@vibemap.ai/mcp-server
Connect your IDE agent to VibeMap via the Model Context Protocol. Load project specs into any MCP-compatible AI coding agent, or reverse-engineer an existing codebase back into structured VibeMap assets.
接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
npx -y @vibemap.ai/[email protected]Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
VIBEMAP_API_KEY=<secret> VIBEMAP_BASE_URL=<value> claude mcp add io.github.ashmet-vibemap-mcp -- npx -y @vibemap.ai/mcp-server@2.8.1在終端機中執行。
{ "mcpServers": { "io.github.ashmet-vibemap-mcp": { "command": "npx", "args": [ "-y", "@vibemap.ai/[email protected]" ], "env": { "VIBEMAP_API_KEY": "<secret>", "VIBEMAP_BASE_URL": "<value>" } } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
Connect your IDE agent to VibeMap via the Model Context Protocol. Load project specs into any MCP-compatible AI coding agent, or reverse-engineer an existing codebase back into structured VibeMap assets.
Load & create VibeMap product specs from your coding agent; sync build progress.
{
"mcpServers": {
"vibemap": {
"command": "npx",
"args": ["-y", "@vibemap.ai/mcp-server"],
"env": {
"VIBEMAP_API_KEY": "vm_your_token_here",
"VIBEMAP_BASE_URL": "https://vibemap.ai"
}
}
}
}
Generate your API key at vibemap.ai → Account → Developer → API Keys.
Outbound (VibeMap → IDE): Load your full project context — features, user stories, acceptance criteria, personas, pages, and DB schema — into your IDE agent. The agent builds to spec and updates your VibeMap kanban in real time as it works.
Inbound (IDE → VibeMap): Point the server at an existing codebase and VibeMap's AI will reverse-engineer it into a structured set of features, user stories, and acceptance criteria.
Config file: ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
{
"mcpServers": {
"vibemap": {
"command": "npx",
"args": ["-y", "@vibemap.ai/mcp-server"],
"env": {
"VIBEMAP_API_KEY": "vm_your_token_here",
"VIBEMAP_BASE_URL": "https://vibemap.ai"
}
}
}
}
Fully restart Claude Desktop after saving. Confirm the 🔨 hammer icon appears in the message box.
Open Settings → MCP and add:
{
"vibemap": {
"command": "npx",
"args": ["-y", "@vibemap.ai/mcp-server"],
"env": {
"VIBEMAP_API_KEY": "vm_your_token_here",
"VIBEMAP_BASE_URL": "https://vibemap.ai"
}
}
}
Same format as Cursor. Add to your Windsurf MCP settings file and restart.
The server exposes 55 tools via the vibemap_ prefix.
Projects & context
Personas & pages (spec authoring)
Conversational agent (hosted, metered)
Features
User stories
Acceptance criteria
Kanban — board & agentic lifecycle
Version control
Codebase
Import an existing codebase
The structure is read on your machine with no model and no network call. What reaches VibeMap is the structural facts (table, column, policy and route definitions with their file paths) and the spec text your agent writes. File contents never leave your machine.
The server also exposes prompts — invocable workflows your IDE surfaces as slash commands (in Claude Code: /mcp__vibemap__<name>). The body of each prompt is expanded from VibeMap's server at call time, so you invoke a workflow rather than paste a long instruction. Every prompt takes a projectId except new_project, which is the one that creates a project; the code-oriented ones also accept an optional localPath.
gen_* — run VibeMap's own generatorsThe author_* prompts above run on your model: your agent does the thinking and VibeMap just stores the result. The gen_* prompts are the other half — they run VibeMap's hosted generation pipelines, the same ones behind the app's /gen-… slash commands. They are metered (they draw down the project owner's VibeMap token budget) and asynchronous (you get a sessionId back and poll vibemap_get_generation_status).
ci-report turns a test run into review results. Tag each test name with the acceptance criterion it proves, for example [AC-042] rejects an empty title. After the run, post the report:
VIBEMAP_CI_TOKEN=... npx @vibemap.ai/mcp-server ci-report \
--junit junit.xml --project <project-id>
Every criterion that is in review and mentioned by the report is resolved from its own tests: passed when all of them passed, failed when any failed (the failing test names go back to the agent). Criteria that are not in review, or are unknown, are listed and left alone.
--junit (JUnit XML), --vitest and --playwright (each tool's JSON reporter). Pass several to combine them.VIBEMAP_CI_TOKEN must be a CI-review token (Account, Developer, scope "CI review"). An agent token is refused.--run-url and --sha.0 reported, 1 the server rejected the report or could not be reached, 2 bad usage, 3 no tagged tests with --strict.--dry-run prints the request without sending it.MIT
Load & create VibeMap product specs from your coding agent; sync build progress.
{ "mcpServers": { "io.github.ashmet-vibemap-mcp": { "command": "npx", "args": [ "-y", "@vibemap.ai/[email protected]" ], "env": { "VIBEMAP_API_KEY": "<secret>", "VIBEMAP_BASE_URL": "<value>" } } }}工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
發布者列出了以下環境變數:VIBEMAP_API_KEY, VIBEMAP_BASE_URL。
Vibemap 透過 stdio 在本機執行。
上次檢查時間:2026-11-08。 Load & create VibeMap product specs from your coding agent; sync build progress.