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.
48 articles · page 1 of 3
Railway MCP Setup: CLI Login, OAuth, and Project Checks
Connect Railway MCP through the current Railway CLI or the official hosted endpoint, then verify your identity and target project before allowing infrastructure changes.
Firebase MCP Setup: CLI Credentials and the Right Project
Use the official Firebase MCP server from firebase-tools, authenticate the Firebase CLI, and verify the active project before reading or changing application data.
Mixpanel MCP Setup: Regional Endpoints and Verified Queries
Connect Mixpanel's official MCP data endpoint for your region, authorize the intended account, and reproduce one known report before relying on a new analysis.
Postman MCP Setup: Choose the Right Endpoint and Verify Access
Connect the official Postman MCP server to the correct account region, start with its Minimal tool configuration, and verify a workspace before running requests. Keep three ideas separate: Postman as an MCP client, generated MCP servers, and the official server that exposes Postman account operations.
Jira MCP Setup: Connect Atlassian OAuth and Start Read-Only
Use Atlassian’s official remote v2 Jira MCP endpoint, https://mcp.atlassian.com/v2/mcp, with OAuth 2.1. Confirm the Jira site and project, verify search and issue reads, and keep creation, transitions, and updates gated until the connected user’s permissions and administrator-controlled domain and IP policies are understood.
GitLab MCP Setup: Connect OAuth, Limit Toolsets, and Verify Reads
Use GitLab’s built-in MCP server for the first connection: enable it for the correct top-level group or instance, connect over HTTP when possible, complete OAuth 2.0 Dynamic Client Registration (DCR), and start with only core and work-item toolsets. Then perform a read-only project check before permitting issue, merge-request, or pipeline actions.
Confluence MCP Setup: Connect OAuth and Protect Page Writes
Use Atlassian’s official remote v2 MCP server at https://mcp.atlassian.com/v2/mcp, authorize only the intended Confluence site, then verify search and page reads within one space. Before any create or update action runs, inspect its target, content, parent, and structural effect so page writes remain deliberate.
AWS MCP Server Setup: Choose OAuth or SigV4 Before Granting Access
Use the managed AWS MCP Server at the official us-east-1 endpoint. Choose browser OAuth for one human account, or use SigV4 through the AWS MCP Proxy when you need account switching or established CLI credentials. First confirm documentation and read operations; allow mutations only after identity, permissions, and audit paths are clear.
n8n MCP Setup: Choose Instance Access, Trigger, or Client Mode
n8n MCP can mean three different setups: n8n’s instance-level MCP access, one workflow published through an MCP Server Trigger, or an n8n workflow using the MCP Client Tool. Choose the smallest scope that matches the task, copy before editing, and validate before allowing execution or production changes.
Splunk MCP Server: Setup, Tools & Real Limits
Splunk MCP gives AI clients a governed route into SPL searches and metadata, but its guardrails, query cost, and context limits define where it belongs.
Tableau MCP Server: Setup, Tools & Real Limits
Tableau MCP gives AI agents governed access to published Tableau data and content, but it is an API bridge—not a replacement for Tableau authoring or careful access control.
ServiceNow MCP Server: Setup, Tools & Real Limits
ServiceNow now has a first-party MCP server, but licensing, narrow default tools, and write risk make a read-only pilot the sensible starting point.
Gong MCP Server: Setup, Tools & Real Limits
The official Gong MCP server brings account, deal, and brief insights into AI clients, but its read-only scope, permissions, and credit model matter.
Zoom MCP Server: Setup, Tools & Real Limits
Zoom MCP now has first-party hosted servers, but useful results still depend on licensing, recording settings, narrow OAuth scopes, and disciplined result retrieval.
LangChain MCP: Use MCP Tools in LangChain Agents
LangChain's MCP adapter lets agents call external tools, but production success depends more on server quality and permission design than on connection code.
Zoho MCP Server: Setup, Tools & Real Limits
A practical guide to Zoho’s hosted MCP service, its verified tools, secure setup, production risks, and better alternatives for fixed workflows.
Oracle MCP Server: Setup, Tools & Real Limits
Oracle now offers three first-party MCP routes to its database, but the right choice depends on whether you value local speed, centralized control, or remote access.
Workday MCP Server: Setup, Tools & Real Limits
Workday MCP can give an AI client governed access to HR and finance data, but the setup and risk depend heavily on which server you choose.
Framer MCP Server: Setup, Tools & Real Limits
Framer now offers an official agent route, while true MCP connections remain third-party—here is how to choose, connect, and contain the risk.
NetSuite MCP Server: Setup, Tools & Real Limits
Oracle’s official NetSuite MCP can expose ERP records, reports, saved searches, and SuiteQL to an AI client, but its role design matters more than its quick connection flow.
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