MCP integrations, tool by tool
Every integration guide here answers the same three questions in the same order: does a server actually exist for this tool, what can an agent do once it is connected, and what will bite you in production. Vendor quick-starts stop after step two.
The pattern that repeats across every platform: the setup is rarely the hard part. The hard parts are permission scope (an integration account with the narrowest role you can get away with), result-set size (a query that returns 50k rows will blow through your context window long before it blows through the API quota), and the gap between what the API exposes and what the MCP server actually wraps.
Start read-only. Every guide below tells you how to do that for its specific platform, because 'read-only' means something different in ServiceNow than it does in Postgres.
If you only change one thing after reading any guide here: give the agent its own credentials with its own role, not yours.
42 articles · page 2 of 3
Workato MCP Server: Setup, Tools & Real Limits
Workato MCP is now an official hosted platform, but its safety and usefulness depend more on tool design and API-client scope than on the connection itself.
Auth0 MCP Server: Setup, Tools & Real Limits
Auth0’s official beta MCP server is useful for bounded tenant administration, but its write tools and narrow API coverage demand deliberate limits.
Miro MCP Server: Setup, Tools & Real Limits
Miro's official remote MCP endpoint turns boards into agent-readable context and writable canvases, but its OAuth, quotas, and layout quality need careful handling.
Smartsheet MCP Server: Setup, Tools & Real Limits
Smartsheet's official MCP server gives AI clients controlled access to live work data, but safe deployment depends on narrow permissions and disciplined writes.
Statsig MCP Server: Setup, Tools & Real Limits
Statsig MCP is a useful official bridge from AI clients to Statsig project data, but write access deserves the same controls as a production deployment tool.
MuleSoft MCP Server: Setup, Tools & Real Limits
MuleSoft MCP brings Anypoint development and governance into AI clients, but its value depends on choosing the right server and tightly limiting write access.
Snyk MCP Server: Setup, Tools & Real Limits
Snyk’s official local MCP server puts code, dependency, container, and IaC scans inside an agent workflow, but it is a scanner—not a general Snyk administration API.
MCP Server for Postgres: the options
Five real MCP servers that talk to Postgres, matched to what you actually run — plus the read-only config that keeps an agent off your production data.
MCP Server for MySQL: The Options Compared
Five real MCP servers connect MySQL to your AI client — here's which to pick, the trade-offs, and the minimal config that works.
MCP Server for SQLite: The Real Options
Four servers cover almost every SQLite use case — here's which one to run and the exact config to paste.
MCP Server for MongoDB: the 4 real options
Four servers connect MongoDB to your agent. One is official, three are community, and only two guard writes properly — here's how to choose.
MCP Server for Gmail: The Options, Ranked
Four real ways to give an AI assistant your inbox — and the one that gets you sending mail in about five minutes.
MCP Server for Slack: The Real Options
Five real MCP servers connect Slack to your AI client — the choice comes down to auth: session token, bot token, or a remote bridge.
MCP Server for Notion: Every Option, Ranked
Five ways to give your agent Notion access — and which one you should actually install.
MCP Server for Discord: the real options
Four real MCP servers that drive a Discord bot, matched to what you actually need — plus the minimal config and the bot-token safety you can't skip.
MCP Server for Obsidian: the 3 options
Two servers actually matter, they both go through the same plugin, and the only real decision is how much editing power you hand the model.
MCP Server for SQL Server: The Options
Three real MCP servers actually talk to Microsoft SQL Server — here's which to pick, the trade-offs, and the minimal read-only config that keeps an agent off your data.
MCP Server for Snowflake: 3 Options Compared
Three servers connect Snowflake to your agent — one is deprecated, one is read-safe by default, one auto-generates its API. Here's which to pick.
MCP Server for Google Sheets: the options
Two real MCP servers actually talk to Google Sheets — one via a service account, one via OAuth — plus the minimal config to wire either into your client.
MCP Server for Docker: Options & Config
Two questions hide inside "MCP server for Docker" — running a server as a container, and giving an agent Docker itself. Here's both, with real configs.
FAQ
Is there an MCP server for every SaaS tool?
No. Coverage is uneven: developer tools and databases are well served, while many enterprise platforms only have community servers or none at all. Each guide here states plainly what exists for that specific tool, including when the honest answer is 'use the REST API directly'.
Do I need admin rights to connect a tool over MCP?
Usually no, and you should not use them. Most integrations work with a scoped API token or an OAuth app limited to the objects you need. Create a dedicated integration account rather than reusing your own credentials, so the agent's blast radius is separate from yours.
Why does my agent time out on large queries?
Because tool results go into the model's context window. A query returning tens of thousands of rows will exhaust context or hit a transport timeout long before it hits an API limit. Every integration guide here gives the practical row/result caps for that platform.
Other topics
Looking for a server rather than an article? Best MCP servers by task