Skip to main content

Understanding MCP Servers

Dashboard vs platform model

In the dashboard this appears under MCP servers; internally we still use the bundle data model.

MCP servers are the core organizing principle of MCPBundles. This page explains what they are, how they're categorized, and their lifecycle from creation to use.

What is an MCP server?

An MCP server is a cloud-hosted collection of related tools exposed through a single MCP URL.

Think of it like an app store, but instead of downloading apps, your AI discovers tools. When you add an MCP URL to ChatGPT or Cursor, all the tools in that MCP server become available to your AI.

About .mcpb Files

You may have heard of .mcpb extension files—Anthropic's packaging format for MCP servers. MCPBundles supports this! You can download any MCP server as a .mcpb file for one-click installation in Claude Desktop. The file is just a convenient installer that connects to our cloud service. Both the MCP URL method and .mcpb file method give you the same MCP server. See the FAQ for details.

Why MCP servers?

Without them, you'd need to:

  • Add 50+ individual tool URLs to your AI
  • Remember which tool does what
  • Manage credentials for each tool separately

With an MCP server, you:

  • Add one URL and get many tools
  • Tools are organized by purpose (marketing, development, etc.)
  • One set of credential bindings covers all tools in the MCP server

MCP server properties

Every MCP server has:

Basic Information

  • Name: What the MCP server is called (e.g., "Marketing Automation")
  • Description: What it does and what tools it contains
  • Slug: URL-friendly identifier (e.g., marketing-automation-a3f) — used in paths like https://mcp.mcpbundles.com/bundle/{bundle-slug}
  • Version: Semantic version number (e.g., 1.0.0)
  • Author: Who created the MCP server
  • Icon: Visual identifier

Organization

  • Category: What type of work the MCP server helps with (see below)
  • Tools: List of tools included
  • Providers: Which external APIs the tools connect to

Lifecycle Status

  • Publication Status: Draft, Published, Deprecated, or Archived
  • Readiness Status: Whether you can use it right now (Ready, Setup Required, Connection Error, Unknown)

Access Control

  • User Access: Whether you've enabled this MCP server on your account
  • Publication: Whether the MCP server is public or private

Categories

MCP servers are organized into categories based on the type of work they help with. This makes it easier to find MCP servers that solve your specific needs.

Available Categories

CategoryDescriptionExample Tools
AnalyticsData analysis and reportingFetch metrics, generate reports, visualize trends
BackendServer and infrastructureDeploy code, manage databases, monitor services
CloudCloud platform servicesAWS, Azure, GCP operations
CollaborationTeamwork and communicationSlack, Teams, Discord integrations
Customer RelationCRM and customer managementHubSpot, Salesforce, Zendesk tools
Developer ToolsCoding and developmentGitHub, GitLab, code analysis
EcommerceOnline shopping and salesShopify, Stripe, inventory management
EducationLearning and trainingCourse management, quiz tools
EmailEmail marketing and managementCampaign tools, inbox automation
EnterpriseBusiness operationsERP, workflow automation
EntertainmentMedia and contentStreaming, gaming, content creation
FinancialMoney and accountingBanking APIs, payment processing
FormsData collectionSurvey tools, form builders
HostingWeb hosting and serversDomain management, hosting control
IoTInternet of ThingsDevice control, sensor data
LocationMaps and geolocationAddress lookup, routing, geocoding
Machine LearningAI and ML operationsModel training, inference
MarketingMarketing automationEmail campaigns, social media, analytics
MediaImage, video, audioProcessing, conversion, editing
MessagingChat and messaging platformsSMS, WhatsApp, Telegram
MonitoringSystem monitoringUptime checks, alert management
Open DataPublic datasetsGovernment data, research data
PaymentPayment processingCredit cards, digital wallets
Project ManagementTask and project trackingAsana, Trello, Jira tools
SearchSearch and discoveryElasticsearch, search APIs
SecuritySecurity and authenticationAuth tools, security scanning
SocialSocial media platformsTwitter, LinkedIn, Facebook tools
StorageFile storage and managementS3, Dropbox, Google Drive
SupportCustomer supportTicketing, help desk
TelecomPhone and SMS servicesTwilio, voice APIs
TextText processingTranslation, summarization
Time ManagementScheduling and calendarCalendar APIs, scheduling tools
ToolsGeneral utilitiesConverters, validators, generators
TransportShipping and logisticsDelivery tracking, route planning
OtherMiscellaneous toolsTools that don't fit other categories

Choosing a Category

When creating an MCP server, pick the category that best describes the primary use case. If an MCP server has tools from multiple categories, choose the one that represents the main purpose.

Example: A "Sales Automation" MCP server might include email tools (Email category) and CRM tools (Customer Relation category). Choose Customer Relation since that's the primary purpose.

Publication Status

MCP servers move through different publication states as you work with them.

Draft

  • You're still building and testing
  • Not visible to others
  • You can add/remove tools freely
  • Tools won't appear in AI clients

When to use: Creating a new MCP server, major changes to existing ones

Published

  • MCP server is complete and ready to use
  • Visible in the public directory at /skills/… (if you've published it)
  • Can be enabled on your account
  • Tools appear in your AI clients
  • You can still edit it, but changes are visible immediately

When to use: Everything is tested and ready for use

Deprecated

  • Outdated but still works
  • Indicates users should migrate to a newer version
  • Still functional for existing users
  • Not promoted to new users

When to use: You've created a better version and want to sunset the old one

Archived

  • No longer maintained
  • Hidden from the public directory
  • Existing users can keep using it
  • New users can't enable it

When to use: Obsolete or no longer supported

Readiness

Readiness tells you whether the tools will actually work for you right now. It depends on which providers are connected and verified.

Ready 🟢

All required providers have valid, verified credentials. Every tool works.

What you see:

  • Green status display showing "Ready" with "Credentials valid" subtext
  • Full tool count shown
  • "Credentials" section header shows "All configured" with green checkmark
  • All provider cards show "Verified" badges

What you can do:

  • Use all tools immediately
  • Tools appear in your AI
  • Fully functional

Example:

Marketing Suite (MCP server)
Status: Ready (Credentials valid) ✓
Required: Smartlead (Verified), HubSpot (Verified)
Optional: OpenAI (Verified)
Tools Available: 12/12

Setup Required 🟡

Not configured yet. Needs credentials for required providers.

What you see:

  • Amber/orange status display showing "Setup Required" with "Connect provider accounts" subtext
  • "Credentials" section header shows "X of Y configured"
  • Provider cards marked "Not configured" (amber badge)

What you can do:

  • Click "Add Credential" on each provider card that needs configuration
  • Add credentials through the credential panel
  • Validate each credential
  • Becomes Ready once all required providers are configured

Example:

Marketing Suite (MCP server)
Status: Setup Required
Required: Smartlead (Not configured), HubSpot (Not configured)
Tools Available: 0/12
Action: Click Configure to add credentials

Connection Error

One or more provider credentials are missing, expired, or invalid.

What you see:

  • Red status display showing "Connection Error" with "Credentials expired" subtext
  • "Credentials" section header shows "X of Y configured"
  • Provider cards showing "Error" badges (red) or "Unverified" badges (amber)
  • Warning message in the Credentials section

What you can do:

  • Click "Edit" on the affected provider card
  • Fix or replace the problematic credential in the credential panel
  • Re-validate to confirm it works
  • Becomes Ready once all credentials are valid

Example:

Marketing Suite (MCP server)
Status: Connection Error ❌
Required: Smartlead (Credential expired), HubSpot (Verified)
Tools Available: Limited
Action: Fix Smartlead credential

Unknown

You haven't enabled this MCP server on your account yet, so we can't evaluate readiness.

What you see:

  • Gray badge
  • Prompt to enable to check readiness

What you can do:

  • Click Enable to add the server to your workspace
  • System will check if you have the required providers
  • Status changes to Ready, Setup Required, or Connection Error based on your credentials

Creating and managing MCP servers

Creating an MCP server

  1. Go to Dashboard → MCP servers
  2. Click "Create" (or equivalent for a new MCP server)
  3. Fill in:
    • Name (clear, descriptive)
    • Description (what it does)
    • Category (from the list above)
    • Version (start with 1.0.0)
  4. Click "Create"
  5. Add tools
  6. Test with your own credentials
  7. Publish when ready

Testing tools

Before using tools in your AI, you can test them in MCP server Studio—an interactive execution environment that lets you run tools directly in your browser with proper credential context.

Studio features:

  • Execute tools with auto-generated forms
  • See real-time results and errors
  • Get help from an AI assistant
  • Verify credentials are working
  • Learn tool behavior safely

See the MCP server Studio Guide for a complete walkthrough.

Adding tools

Tools can belong to multiple MCP servers. This lets you:

  • Create general-purpose MCP servers (all marketing tools)
  • Create focused MCP servers (only email campaign tools)
  • Mix and match tools for specific workflows

To add tools:

  1. Open the MCP server
  2. Click "Add Tool"
  3. Search for existing tools or create new ones
  4. Tool appears immediately

Enabling on your account

Before you can use the tools, you must enable the MCP server:

  1. Find it on Discover or in your Connected tab
  2. Click Enable in the header
  3. System checks which providers you need
  4. Scroll to the "Credentials" section
  5. Click "Add Credential" on each provider card that needs configuration
  6. Add credentials through the credential panel
  7. Validate your credentials
  8. Status changes to "Ready" with "Credentials valid" subtext
  9. Scroll to "Quick Setup" section and copy the MCP URL
  10. Add to your AI client

Disabling

If you stop using an MCP server:

  1. Open its detail page
  2. Click Turn off in the header (or remove access if it's a shared server you don't own)
  3. Confirm in the dialog
  4. Tools disappear from your AI
  5. Credentials remain (in case you re-enable later)
  6. It stays in your list (disabled state)

Composed MCP servers

You can compose MCP servers by including one inside another. This lets you build custom endpoints that combine tools from multiple sources.

How composition works

When you include MCP server A inside MCP server B:

  • All of A's tools become available through B's MCP URL
  • Each included MCP server keeps its own credential bindings
  • The composed MCP server acts as a single MCP endpoint with combined tools

When to compose

Use composition when:

  • You want tools from multiple providers in one endpoint
  • You're building a project-specific server (e.g., "Sales Stack" = HubSpot + Resend + Stripe)
  • You want a single MCP URL instead of multiple URLs

Keep MCP servers separate when:

  • You want to enable/disable groups independently
  • Different AI clients need different tool sets
  • You're using the Hub endpoint (which already aggregates everything)

Creating a composed MCP server

  1. Navigate to any MCP server detail page
  2. Click "Add to Custom Server" button in the header (compact button in the navigation row)
  3. Choose an existing custom MCP server, or create a new one
  4. The source MCP server's tools are now available through the target MCP server

You can include multiple MCP servers in the same custom server. Each keeps its own credential bindings.

See Creating custom MCP servers for step-by-step instructions.

MCP URLs

Each MCP server has a unique MCP URL you add to your AI clients.

Format:

https://mcp.mcpbundles.com/bundle/{bundle-slug}

Example:

https://mcp.mcpbundles.com/bundle/marketing-automation-a3f

Using MCP URLs

Different AI clients configure MCP servers differently:

ChatGPT:

  • Settings → Apps → Create app → Paste URL (requires Developer mode)

Cursor:

  • .cursor/mcp.json → Add to mcpServers → Paste URL

Claude Desktop:

  • Add Custom Connector → Paste URL

Claude Code:

  • claude mcp add --transport http {name} {url}

See Integration Guides for detailed steps.

Versioning

MCP servers use semantic versioning: MAJOR.MINOR.PATCH

  • MAJOR (1.x.x): Breaking changes, incompatible with previous version
  • MINOR (x.1.x): New features, backward compatible
  • PATCH (x.x.1): Bug fixes, backward compatible

When to Increment

  • Add tools: Increment MINOR (1.0.0 → 1.1.0)
  • Remove tools: Increment MAJOR (1.1.0 → 2.0.0)
  • Fix tool bugs: Increment PATCH (1.1.0 → 1.1.1)
  • Change tool behavior: Increment MAJOR or MINOR depending on impact

Managing Multiple Versions

You can have multiple versions:

  • marketing-suite-v1 (version 1.5.0, deprecated)
  • marketing-suite-v2 (version 2.0.0, published)

Users on v1 keep working. New users get v2. Migration is optional.

Common Workflows

Workflow 1: Using an existing MCP server

  1. Open Discover or your Connected tab
  2. Click Enable on the server detail page
  3. Connect required providers in the Connections section
  4. Validate credentials
  5. Copy the MCP URL from Quick Setup
  6. Add to your AI client
  7. Start using tools

Workflow 2: Creating a custom MCP server

  1. Click "Create"
  2. Name it based on your workflow (e.g., "Daily Standup Automation")
  3. Pick a category
  4. Add relevant tools:
    • Slack notification
    • Calendar fetch
    • Email send
    • GitHub PR list
  5. Test with your credentials
  6. Publish
  7. Add to your AI

Workflow 3: Combining multiple MCP servers

You can enable multiple MCP servers simultaneously. Your AI sees all tools from all enabled MCP servers.

Example setup:

  • Marketing Suite (12 tools) → For campaigns
  • Developer Tools (25 tools) → For code work
  • Customer Support (8 tools) → For tickets

Total: 45 tools available in your AI, organized across 3 MCP servers.

Next Steps