect open HubSpot pipeline to recent unresolved Intercom conversations, with customer-message rules, a conversation map and tested SQL.
Compare Salesforce opportunities with Stripe payments and balances
Give your agent one account view of open Salesforce pipeline, paid Stripe invoices and remaining balances, with a tested example that handles missing due dates.
Find Chargebee renewals missing a HubSpot deal
Match upcoming Chargebee subscription terms to explicit HubSpot renewal deals, with a per-subscription coverage check and a runnable SQL fixture.
Find HubSpot customers with unpaid QuickBooks invoices
Compare recent won HubSpot deals with current QuickBooks invoice balances, including partial payments and customer subaccounts, using tested SQL.
Find Salesforce renewals with aging Freshdesk tickets
Prioritize renewal accounts using Freshdesk ticket age and priority, with explicit status mapping, missing-account handling and a tested SQL example.
Combined vs Composio: business-data SQL or agent actions?
Compare Combined and Composio for business-data agents: synced SQL, tool execution, access scope, pricing inputs, and a practical CRM-to-billing evaluation.
Combined vs Nango: managed SQL or integration code you control?
Compare Combined and Nango for synced business data. See who owns integration logic, records, SQL, agent access, and custom-field maintenance.
Combined vs Pipedream Connect: agent data or embedded integrations?
Compare managed business-data SQL with Pipedream Connect's embedded auth, tools, and workflows. Includes a two-user evaluation and production cost inputs.
Combined vs Zapier MCP: repeatable business answers or app actions?
Compare Combined SQL with Zapier MCP's reads, writes, dynamic tools, and task billing. Evaluate an exception digest and its authorized follow-up.
Combined vs Merge Unified API: SQL datasets or normalized integrations?
Compare Combined and Merge Unified API for business-data agents: common models, source datasets, custom fields, syncs, and a practical portability evaluation.
Combined vs Workato: self-serve agent data or enterprise orchestration?
Compare Combined with Workato's workflows, enterprise MCP, and context search. Evaluate a revenue exception process from source data to approved action.
Combined vs Glean for cross-app business analysis
Compare Combined and Glean for cross-app analysis: SaaS ingestion, warehouse SQL, MCP tools, source permissions and a runnable Salesforce–Stripe evaluation.
Combined vs Paragon for AI agent data access
Compare Combined with Paragon ActionKit and Managed Sync: query-layer ownership, customer identity, permissions and a Salesforce–Zendesk evaluation.
Combined vs Snowflake MCP: start with business apps or a warehouse?
Compare Combined and Snowflake MCP for business-data agents: managed source sync, SQL, Cortex services, setup, and a Salesforce–Chargebee renewal evaluation.
Combined vs Databricks MCP: turn business apps into agent answers
Compare Combined with Databricks SQL, Genie, and AI Search MCP. Choose your data setup and evaluate paid customer retention across PostHog and Stripe.
Combined vs MotherDuck: managed Sources or flexible data pipelines?
Compare Combined's managed Sources with MotherDuck Flights, SQL and MCP. Evaluate HubSpot–Stripe answers, sync behavior, access and pricing.
Combined vs custom ETL: keep agent answers correct after the first sync
Compare Combined with custom ETL using a runnable replay and recovery drill, Source grants, operating costs, and a Salesforce–Stripe answer contract.
Connect Claude Code to business data with Combined MCP
A practical setup guide: connect a source, grant access, add the MCP server, discover schemas and verify a real query receipt.
Connect HubSpot to your AI agent and ask about pipeline
Turn HubSpot deals into answers in your AI workflow. Follow the connection steps, copy a pipeline-analysis prompt and check it against a simple worked example.
Direct SaaS MCP servers vs. a managed data layer for AI agents
Choose the right path to business context: direct application tools for actions, or Combined for SQL over synced, permissioned business records.
A Fivetran alternative for AI agents: ingestion, storage, and MCP
Evaluate Combined for the whole path from business apps to agent answers: managed ingestion, storage, scoped MCP access, and $5 per million MAR after the trial.
An Airbyte alternative for AI agents: managed data and SQL
Compare Combined with Airbyte Agents and Data Replication for business-data agents: SQL access, managed context, usage pricing, and a practical first workload.
Choosing managed data ingestion for AI agents
Compare direct APIs, replication and managed agent data platforms. Use a practical checklist to evaluate source readiness, permissions, freshness and cost.
SQL or vector search for AI agents? Start with the question
Use SQL for exact calculations over structured records and semantic retrieval for meaning in text. Work through a reproducible business-data example.
How to check data freshness before an AI agent answers
Check source and dataset timestamps with a free freshness checker. Set age limits, flag stale or missing metadata, and download an AI agent policy and report.
DuckDB, DuckLake and the data work around an AI agent
Understand the query engine, table format and operational responsibilities behind a managed business-data layer for agents.
What is an FDE?
The role of forward deployed engineers in bringing AI systems into production.