Test MCP Server On Ic Canister
This project is an MCP server that only supports Streamable HTTP and tool capabilities, providing a stateless service without response validation, which can be deployed to the Playground environment via DFX.
rating : 2.5 points
downloads : 84
What is the MCP server?
The MCP server is a lightweight service based on the Internet Computer Protocol, providing the basic functions of the model context protocol. It supports data transmission through HTTP streaming and focuses on providing tool-related capabilities.How to use the MCP server?
You can deploy it to the DFINITY Playground environment and then interact with the server using simple HTTP requests. The server supports the standard request format of the JSON-RPC 2.0 specification.Applicable scenarios
Suitable for scenarios that require a lightweight, stateless model context protocol service, especially simple applications that only need basic tool functions.Main features
Streamable HTTP supportSupports data transmission through HTTP streaming, suitable for handling large amounts of data or real-time data streams
Tool capabilitiesProvides basic tool-related functions, such as listing available tools
JSON-RPC 2.0 interfaceUses the standard JSON-RPC 2.0 protocol for communication, easy to integrate
Advantages and limitations
Advantages
Easy to use and convenient to deploy
Based on the standard protocol (JSON-RPC 2.0), with good compatibility
Supports HTTP streaming, suitable for handling streaming data
Limitations
Currently only supports tool capabilities, with limited functions
Stateless design, does not save request history or context
Currently does not perform response validation, with low security
How to use
Deploy the service
Use the DFINITY Canister SDK to deploy the service to the Playground environment
Get the service URL
After deployment, you will get an endpoint URL similar to https://{DEPLOYED_CANISTER_ID}.icp0.io/mcp
Send a request
Use an HTTP POST request to send a JSON-RPC formatted request to the /mcp endpoint
Usage examples
List available toolsQuery the list of all tools supported by the server
Frequently Asked Questions
Which protocols does the MCP server support?
How to deploy the MCP server?
Does the server save the state?
Related resources
JSON-RPC 2.0 specification
Official specification document of the JSON-RPC 2.0 protocol
DFINITY Canister SDK documentation
Official DFINITY development documentation
Featured MCP Services

Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
141
4.5 points

Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
830
4.3 points

Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.7K
5 points

Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
88
4.3 points

Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
567
5 points

Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.7K
4.5 points

Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
754
4.8 points

Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
5.2K
4.7 points