simulate-monte-carlo

io.github.encodi由 GitHub 帳號 encodi 發布v1.0.0更新於 Oct 25, 2026

Real Monte Carlo simulation of a compound event/conditional probability. Paid via x402.

已驗證Streamable HTTP可網頁執行資料與分析AI 與機器學習

概覽

AI 產生的概覽

遠端 MCP 伺服器,透過實際執行蒙地卡羅模擬,以宣告的隨機變數估算複合事件或條件機率。

可以做什麼
宣告具名隨機變數(uniform、normal、bernoulli、binomial、poisson、exponential、discrete),搭配事件表達式與選用的條件表達式,以拒絕取樣取得 P(事件 | 條件),是真正抽樣與計數而非模型猜測。回傳回應中的 seed 可重現同一次結果。表達式由受限解譯器求值,僅支援算術、比較、布林邏輯、括號與 min/max/abs,沒有執行程式碼的路徑。每次呼叫皆自成一體,沒有資料庫或持久狀態。
適用情境
適合需要快速數值機率估計的情況,例如骰子點數和或簡單風險情境,而不是依賴大型模型的猜測。適用於探索性估算,不適合高風險統計用途。
執行需求
透過 streamable HTTP 連線的遠端端點;未宣告帳號或 API 金鑰。每次工具呼叫需透過 x402 在 Base 主網以 USDC 付費,因此需要能付款的用戶端。另有上限:最多 10 個變數、100 至 100,000 次試驗、表達式 500 字元,以及總抽樣預算上限。
安裝前請注意
每次呼叫收取真實費用(Base 主網 0.03 USDC),未付費的呼叫會回傳錯誤並附付款資訊以便重試。95% 信賴區間採常態近似,機率接近 0 或 1 時不夠精確。呼叫端提供的表達式由受限解譯器解析,不會當成程式碼執行。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 simulate-monte-carlo,將其新增到工作區。
  2. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.encodi%2Fsimulate-monte-carlo/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "simulate-monte-carlo": {
      "type": "http",
      "url": "https://simulate-monte-carlo.encodari.workers.dev/mcp"
    }
  }
}

README

simulate-monte-carlo

[simulate-monte-carlo MCP server]

Remote MCP server (Cloudflare Workers) with one tool that estimates a compound event or conditional probability by actually running a Monte Carlo simulation:

  • simulate_monte_carlo — declare named random variables (uniform, normal, bernoulli, binomial, poisson, exponential, discrete), an event boolean expression over those names (e.g. "a > 0.5 && b == 1"), and an optional condition expression to get a conditional probability P(event | condition) via rejection sampling. Real random sampling and real counting — not a model guess about what the probability should be.

No database, no persistent state: each call builds a fresh McpServer (see createServer() in src/index.ts) and is self-contained. The PRNG is seedable (mulberry32): pass the seed returned in a previous response to reproduce the exact same result.

Why a hand-written expression interpreter, not eval

event/condition are arbitrary caller-supplied strings. Running them through eval/Function would mean executing untrusted code inside the Worker. Instead, src/tools/monteCarlo.ts includes a small tokenizer + recursive-descent parser + AST interpreter that only understands numbers, declared variable names, arithmetic (+ - * /), comparisons (< <= > >= == !=), boolean logic (&& || !), parentheses, and a three-function whitelist (min, max, abs). There is no code execution path — the interpreter can't do anything beyond evaluate that narrow grammar.

Billing (x402)

Charges per call via x402 — real USDC payment on Base mainnet, against the Coinbase Developer Platform (CDP) facilitator. The payment travels inside the MCP JSON-RPC itself (_meta), not as an HTTP header; see src/payments.ts.

ToolPrice
simulate_monte_carlo$0.03 USDC

An unpaid tools/call returns isError: true with the accepts (network, amount, payTo) the client needs to pay and retry — not an unexplained exception.

Structure

src/  index.ts            # registers the tool in the McpServer and exposes the MCP HTTP handler  payments.ts         # x402 billing on Base mainnet via the CDP facilitator  tools/    monteCarlo.ts        # distributions, expression parser/interpreter, simulation loop (testable without Workers)    monteCarlo.test.tsscripts/  dev-node.ts          # dev server that runs the handler in plain Node, no wrangler

Resource limits

Set from the start, not bolted on after: max 10 variables, 100–100,000 trials (default 10,000), 500-character expressions, binomial n ≤ 1,000, poisson lambda ≤ 1,000, and a discrete-outcome cap of 20. On top of the individual caps, a combined sampling-budget check (trials × sum(per-variable cost) ≤ 5,000,000) rejects combinations that would be individually within limits but jointly too expensive — e.g. 100,000 trials against a binomial(n=1000) variable.

Running it locally

⚠️ Note on wrangler dev: the real Cloudflare Workers runtime (workerd) requires macOS 13.5+. If your Mac has an older version, wrangler dev (and npm run dev) will fail. This project includes a plain-Node shim that runs the exact same fetch() handler without needing workerd.

1. Install dependencies

bash
npm install

2. Run the unit tests

bash
npm test

3a. If your wrangler dev works (macOS 13.5+, Linux, Windows)

bash
npm run dev

3b. If wrangler dev fails because of the macOS version

bash
npm run dev:node

Starts at http://localhost:8787/mcp, reading CDP credentials from ~/.mcp-tools-factory-credentials.env (shared across all tools in this factory).

4. Test with curl

bash
# 1) initializecurl -s -X POST http://localhost:8787/mcp \  -H "Content-Type: application/json" \  -H "Accept: application/json, text/event-stream" \  -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"curl-test","version":"0.0.1"}}}'
# 2) tools/listcurl -s -X POST http://localhost:8787/mcp \  -H "Content-Type: application/json" \  -H "Accept: application/json, text/event-stream" \  -d '{"jsonrpc":"2.0","id":2,"method":"tools/list","params":{}}'
# 3) tools/call — simulate_monte_carlo (two dice, P(sum > 9 | first die == 6))curl -s -X POST http://localhost:8787/mcp \  -H "Content-Type: application/json" \  -H "Accept: application/json, text/event-stream" \  -d '{"jsonrpc":"2.0","id":3,"method":"tools/call","params":{"name":"simulate_monte_carlo","arguments":{"variables":[{"name":"d1","distribution":{"type":"discrete","values":[1,2,3,4,5,6],"weights":[1,1,1,1,1,1]}},{"name":"d2","distribution":{"type":"discrete","values":[1,2,3,4,5,6],"weights":[1,1,1,1,1,1]}}],"event":"d1 + d2 > 9","condition":"d1 == 6","trials":40000,"seed":3}}}'

Responses come as Server-Sent Events (event: message + data: {...}); the data: line is the usual JSON-RPC response.

Deploy and listings

Deployed at https://simulate-monte-carlo.encodari.workers.dev/mcp (Cloudflare Workers). Published on the official MCP registry, Smithery, mcp.so, and with an open PR to awesome-mcp-servers.

What it doesn't do (yet)

  • Charges on Base mainnet with real money. To switch back to testnet (Base Sepolia, eip155:84532) during development, change NETWORK in src/payments.ts.
  • No database or persistent state between calls (beyond the billing config, cached in memory per isolate — see src/payments.ts).
  • The 95% confidence interval uses the normal (Wald) approximation, which is imprecise near probabilities close to 0 or 1 — good enough for a quick estimate, not a substitute for exact binomial confidence intervals in high-stakes use.

來源:README.md,提交 1347a3f

工具

0
SourceWeft 尚未讀取此伺服器的工具。

版本歷史

1
  1. v1.0.0最新Sep 16, 2026

評分

已滿足適用檢查項的 50%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分

    請保持端點能夠回應 MCP 握手;SourceWeft 每 30 天探測一次。

  • 已宣告認證方式必需10 分

    請在註冊中心條目中宣告憑證請求標頭,或保持端點能夠回應探測,以便判定其認證方式。

  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分