1C: Platform Tools MCP
1C: Platform Tools MCP

MCP 服务器为 Cursor 或 VS Code 代理提供对 1C: Platform Tools 扩展命令的访问:测试、启动配置文件、配置构建、数据库操作。
安装
安装 1C: Platform Tools:Marketplace、Open VSX
安装 1C: Platform Tools MCP:Marketplace、Open VSX
打开 1C 项目(包含
packagedef的文件夹)。
Related MCP server: 1C_MCP_SERVER_OWN
连接
VS Code 无需额外操作:扩展会自动注册 MCP 服务器。
Cursor 不支持 VS Code 的 MCP 服务器提供程序,因此服务器通过项目的 .cursor/mcp.json 文件连接。该文件由扩展创建和更新:
命令面板 (F1) →
1C: Platform Tools MCP: 为 Cursor 配置 MCP,或者在 1C 工具 树 → AI 技能 → 为 Cursor 配置 MCP。重新加载窗口。
在 MCP 设置中启用
mcp-1c-platform-tools服务器:Cursor 添加的新服务器默认是禁用的。
该命令会写入服务器路径和 IPC 参数;文件中的其他服务器保持不变。路径包含扩展版本,因此更新后该记录会过时,服务器会因 MODULE_NOT_FOUND 崩溃。扩展在启动时会修复此问题:如果路径指向同一扩展的其他安装,则更新路径。手动写入的路径(例如指向源代码构建的路径)保持不变。
验证
让代理“显示 1C 环境状态”。响应中将包含活动启动配置文件、平台版本和数据库路径。之后可以请求运行测试、切换配置文件、构建配置等。
文档
手动配置
仅在无需扩展的情况下创建配置文件时需要。必须启用 1c-platform-tools.ipc.enabled 设置,ONEC_IPC_* 值取自 1c-platform-tools.ipc.*:
{
"mcpServers": {
"mcp-1c-platform-tools": {
"command": "node",
"args": ["<путь к каталогу расширения>/out/src/index.js"],
"env": {
"ONEC_IPC_HOST": "127.0.0.1",
"ONEC_IPC_PORT": "40241",
"ONEC_IPC_TOKEN": ""
}
}
}
}扩展目录:%USERPROFILE%\.cursor\extensions\yellow-hammer.mcp-1c-platform-tools-<版本>-universal(Windows)或 ~/.cursor/extensions/...(macOS、Linux)。每次更新扩展后,此类路径都需要手动修改。
全局配置(%USERPROFILE%\.cursor\mcp.json)同样有效,但扩展不会更新它:对于多个项目,项目级文件更可靠。
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-quality-maintenanceEnables AI assistants to perform Business Central AL development tasks including language server operations, container management, Git version control, and file system operations for professional BC development workflows.
- Flicense-qualityDmaintenanceEnables AI agents to interact with 1C:Enterprise databases through natural language, providing metadata retrieval, configuration analysis, and code generation.9
- Flicense-qualityDmaintenanceActs as a bridge between AI agents (Claude, Cursor) and 1C:Enterprise databases, enabling metadata retrieval, configuration analysis, and code generation through natural language using the MCP protocol.
- Alicense-qualityAmaintenanceIntegrates AI agents with 1C:Enterprise databases via MCP and REST API, supporting a built-in HTTP server (no Python required) or a Python proxy mode.227GPL 3.0
Related MCP Connectors
Create and manage AI agents that collaborate and solve problems through natural language interacti…
Build, validate, and deploy multi-agent AI solutions from any AI environment.
Provides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to i…
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/yellow-hammer/mcp-1c-platform-tools'
If you have feedback or need assistance with the MCP directory API, please join our Discord server