All in one vscode plugin for mcp developer
# Add to your Claude Code skills
git clone https://github.com/LSTM-Kirigaya/openmcp-clientEnglish | δΈζ
<a href="https://openmcp.kirigaya.cn" target="_blank" style="display: inline-block; padding: 8px 16px; background-color: rgb(84, 176, 84); color: white; border-radius: .5em; text-decoration: none;">π«± Official Documentation</a>
<a href="https://qm.qq.com/cgi-bin/qm/qr?k=C6ZUTZvfqWoI12lWe7L93cWa1hUsuVT0&jump_from=webapi&authKey=McW6B1ogTPjPDrCyGttS890tMZGQ1KB3QLuG4aqVNRaYp4vlTSgf2c6dMcNjMuBD" target="_blank" style="display: inline-block; padding: 8px 16px; background-color: #CB81DA; color: white; border-radius: .5em; text-decoration: none;">OpenMCP QQ Group</a>
<a href="https://discord.gg/SKTZRf6NzU" target="_blank" style="display: inline-block; padding: 8px 16px; background-color: rgb(84, 176, 84); color: white; border-radius: .5em; text-decoration: none;">OpenMCP Discord Channel</a>
</div>An all-in-one vscode/trae/cursor plugin for MCP server debugging.
Integrated Inspector + MCP client basic functions, combining development and testing into one.
![]()
Test mcp tools, prompts and resources with a variety of tools.
![]()
Tested tools can be placed in the "Interactive Testing" module for large model interaction testing.
![]()
Complete project-level management panel for easier MCP project management at both project and global levels.
![]()
Supports multiple large models
![]()
Support XML mode and customized options for your tool selection.
![]()
once everything is tested and verified in openmcp-client, you can deploy your mcp as an agent app with openmcp-sdk fastly and easily:
npm install openmcp-sdk
then deploy your agent with just lines of codes
import { OmAgent } from 'openmcp-sdk/service/sdk';
// create Agent
const agent = new OmAgent();
// Load configuration, which can be automatically generated after debugging with openmcp client
agent.loadMcpConfig('./mcpconfig.json');
// Read the debugged prompt
const prompt = await agent.getPrompt('hacknews', { topn: '5' });
// Execute the task
const res = await agent.ainvoke({ messages: prompt });
console.log('βοΈ Agent Response', res);
output
[2025/6/20 20:47:31] π [crawl4ai-mcp] 1.9.1 connected
[2025/6/20 20:47:35] π€ Agent wants to use these tools get_web_markdown
[2025/6/20 20:47:35] π§ using tool get_web_markdown
[2025/6/20 20:47:39] β use tools success
[2025/6/20 20:47:46] π€ Agent wants to use these tools get_web_markdown, get_web_markdown, get_web_markdown...