@Armada735
基本情報
MCP server issuing HMAC-attested receipts for AI agent tool-call evidence (verify_action_receipt.v0 reference impl)
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"verify-action": {
"url": "https://verify.armadalab.dev/mcp"
}
}
}ツール一覧はまだありません
この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。
上のボタンでサーバーのエンドポイントに接続し、ツール一覧を取得できます。
Verify Action is a post-action verification service for AI agent tool calls. Submit a (claim, evidence) pair and get back a 4-value verdict and a tamper-evident hosted receipt that downstream agents, CI steps, or deployment pipelines can use to continue, block, or escalate. It checks whether supplied evidence is internally consistent with the supplied claim — it does not independently access the caller’s database, code repository, or APIs.
Configure it as an MCP server (e.g., in claude_desktop_config.json with transport http pointing to https://verify.armadalab.dev/mcp). The agent then has a verify_action tool available. You can also call the REST API directly (POST /verify) or self-host the pure Python stdlib service (no pip install; clone and run ./start.sh).
It examines the supplied evidence object against the supplied claim using rule‑based verifiers. It does not access external systems; the trust boundary depends on the evidence kind — strongest for `code_diff` (the diff is the evidence), weaker for kinds that rely on the caller faithfully reporting external state.
`verified` (proceed), `contradicted` (block), `insufficient_evidence` (request more evidence), and `unsafe_to_verify` (escalate to human — the verifier itself raised an exception).
Receipts are HMAC‑SHA256 symmetric‑key signatures — they prove this service issued the verdict under a known key id. They are **tamper‑evident hosted log entries**, not third‑party cryptographic attestations. Public‑key (Ed25519) receipts are planned for a future v1.
The service is rule‑based only (no LLM‑as‑judge), does not decompose sub‑claims, and does not correlate traces across calls. The generic evidence handler is conservative and often returns `insufficient_evidence`.
IP addresses are SHA‑256‑hashed with a rotating salt. Claims and evidence are written to private trace logs with 30‑day retention. A structural PII guard rejects email, phone, JP postal codes, national‑ID‑shapes, passport patterns, and credit‑card‑shape digits. Individual traces stay private; only aggregate findings may be published.
不止于 CSS
Model Context Protocol Servers
Open-source MCP to use Blender with any LLM
Handl speaks the Model Context Protocol. Your whole billing operation — projects, invoices, clients, reports, approvals — as tools any AI assistant can call, inside your autonomy rules.
Model Context Protocol Servers
コメント