Skip to content

What is a MCP

MCP (Model Context Protocol) is an open-source standard for connecting AI applications to external systems.

Think of MCP like a USB-C port for AI applications.

AspectDescriptionExample
What it isA server that exposes tools/data to the AIFilesystem, GitHub, Jira, Postgres, Slack
What it replacesCustom tool integrations per modelOne MCP server works with any MCP-compatible model
How it worksServer exposes resources + tools; agent calls themAgent reads a Jira ticket, then edits a file
Where configured.mcp.json or IDE settingsVaries by harness

When to use MCP: when the agent needs to read or write data from an external system (databases, issue trackers, APIs).

How MCP works

MCP uses a client-server architecture over JSON-RPC:

  • The MCP client fetches a tool manifest that describes each available tool and when it should be used
  • When the agent determines a tool matches the needs of its prompt, it calls that tool
  • The MCP server executes the request and returns enriched context to the client

What an MCP server exposes

PrimitiveWhat it isExample
ToolsCallable functions the agent can invokesearch_docs(), run_query()
ResourcesRead-only data the agent can accessFiles, database rows, API responses
PromptsPre-built prompt templatesSummarization, code review prompts

How to use

Claude Code

claude mcp add --transport http notion https://mcp.notion.com/mcp

OR

Create .mcp.json and edit following the instructions

Copilot CLI

/mcp add

OR

Create a mcp-config.json in the .copilot folder following the instructions

Types of MCP

TransportDescription
HTTPRemote MCP servers accessed over HTTP (recommended for cloud services)
stdioLocal MCP servers running as processes on your machine

Tips

  • MCP tool manifests consume context, so consider if you really need them in a certain context.
  • For efficiency and simplicity, consider instructing the agent to use the CLI (e.g., GitHub CLI) directly or via a skill.

Remember: Always use a reputable source for your mcp.

Useful MCPs

CategoryMCP ServerDescription
FrontendAngular CLI MCPAngular development tools
FrontendPlaywright MCPBrowser automation and testing
FrontendChrome DevToolsChrome debugging tools
FrontendFigma MCPDesign system integration
GeneralContext7Context management
GeneralAtlassian MCPJira, Confluence integration
GeneralGitHub MCPGitHub repository management
DevOpsAWS MCP ServersAWS service integration
DevOpsAzure MCPAzure service integration
DevOpsTerraform MCPInfrastructure as code

Resources

Copyright © MSG Systems Romania AI Labs