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)
Strategic BDI reasoning engine for autonomous AI agents with spatial utility and replanning.
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": {
"agent-reasoning": {
"command": "npx",
"args": [
"-y",
"@putervision/agent-reasoning-mcp"
]
}
}
}在终端中运行这条命令
claude mcp add agent-reasoning -- npx -y @putervision/agent-reasoning-mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"agent-reasoning": {
"command": "npx",
"args": [
"-y",
"@putervision/agent-reasoning-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": {
"agent-reasoning": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@putervision/agent-reasoning-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7日
注册名称已通过 GitHub 账户 putervision 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(0.4.1)于34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, Claude Checkpoint MCP
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.
MCP server that checkpoints Claude Code session context to survive crashes and token limits
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。
Strategic BDI Reasoning, Multi-Attribute Expected Utility Theory & Decision Intelligence for Autonomous AI Agents
@putervision/agent-reasoning-mcp is a formal Model Context Protocol (MCP) server that provides strategic belief-desire-intention (BDI) reasoning, hierarchical goal decomposition, multi-attribute expected utility calculation (\(E[U] = \sum w_i u_i\)), exponential belief decay, quantitative risk evaluation, and reactive replanning across multi-modal memory bridges.
🌐 Official Documentation: putervision.com • Interactive Web Docs
# 1. Initialize reasoning database & seed default utility profiles
npx @putervision/agent-reasoning-mcp init
npx @putervision/agent-reasoning-mcp doctor
npx @putervision/agent-reasoning-mcp inspect
| Tool | Actions | Purpose |
|---|---|---|
set_goal | create, update, decompose, get, list, abandon | Manage goal hierarchy, task DAGs, and success criteria |
evaluate_situation | snapshot, quick | Score and rank candidate actions from environment snapshots |
replan | blocker, event, full | Adaptively reconstruct subgoals upon obstacles and abort stale intentions |
assess_risk | action, plan, compare | Quantitative threat and risk calculation across candidate actions |
query_knowledge | search, patterns, similar_situations | Search learned heuristics, tactical knowledge, and past decision patterns |
set_utility_weights | configure, get, list, activate | Configure utility weights (aggression, caution, greed, efficiency, exploration) |
get_decision_trace | latest, get, list, explain | Explainable chain-of-thought rationale and latency telemetry |
manage_beliefs | update, query, expire, reconcile | Structured belief state with exponential confidence decay ($C = C_0 e^{-\lambda t}$) |
manage_intentions | create, dispatch, get, list, cancel, resolve | Wire contract directives queue for runtime execution engines |
manage_reasoning_db | stats, audit, snapshot, restore | Reasoning database statistics, SHA-256 Merkle audit, and snapshot rollback |
Inspired by the typed System 1 pattern pioneered by TypeSafe's Jev (evaluating typed
Choice,Score, andNoulprimitives over compact state without token generation), implemented locally via in-memory LRU caches and deterministic heuristics (<2ms) without external API calls.
| Tool | Purpose | Latency Target | L1 Cache (p50) | Throughput |
|---|---|---|---|---|
classify | Low-latency categorical labeling over multi-modal StatePacks | <2ms | `0.0075 ms` | ~90,000 ops/s |
ask_noul | Typed probabilistic hypothesis and Boolean verification ($p \in [0.0, 1.0]$) | <2ms | `0.0049 ms` | ~127,000 ops/s |
ask_choice | Discrete $1$-of-$N$ choice selection ($N \le 16$) with probability simplex | <2ms | `0.0138 ms` | ~64,000 ops/s |
ask_score | Bounded numeric scalar scoring and calibrated utility rating | <2ms | `0.0057 ms` | ~129,000 ops/s |
gate_intention | Pre-dispatch blast-radius audit gate issuing signed HMAC dispatch tokens | <1ms | `0.0709 ms` | ~12,000 ops/s |
See [docs/benchmarks.md](docs/benchmarks.md) for full benchmark reproduction commands, latency percentiles (p50/p95/p99), and multi-tier caching architecture details.
agent-reasoning-mcp coordinates the closed-loop PuterVision Super-Loop:
init, doctor, inspect, run)..agent-reasoning-mcp.json parameters and environment variables.Add to .cursor/mcp.json or .vscode/mcp.json:
{
"mcpServers": { "agent-reasoning-mcp": { "command": "agent-reasoning-mcp", "args": ["run"], "env": { "PENTAD_HMAC_SECRET": "your-secure-shared-secret-here", "DISPATCH_TOKEN_TTL_MS": "30000" } } } }
PENTAD_HMAC_SECRET: 256-bit shared key for cryptographic intention dispatch token signing.DISPATCH_TOKEN_TTL_MS: Dispatch token expiration window (default: 30,000ms).SKIP_MODEL_LOAD: Set to 1 (or OFFLINE=1) to force air-gapped L1/L2 deterministic evaluation.# Run full unit and integration test suites
npm test
npm run benchmark
OFFLINE=1 SKIP_MODEL_LOAD=1 npm test
MIT © PuterVision