Fidacy Mcp

io.github.lucaslubi由 GitHub 帳號 lucaslubi 發布v0.19.0更新於 Oct 24, 2026

AI Agent Firewall. Enforce signed authority before consequential actions. Free API key required.

已驗證STDIO僅桌面金融安全與監控

概覽

AI 產生的概覽

一個本機 MCP 伺服器,作為 AI 代理的付款防火牆,依簽章授權核驗擬議付款,並回傳簽章裁決與稽核證明。

可以做什麼
評估擬議動作(付款、傳訊息、語音通話、文件聲明),向 Fidacy 引擎取得簽章信任裁決,並附可驗證的證明內容與簽章金鑰識別碼。依授權核驗付款,回傳附短期 Ed25519 授權的允許結果,或附違規規則的拒絕結果。讀取授權信封與 Fidacy 公開金鑰。依決策 ID 取得雜湊鏈稽核證明。本機執行,預設拒絕,受信任收款方與額度在本地設定檔中設定。
適用情境
當 AI 代理可發起付款或其他有後果的動作,且你希望在執行器之前設置確定性關卡,而非依賴提示詞層級的防護時使用。適合需要為每筆付款決策產生可驗證、可稽核證明的情境。
執行需求
透過 npx 或全域 npm 安裝作為本機 stdio 程序執行(需要 Node.js)。呼叫裁決工具需要 FIDACY_ENGINE_API_KEY 環境變數,免費金鑰須在提供方註冊頁面取得。選用 FIDACY_MODE=http 指向託管核心。取得裁決需要連線至 Fidacy 引擎的網路。
安裝前請注意
此伺服器涉及付款授權,設定錯誤可能放行或阻擋真實資金流動;它為非託管,不持有資金。需要 FIDACY_ENGINE_API_KEY 密鑰,README 稱其不會被記錄或回顯。擬議動作與授權會傳送至 Fidacy 引擎進行評估。唯有它是代理唯一具備付款能力的工具,且下游執行器強制要求授權時,防護才有效。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Fidacy 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

@fidacy/mcp

[fidacy-mcp MCP server]

[Fidacy blocks a BEC lookalike-payee payment, then allows the legit one with a signed Ed25519 grant]

The action firewall for AI agents. A drop-in MCP server that gates payment actions against a cryptographically signed mandate before money can move. Non-custodial: Fidacy authorizes and proves, it never holds funds.

Install once, works in any MCP-compatible agent: Claude Code, Claude Desktop, Hermes, OpenClaw, and anything else that speaks MCP.

[npm] [license] Works with: Claude Code · Claude Desktop · OpenClaw · Hermes · Brex CrabTrap

Your agent could be paying scammers right now. Prompt-injected into the wrong payee, an inflated amount, or the same invoice twice — and your logs aren't evidence. Fidacy blocks it before money moves, and hands back a signed verdict anyone can verify against public keys. You don't trust us — you check the signature.

Quick start (free, local-first, no account)

json
{  "mcpServers": {    "fidacy": { "command": "npx", "args": ["-y", "@fidacy/mcp"] }  }}

Runs on your machine, offline, deny-by-default. Add trusted payees + caps in ~/.fidacy/config.json. Verify any verdict yourself against the public keys at /.well-known/jwks.json.

Why

An agent can hallucinate or be prompt-injected into a payment: wrong payee, wrong amount, fabricated invoice. Prompt-level guardrails are probabilistic and bypassable. @fidacy/mcp is a deterministic gate between the agent's intent and the executor: the action is dead on arrival unless it validates against a signed mandate, and every decision lands in an immutable hash-chained audit trail.

Enforcement model

  1. Register @fidacy/mcp as the agent's only payment-capable tool. Do not give the agent a raw payment tool. Tool inventory is the runtime firewall.
  2. The agent calls request_payment. Fidacy checks it against the mandate (payee allowlist, per-tx cap, total cap, currency, time window, revocation).
  3. ALLOW returns a short-lived Ed25519 grant. DENY returns no grant and the violated rule. The downstream executor MUST require the grant, so a denied action cannot proceed.
  4. Every decision is appended to a hash-chained log. get_audit_proof returns the portable, verifiable proof.

One install, two backends

@fidacy/mcp ships two complementary capabilities in a single install:

  • Verdict layer (advisory): assess_action calls the live Fidacy engine and returns a signed trust verdict. It moves no money; it returns a judgment whose proof (riskPayloadJws + signingKeyId) is verifiable by anyone via @fidacy/verify against the engine JWKS at /.well-known/jwks.json.
  • Payment firewall (enforcement): request_payment / verify_mandate / get_audit_proof gate and prove a payment against a signed mandate through the core, returning short-lived Ed25519 grants.

Mental model: assess_action -> engine (signed verdict); request_payment and friends -> core (payment firewall).

Tools

ToolBackendPurpose
assess_actionengineSigned Fidacy trust verdict for a proposed action. Advisory.
request_paymentcoreAuthorize a payment action. ALLOW + grant, or DENY + rule.
verify_mandatecoreRead the mandate envelope + Fidacy public key.
get_audit_proofcoreHash-chained proof for a decision id.

assess_action

Returns a signed Fidacy trust verdict from the live engine for a proposed action. The signed proof is riskPayloadJws + signingKeyId, verifiable by anyone via @fidacy/verify against {engineUrl}/.well-known/jwks.json.

Inputs:

  • kind (optional, default ap2_payment): one of ap2_payment, message_send, voice_call, custom, claim_document.
  • mandate (required): the action/mandate object for that kind.
  • mandateType, spendingMandate, idempotencyKey, a2a.task_id (optional).

Environment:

VarDefaultPurpose
FIDACY_ENGINE_URLhttps://api.fidacy.comBase URL of the Fidacy engine.
FIDACY_ENGINE_API_KEY(none)An fky_live_ / fky_test_ key with scope assess:write.

The server boots without FIDACY_ENGINE_API_KEY; the tool is always registered. Only calling assess_action without the key returns a helpful error telling you to set it. The key is never logged, echoed, or attached to any error.

Install

bash
npm install -g @fidacy/mcp   # or run via npx, no install

Claude Code

bash
claude mcp add fidacy -- npx -y @fidacy/mcp

Claude Desktop (claude_desktop_config.json)

json
{  "mcpServers": {    "fidacy": { "command": "npx", "args": ["-y", "@fidacy/mcp"] }  }}

Hermes (config.yaml)

yaml
mcp_servers:  fidacy:    command: npx    args: ["-y", "@fidacy/mcp"]

OpenClaw

Add the same server via the Tools panel, or the mcpServers block in your agent config. Any MCP-compatible host uses the same command.

Wiring the real core (production)

The MCP layer talks to your core through one interface (FidacyCore). Your repository stays private. Set FIDACY_MODE=http and implement three endpoints:

  • POST /v1/mandate/get -> Mandate
  • POST /v1/decide -> Decision (runs your Ed25519/AP2 verification + audit append)
  • POST /v1/audit/proof -> AuditProof

No change to the MCP layer is needed.

Dev

bash
npm installnpm run buildnpm start      # stdio server, in-memory demo mandate

來源:README.md,提交 ce42c70

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. v0.19.0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