FinalApproval 用のスタンドアロン Model Context Protocol サーバー — AIエージェントのアクションを人間の承認でゲートします。
エージェントが submit_approval を呼び出すと、人間がFinalApprovalダッシュボードのブランド化されたページでレビューを行い、人間が決定を下すとチャネルに設定されたWebhookが発火します。
これはローカル / ヘッドレス / CI / ディレクトリインデックス（Glama）用途を想定した stdio バリアントです。ホスト型のOAuthゲート付きStreamable-HTTPサーバーが必要な場合は、MCPクライアントを https://www.finalapproval.ai/mcp に向けてください。
v0.1では以下のツールを公開しています：
ツール | ステータス | 備考 |
| ✅ 実装済み | 保留中の承認を作成します。解決時にWebhookが発火します。 |
| 計画中 | 公開API |
| 計画中 | 公開API |
| 計画中 | 公開API |
現在利用可能なすべてのツール機能については、ホスト型エンドポイント https://www.finalapproval.ai/mcp (OAuth 2.1, スコープ approvals:write) を使用してください。
Related MCP server: Approval Gate
finalapproval.ai にサインインし、チャネルを作成します。APIキー（fa_で始まります）をコピーし、Webhook URLを設定します。
FINALAPPROVAL_API_KEY にAPIキーを設定してMCPサーバーを実行します。
npx -y @finalapproval/mcp-server設定スニペット (Claude Code ~/.claude.json):
{
"mcpServers": {
"finalapproval": {
"command": "npx",
"args": ["-y", "@finalapproval/mcp-server"],
"env": {
"FINALAPPROVAL_API_KEY": "fa_..."
}
}
}
}docker run --rm -i \
-e FINALAPPROVAL_API_KEY=fa_xxx \
ghcr.io/finalapproval/final-approval-mcp:latest（公開イメージは近日公開予定です。ローカルでビルドすることも可能です: docker build -t finalapproval-mcp .）
変数 | 必須 | デフォルト | 用途 |
| はい | — | チャネルAPIキー ( |
| いいえ |
| セルフホスト / 開発用の上書き |
submit_approval は保留中の承認IDを即座に返します。実際の決定はMCP経由ではなく、チャネルのWebhook経由で届きます。ホストアプリケーション（エージェントのサーバー）は、HMAC署名を検証し、approved の場合はゲートされたアクションを実行し、denied の場合はログを記録するWebhookレシーバーを実装する必要があります。Webhookペイロードのスキーマについては FinalApprovalドキュメント を参照してください。
npm install
npm run build
FINALAPPROVAL_API_KEY=fa_... npm startMIT
Create a pending approval in the FinalApproval channel whose API key is configured in this MCP server. The channel's webhook fires when the human approves or denies. Use this before any irreversible agent action (sending email, merging a PR, publishing a post, running a migration, etc).
| Name | Required | Description | Default |
|---|---|---|---|
| title | Yes | Short headline shown in the approval list. | |
| body | Yes | HTML body shown to the human reviewer. Tailwind utility classes are supported. Include the actual content being gated (diff, PR body, email text) — the reviewer decides from this card alone. | |
| data | No | Machine-readable payload attached to the approval. Echoed back to the channel's webhook on resolution — put the structured args your callback will need to execute the gated action. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key behaviors: the approval is pending until human action, webhook firing on resolution, and the irreversible nature of gated actions. However, it lacks details on error handling, rate limits, or authentication requirements beyond the API key mention.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is efficiently structured in two sentences: the first defines the tool's purpose, and the second provides critical usage guidelines. Every phrase adds value, with no redundant or unnecessary information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations and no output schema, the description provides strong contextual completeness by explaining the approval workflow, webhook behavior, and use-case guidance. It adequately compensates for the lack of structured fields, though it could benefit from mentioning response format or error cases.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, providing full parameter documentation. The description adds minimal parameter semantics beyond the schema—it mentions the channel's API key context but doesn't elaborate on parameter usage or constraints. Baseline 3 is appropriate since the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Create a pending approval') and the target resource ('in the FinalApproval channel'), with specific context about the channel's API key configuration. It distinguishes this as a submission tool for approval requests, which is unambiguous even without sibling tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides explicit guidance on when to use this tool ('before any irreversible agent action') and lists concrete examples of such actions (sending email, merging a PR, etc.). This gives clear context for application without needing sibling tool comparisons.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0submit_approvalScored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool has a clear and distinct purpose for submitting approvals.
The tool name 'submit_approval' follows a clear verb_noun pattern. Since there is only one tool, consistency is inherently perfect with no deviations or mixed conventions.
A single tool is too few for most practical server purposes, as it severely limits functionality and scope. While it might serve a narrow use case, it feels thin and incomplete for typical agent workflows.
The server's domain appears to be approval workflows, but with only a submit tool, there are significant gaps. Missing operations likely include checking approval status, listing pending approvals, or handling approvals programmatically, which could cause agent failures.
Give any AI agent a way to ask a person — for approval, a decision, an answer or a review.
Supervised API-write gateway for AI agents with policy, human approval and execution receipts.
Human approvals, notifications, inbound webhooks, wake-ups for headless agents. Free trial: /try