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)
Deterministic local repository context, impact analysis, and merge-readiness evidence for AI agents.
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": {
"solumbe": {
"command": "npx",
"args": [
"-y",
"@bashbop/solumbe",
"mcp"
]
}
}
}在终端中运行这条命令
claude mcp add solumbe -- npx -y @bashbop/solumbe mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"solumbe": {
"command": "npx",
"args": [
"-y",
"@bashbop/solumbe",
"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": {
"solumbe": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@bashbop/solumbe",
"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6日
注册名称已通过 GitHub 账户 BASHBOP 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(4.10.0)于5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, debuff
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.
Let coding agents play, test and tune your 2D web game: live state, explained errors, replays, fuzz.
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。
Models generate the change. Solumbe proves whether it is safe to merge.
Formerly Òtítọ́ (@bashbop/otito), renamed in 4.0.0; the CHANGELOG maps every old name to its new one.
Solumbe is a local-first, deterministic, model-agnostic trust layer for AI-assisted development. It builds task-aware repository context before an agent edits, scores how much a change actually touches, and gates merge readiness against the exact staged tree, with no server, no account, and no code leaving the machine.
It does not replace Claude Code, Codex, Cursor, Gemini, or any native agent harness. It runs beside them and keeps working as the models change underneath.
A passing local gate is never an automatic merge approval: hosted CI, GitHub review, CODEOWNERS, and the human release decision remain separate authorities.
npm install -g @bashbop/solumbe
solumbe doctor solumbe install --host all
The last command connects Solumbe's MCP server to every agent host it finds: Claude Code, Claude Desktop, Codex CLI, Cursor, VS Code, Gemini CLI and Kimi Code CLI. Add --dry-run to see the plan first, or name hosts with --host claude-code,cursor. Restart each host afterwards.
Or without installing: npx -y @bashbop/solumbe doctor.
Rank what a change actually touches, from the request alone, with no model, no embeddings, and no network:
$ solumbe impact . "add refund handling to checkout" --top 3
concepts: money flow
Gate the exact staged tree, and say precisely why:
$ solumbe gate . --staged --base origin/main --request "add refund handling to checkout" --min-convergence 80
[OK] Changed files 1 changed file found. [OK] Staged snapshot Changed-file scope and convergence evidence are captured from the exact staged Git tree. |- Tree: 7d0b513dd256877d6bd309a6406468a9b1eaeedc |- Base: b776f04fcfbd02c8ce8d63e1a0c2450be58de039 [OK] Secret safety No secret file paths and no credential values found in the changed content. [WARN] Risk review Risk-sensitive files changed; maintainer review should be explicit. |- src/payment/checkout.service.ts [OK] Convergence Task and diff satisfy the convergence requirement. |- Score: 100/100 (aligned) |- Receipt handle: rcpt_a8d31efae06e |- Subject tree: 7d0b513dd256877d6bd309a6406468a9b1eaeedc
VERDICT WARN
The convergence score is the part a model cannot grade for itself: it compares the stated intent against the files the diff actually changed, and produces a receipt bound to the exact base, parent, and staged-tree identity.
Hold the change to what was declared. Record the files a request is expected to touch before the edit, and the gate names any file that was never declared:
$ solumbe declare . "add refund handling to checkout"
$ # ... the agent edits ... $ solumbe gate . --staged --base HEAD --intent .solumbe/intent.json
[FAIL] Scope contract Touched src/auth/session.ts, which was never declared. Amend the intent with the reason it belongs (solumbe amend --reason " "), or take it out of the change. |- Request: "add refund handling to checkout" |- Contract: fe655c2af2b31b7e3edec6aedd248b379235811d1228c829f87ff73796ace487 |- Changed files: 3 (1 declared, 0 amended, 1 implied, 1 undeclared) |- Implied: tests/checkout.service.test.ts (owner-test of src/payment/checkout.service.ts) |- Undeclared on a risk-sensitive path: src/auth/session.ts [auth/security]
An amendment adds a file with its reason, hashed onto the contract, so a reviewer reads why the scope grew. Over MCP it is change_impact with declare: true, and review_gate with intent.
Four commands are the product. They call no model, open no socket, and read nothing outside the repository.
| Step | Command | What it proves |
|---|---|---|
| Before the edit | solumbe context "add refund handling" --path . | Which files, tests and commands the request needs |
| After the edit | solumbe converge . "add refund handling" --base origin/main --staged | How far the diff is from the request, with a receipt |
| Before the merge | solumbe gate . --staged --base origin/main --request "add refund handling" | PASS / WARN / FAIL on the exact staged tree |
| After the merge | solumbe attest . --verdict verdict.json --merge | A hash-chained record of what shipped, under which verdict |
solumbe help shows these and how to set up; solumbe help --all lists every command, including the ones that support them (impact, declare, pr, review, map, calibrate, route, ax, dashboard and the rest). Nothing was removed.
Nothing hosted is required, and nothing hosted can change a verdict. Local Core, Optional Hosted lists exactly what the optional pieces send, and where.
| Goal | Command |
|---|---|
| Rank change blast radius | solumbe impact . "add refund handling" --top 12 |
| Score intent vs. execution | solumbe converge "add refunds" --path . --base HEAD --staged |
| Score a committed change exactly | solumbe converge "add refunds" --path . --base HEAD~1 --head HEAD |
| Gate a product change across repos | solumbe workspace-gate ../web ../api --request "ship change" |
| Grade risk flags against history | solumbe calibrate . --window 30 |
| Grade route tiers against history | solumbe regret . --window 30 --offline |
| Regrade a saved run, same answers | solumbe regret --rescore run.json |
| Score Agent Experience | solumbe ax . "add a new MCP tool" |
| Recommend a model tier | solumbe route . "add a new MCP tool" |
| Sharpen context with a model read | solumbe context "add a new MCP tool" --path . --online |
| Inspect one repo | solumbe repo . --json |
| Build a code map | solumbe map . --json |
| Index and search local projects | solumbe index ~/projects --discover then solumbe search "events controller" |
| Generate an agent harness | solumbe harness . --out .solumbe/harness.md |
| Run the MCP server | solumbe mcp |
Every command takes --json, and solumbe help lists the full set with flags.
Solumbe ships a stdio MCP server exposing 14 tools: repo_inspect, repo_map, repo_index, repo_search, context_pack, change_impact, agent_experience, model_route, convergence_score, review_context, review_gate, review_verdict, workspace_report, and repo_harness.
{
"mcpServers": { "solumbe": { "command": "npx", "args": ["-y", "@bashbop/solumbe", "mcp"] } } }
solumbe install --host all writes this entry for you, using absolute paths so hosts that do not inherit your shell PATH can still start it. Published in the MCP Registry as io.github.BASHBOP/solumbe. Repo-map lookups use an external per-user cache and never write into the inspected repository. Host-specific setup for Claude Code, Claude Desktop, Codex, Cursor, VS Code, Gemini CLI, and Kimi Code is in MCP and Agent Workflows.
| Approach | Strengths | Where solumbe differs |
|---|---|---|
| Sourcegraph / Cody context | Powerful hosted code search and embedding-based context across an org | Local-first and deterministic: no server, no account, no code leaves the machine, and the same query always yields the same packet |
Hand-written CLAUDE.md / rules files | Curated, intent-rich guidance | Hand-written context goes stale; solumbe regenerates context from the actual code (symbols, imports, routes, tests) on every run and complements a short CLAUDE.md |
grep / ripgrep | Fast, universal text matching | solumbe ranks whole files by task intent across paths, symbols, exports, and tests, then adds patterns and validation commands, producing a context packet rather than a list of matching lines |
Full command reference, agent workflows, release process, evaluation method, and the design theses behind the trust layer:
[bashbop.github.io/solumbe](https://bashbop.github.io/solumbe/)
git clone https://github.com/BASHBOP/solumbe.git
cd solumbe && npm ci && npm run ci
npm run ci is the full gate: format, lint, typecheck, version check, tests, coverage floors (70% lines / 60% branches / 75% functions), three evaluation corpora, dependency audit, and a packaged-tarball smoke test. Run it before requesting review.
Start with CONTRIBUTING.md and the Code of Conduct. All changes need maintainer review; main requires passing gates and resolved conversations. Solumbe follows Semantic Versioning, so say whether a PR is no-impact, patch, minor, or major.
solumbe is one of four tools that form a deterministic trust layer for AI-assisted development. Each uses static analysis to answer a question people keep handing to an LLM.
只显示了开头部分;其余内容请在仓库中阅读