Source control MCP
Repository, issue, pull-request, code-search, and project workflows exposed to AI clients.
Gitcodedeveloper
Model Context Protocol
MCP servers and agent connections
Explore common MCP server categories and understand how Model Context Protocol connects AI clients with tools, resources, and external context.
MCP is the interoperability layer in the AI stack. A server exposes tools, resources, or prompts through a common protocol; a client decides how those capabilities appear inside an AI workflow.
Browse
MCP servers and agent connections
6 entries
Database MCP
Structured access to database schemas, queries, metadata, and data workflows with scoped permissions.
SQLdataschema
Browser & web MCP
Browser automation, page inspection, navigation, and web research capabilities for agent workflows.
browserautomationresearch
Files & documents MCP
Expose files, documents, folders, or knowledge resources to clients through a controlled context layer.
filesdocumentscontext
Communication MCP
Connect messaging, support, collaboration, and notification systems to repeatable agent tasks.
messagessupportcollaboration
Infrastructure MCP
Cloud, deployment, logs, observability, and operations capabilities exposed to development agents.
cloudDevOpslogs
MCP servers and agent connections FAQ
What does an MCP server do?+
An MCP server exposes tools, resources, or prompts through the Model Context Protocol so compatible AI clients can discover and use them through a standard interface.
Is MCP the same thing as an agent skill?+
No. MCP exposes capabilities and context. A skill defines repeatable task behavior: the steps, constraints, validation, and expected output. A skill can call tools exposed by MCP.
Does MCP replace plugins?+
Not automatically. MCP standardizes capability access, while a plugin can package authentication, permissions, product-specific workflows, and user experience around one or more integrations.