Model Context Protocol (MCP)
The Model Context Protocol (MCP) is an open standard that allows seamless integration between large language model (LLM) applications and external tools or data sources. Whether you're building an AI-enhanced IDE, a chat interface, or custom AI workflows, MCP makes it easy to supply LLMs with the context they need.
Features Overview
CrestApps provides both client and server MCP support:
| Feature | Feature ID | Description |
|---|---|---|
| MCP Client Integration | CrestApps.OrchardCore.AI.Mcp / .Mcp.Stdio | Connect to remote (SSE) or local (Stdio) MCP servers |
| MCP Server | CrestApps.OrchardCore.AI.Mcp.Server | Expose Orchard Core AI capabilities to external MCP clients |
Supported Capabilities
The MCP implementation supports the following capabilities:
| Capability | Client | Server | Description |
|---|---|---|---|
| Tools | Yes | Yes | Discover and invoke AI tools |
| Prompts | Yes | Yes | List and invoke prompts. Can be managed via the admin UI. |
| Resources | Yes | Yes | Access various data sources. Can be managed via the admin UI. |
| Templated Resources | Yes | Yes | Resources with URI variable placeholders that resolve dynamically |
Resource Type Modules
Additional resource type handlers are available as separate modules:
Explore More MCP Servers
Looking for more MCP-compatible tools? Explore these resources: