A Model Context Protocol server
Coding devops mcp server lets Claude, Cursor and other MCP clients work with Coding Devops directly. A Model Context Protocol server.
CODING DevOps MCP Server 是一个基于 Model Context Protocol (MCP) 的服务器实现,用于与 CODING DevOps 平台进行交互。它提供了一套标准化的接口,使得用户可以方便地管理 CODING 平台上的项目和工作项。
Once connected, the assistant can call these 4 tools directly:
list_projects — 列出用户可访问的项目list_work_items — 列出工作项create_work_item — 创建工作项delete_work_item — 删除工作项Setup follows the standard MCP pattern: clone or install the server, then register it in your client's configuration file and restart the client. The configuration snippets on this page cover Claude Desktop, Claude Code and Cursor.
Before the server will start you need to supply 2 environment variables: CODING_TOKEN, PROJECT. Keep credentials in your client's env block or a secrets manager rather than committing them.
Developer-tool servers are usually the first ones people connect, because they turn "help me with this code" into an assistant that can actually read the repo and act on it. Coding Devops sits in that group, and the shape of its toolset — list_projects, list_work_items, create_work_item among others — tells you what it is really for. Worth comparing against the other developer tools servers in this directory before you commit to one, since several overlap in scope but differ sharply in setup cost and permissions.
| Tool | What it does |
|---|---|
| list_projects | 列出用户可访问的项目 |
| list_work_items | 列出工作项 |
| create_work_item | 创建工作项 |
| delete_work_item | 删除工作项 |
| Variable | Description | Required |
|---|---|---|
| CODING_TOKEN | Credential the server authenticates with. | Yes |
| PROJECT | Configuration value read at startup. | Optional |
A knowledge graph your assistant keeps between sessions — entities, relations and observations that persist.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Your workspace, on speaking terms with AI — search, read and write Notion pages and databases.
A structured scratchpad for hard problems — stepwise reasoning with revisions, branches and visible logic.
Symbol-level code navigation, refactoring and memory for coding agents — the IDE brain your assistant has been missing.
Chat with your second brain — search, read and write vault notes through the Local REST API.