Spec Driven Development
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
作者提供的说明(英文原文)
SSTIM reference for senses, stimuli, perception and scientific contributions.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"sstim": {
"command": "npx",
"args": [
"-y",
"@sstim/mcp"
]
}
}
}在终端中运行这条命令
claude mcp add sstim -- npx -y @sstim/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"sstim": {
"command": "npx",
"args": [
"-y",
"@sstim/mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"sstim": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@sstim/mcp"
]
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月8日
注册名称已通过 GitHub 账户 w3c-cg 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(0.3.0)于27天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:Spec Driven Development, Remote Desktop Commander, NexusWindows
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
MCP Server that facilitates spec-driven development workflows, not just Vibe Coding.
Remote Desktop Commander: use files, terminal and processes on your own computers from any AI app.
Windows computer use in the background: desktop apps driven without your mouse or keyboard.
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Status: version 0.3.0 adds an explicitly authorized, GitHub-backed contribution workflow to the read-only knowledge tools. It supports the current MCP `2026-07-28` stateless protocol and legacy initialization-based clients (2025-11-25, 2025-06-18, 2024-11-05).
The adapter retrieves frozen SSTIM release data from the Concept Reference API. It is not an ontology write interface or hosted remote MCP endpoint. The four knowledge tools remain available without credentials. Four additional proposal tools can draft suggestions, browse GitHub review issues, and, only when an authorized operator has configured an Issues-write token and approved the exact public content, submit a GitHub issue for review. No tool changes canonical RDF or accepts scientific assertions as established.
Primary author and responsible project: the SSTIM W3C Community Group. The canonical source is w3c-cg/sstim.
Acknowledgement: BioSynCare, for its contributions to and support of SSTIM's wider ecosystem. BioSynCare is not the authority behind the open SSTIM vocabulary.
Community Group work is not a W3C Recommendation or a W3C-endorsed product.
`@sstim/mcp@0.3.0` is published on npm. It is listed as io.github.w3c-cg/sstim in the official MCP Registry, registered by the canonical W3C Community Group repository via OIDC.
With Node.js 20+ and a compatible stdio MCP client, set command npx and arguments ["--yes", "@sstim/mcp@0.3.0"]. The server needs no checkout or API token. For a smoke test, run it outside packages/sstim-mcp/: npm may resolve the local package there instead of the published executable.
cd /tmp
npx --yes @sstim/mcp@0.3.0
The command waits for protocol messages; silence is expected until the MCP client sends them. Pin the exact npm version for reproducibility. Run node packages/sstim-mcp/server.mjs from a checkout only for development.
Distribution and directory-listing status. Each npm tarball is immutable; later repository documentation edits reach npm's package README only with a future release.
For each local-checkout example below, replace /absolute/path/to/sstim/packages/sstim-mcp/server.mjs with the actual absolute path to this file. On Windows, use a path like C:/Users/you/sstim/packages/sstim-mcp/server.mjs and ensure node is in the launching application's PATH.
The server is launched by the AI client. Running it manually will appear idle because it waits for JSON-RPC messages on stdin. It must not emit human-readable logs to stdout.
For a hands-on tutorial with eight concrete AI prompts, prerequisites, tool usage and limits, see the SSTIM MCP manual chapter and the MCP examples cookbook.
Here are examples for users of Codex, Claude Code, GitHub Copilot, Cursor, Gemini and compatible Neovim plugins. Each task combines an AI assistant's ordinary reasoning and project access with *read-only released SSTIM data*:
| Task | What to ask for | What SSTIM MCP contributes |
|---|---|---|
| Code/data schema alignment | "Inspect my session JSON and map frequency, technique, channels and session fields to SSTIM" | Canonical term IRIs and module/release provenance; not an automatically validated mapping |
| Research terminology review | "Compare meanings of binaural and isochronous techniques without conflating stimulation with EEG bands" | Definitions and related concept links |
| Version migration | "Retrieve this exact IRI in 0.18.0 and 0.19.0; report asserted differences" | Version-pinned details, deprecation and mappings |
| Cross-ontology interoperability | "List external alignments for this term, including the precise SKOS relation" | Mapped external IRIs and relation strengths |
| Codebase audit | "Find fields in my code matching published SSTIM properties; flag unknown ones" | Stable identifiers; human review of inferred matches |
| Write scientific documentation | "Explain these terms with source references; distinguish evidence from labels" | Released definitions, source module and hashes |
| Correct the standard | "Find this term or gap and prepare a link for me to submit a correction" | A user-reviewed Contribution Bridge link, not a submission |
| Repeatable research | "Use only release 0.19.0 for all SSTIM terms cited in this protocol" | Release-qualified records for reproducibility |
These MCP tools do not perform automatic SHACL validation, execute a stimulation protocol, diagnose anything, or modify the ontology. Use Python sstim or JavaScript @sstim/core for data validation, and use the Workbench to explore or author reference patches.
The new sstim_draft_contribution tool builds a structured, unreviewed issue proposal, with an explicit epistemic status. sstim_list_contributions and sstim_get_contribution retrieve public issue records and their actual state. sstim_submit_contribution creates a public GitHub Issue, but only if SSTIM_ENABLE_PUBLIC_SUBMISSIONS=1 is explicitly set by the operator and SSTIM_GITHUB_TOKEN is configured with appropriate GitHub Issues write access and approvedForPublicSubmission: true is supplied after the operator reviews the exact proposal. A local cooldown and fingerprint scan reduce accidental duplicates. This is not an unattended permission to submit private material.
Never put the token in a plugin manifest or conversation. Use the host's credential or environment management; no GitHub credential is bundled. Contributions are not automatically accepted; a closed GitHub issue is not necessarily an accepted scientific assertion.
Supported proposal kinds: correction, missing knowledge, scientific evidence, interoperability, research need and other. Relevant subjects may include sensory transduction, perception, sound or music-based practices, neuroscience, creative work and technological applications. SSTIM is not a comprehensive encyclopedia of these areas; gaps are valid reports. Sources are contributor-supplied and must be independently assessed.
| Tool | Result |
|---|---|
sstim_list_releases | Supported frozen releases and latest available version |
sstim_search_concepts | Search terms by IRI/CURIE, labels, alternatives or definition |
sstim_get_concept | Retrieve exact term, definitions, declared relationships, source provenance |
sstim_prepare_feedback | User-facing Contribution Bridge link; nothing is submitted |
sstim_draft_contribution | Structured, unreviewed proposal text; nothing is submitted |
sstim_list_contributions | Recent public contribution issues and their GitHub state |
sstim_get_contribution | One public contribution issue, its unverified text and state |
sstim_submit_contribution | Public GitHub issue for review; refused unless the operator enabled submissions |
Every tool except sstim_submit_contribution is read-only, and that one is disabled unless the operator opts in as described above. The feedback tool generates only a link with the selected public concept ID and label, without copying conversation text. The user reviews any issue and decides whether to publish it. No tool writes to the SSTIM ontology.
Choose one configuration appropriate to the AI client in use. They are not interchangeable. Sample files are in examples/.
Create or update .vscode/mcp.json in your project using the examples/vscode.mcp.json contents:
{
"servers": { "sstim": { "type": "stdio", "command": "npx", "args": ["--yes", "@sstim/mcp@0.3.0"] } } }
In VS Code run MCP: List Servers (or use MCP commands in the Command Palette), start sstim, then open GitHub Copilot Chat → Agent mode and enable the SSTIM tools in the tool picker.
This is VS Code's servers format, not the mcpServers format used by Cursor and Gemini. VS Code can also use a portable project-root .mcp.json, which has different keys; see its official MCP setup.
Codex's IDE extension and CLI share ~/.codex/config.toml (or supported project-scoped .codex/config.toml). Append the contents of examples/codex.config.toml:
[mcp_servers.sstim]
command = "npx" args = ["--yes", "@sstim/mcp@0.3.0"]
Or configure the server via the Codex IDE extension: Settings → MCP servers → Add server → STDIO. Restart the extension if prompted. In the CLI, codex mcp list can show the configured servers. This configuration is separate from .vscode/mcp.json for Copilot Chat.
Reference: Codex MCP configuration.
Run in a terminal (using the same Claude Code installation as your extension):
claude mcp add --transport stdio --scope user sstim -- npx --yes @sstim/mcp@0.3.0
claude mcp get sstim
Then open Claude Code (CLI or VS Code extension) and check the /mcp menu to confirm the server is connected and tools are visible. The -- separator is important: arguments after it belong to npx, not to Claude's CLI. For a shared project installation instead of a personal user installation, consult the project's .mcp.json and approval rules.
Reference: Claude Code MCP setup.
Add to your user ~/.gemini/settings.json or project .gemini/settings.json:
{
"mcpServers": { "sstim": { "command": "npx", "args": ["--yes", "@sstim/mcp@0.3.0"] } } }
See examples/gemini.settings.json. Alternatively use:
gemini mcp add -s user sstim npx --yes @sstim/mcp@0.3.0
Open Gemini CLI and use /mcp to inspect connectivity and exposed tools.
Gemini CLI is not the same product as the Gemini Code Assist VS Code extension. This configuration applies to the CLI; support for an extension must be verified against that extension's own settings. Reference: Gemini CLI MCP.
Create a project .cursor/mcp.json, or ~/.cursor/mcp.json globally, with the contents of examples/cursor.mcp.json:
{
"mcpServers": { "sstim": { "command": "npx", "args": ["--yes", "@sstim/mcp@0.3.0"] } } }
Open Cursor Settings → Tools & MCP and verify the server is connected. Ask Cursor Agent to use sstim_search_concepts.
Reference: Cursor MCP documentation.
Neovim does not supply an AI/MCP client merely by being installed. If you use CodeCompanion.nvim, add
只显示了开头部分;其余内容请在仓库中阅读