Balmas Mcp

com.balmasai由 balmasai.com 發布v0.3.0更新於 Oct 24, 2026

Agents read cleaned copies of your files: PII replaced with local consistent tokens. Read-only.

發布方自己的服務:Persqo

已驗證STDIO僅桌面檔案與儲存安全與監控

概覽

AI 產生的概覽

讓助理以本機匿名化副本的形式讀取白名單內的檔案,並提供還原工具把代稱對應回真實值。

可以做什麼
此伺服器對已加入白名單的資料夾提供唯讀工具:list_files 回傳名稱、大小與類型而不回傳內容,read_clean_file 回傳本機匿名化後的檔案文字,restore_text 在工作階段內把助理輸出中的代稱還原為原始值。姓名、身分證號、電話、電子郵件、公司、金額,以及 API 金鑰、JWT、私鑰區塊等機密,會在內容回傳前被替換成一致的代稱,例如 PERSON_001 或 SECRET_001。偵測在本機行程中執行,採用確定性樣式、詞彙表與檢查碼,支援希伯來文與英文。支援的輸入包括 txt、csv、md、docx、xlsx、pptx 以及含文字層的 pdf。
適用情境
當助理需要讀取含有個人或敏感資料的文件,而你希望它看到的是去識別化副本而非原始檔案時使用。它的定位是取代該助理對檔案系統的直接存取,而不是與之並用。適用於郵件、人資、法律或財務文件審閱等重視最小化的情境。
執行需求
透過 stdio 在本機執行,通常以 npx 從 npm 套件 balmas-mcp 啟動。需要一個免費帳號,並透過環境變數 BALMAS_API_KEY 提供 API 金鑰,還要以位置參數傳入至少一個白名單資料夾。可選的 --level 參數可選擇 standard、strict 或 maximum。每次讀取檔案都會計入每月文件配額。
安裝前請注意
BALMAS_API_KEY 是機密,會傳送給服務提供者;檔案內容、路徑與替換對照表據稱留在本機,但計量計數會離開本機。讀取會消耗每月配額。偵測是確定性的,可能漏掉敏感值,風險較高時應人工檢視輸出。只有當助理透過它讀取檔案、而不是擁有原始檔案系統存取權時才有用。沒有文字層的掃描版 PDF 不受支援。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Balmas Mcp,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。

Desktop only,透過 STDIO。 STDIO 服務會啟動本機處理程序,因此需要 SourceWeft 桌面主機。

其他 MCP 客戶端

參照 儲存庫 中的啟動說明。

README

balmas-mcp

Your AI agent reads everything. This gateway hands it redacted copies instead.

[npm] [license]

[balmas-mcp demo: the agent reads a contract and sees PERSON_001 instead of real names]

Why

AI agents are getting file access — and they over-read. Israel's Privacy Protection Authority put it bluntly in its guidance on AI agents: an email-sorting agent can analyze 15 years of correspondence for a 2-year task, infer your health and finances along the way, and leak what it learned. Their recommendation: strict permission minimization — read-only, dedicated folders, minimum necessary data.

balmas-mcp turns that advice into code, and goes one step further: it minimizes not just which files the agent reads, but what's inside them.

How it works

  1. You allowlist folders. The agent can't reach anything else — enforced with realpath checks, not honor rules.
  2. Every read is anonymized locally. Names, ID numbers, phones, emails, companies and amounts become consistent tokens (PERSON_001, ID_001) before the content is returned. Secrets too: API keys (OpenAI, Anthropic, GitHub, AWS, Stripe, Slack…), JWTs, private-key blocks, password: values and .env credentials become SECRET_001 at every level — and are never written back by restore_text. The same person is PERSON_001 in every file, so the agent's reasoning stays coherent. Detection runs in this process — deterministic patterns, lexicons and checksums (Israeli ID included). Hebrew and English.
  3. The answer comes back real. restore_text maps the tokens in the agent's final output back to the original values — locally.

Read-only by design: the server exposes no write tools at all.

Quickstart

  1. Create a free account at balmasai.com/signup (10 documents/month free).
  2. Create an API key (bk_...) at balmasai.com/app/team.
  3. Add to your MCP client config (Claude Desktop shown; Cursor and others are the same idea):
json
{  "mcpServers": {    "balmas": {      "command": "npx",      "args": ["-y", "balmas-mcp", "/Users/me/Documents/work", "--level", "strict"],      "env": { "BALMAS_API_KEY": "bk_..." }    }  }}

Options: allowed folders as positional args (required, one or more) · --level standard|strict|maximum (default strict).

Tools

ToolWhat the agent gets
list_filesNames, sizes, types inside allowed folders — never contents
read_clean_fileThe file's text after local anonymization
restore_textReal values back into its output (session tokens only)

Supported inputs: txt csv md docx xlsx pptx pdf (text layer).

Privacy model

Leaves your machine?
File contentsNever
File names / pathsNever
The replacement mapNever
Metering counters (file type + item counts)Yes — that's all

Each file read counts as one document against your account's monthly quota (free 10 / PRO 200 / TEAM 1,000). Full processing happens in this local process.

Honest limits

  • The gateway helps only when the agent reads files through it — grant it instead of raw filesystem access, not alongside.
  • Detection is deterministic: excellent, not clairvoyant. Review output where the stakes demand it.
  • Scanned PDFs (no text layer) need the OCR flow at balmasai.com/clean.

Built by BALMAS AI — sensitive data stops here. Docs: balmasai.com/mcp

來源:README.md,提交 29e7c36

工具

0
SourceWeft 尚未在沙箱中啟動過該軟體包,因此其工具未知。

版本歷史

1
  1. v0.3.0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

其他 Persqo 整合