# Relvo

> Connect AI agents to external data, tools, and action APIs through one gateway. Relvo routes requests across providers and switches automatically when one fails

Product: https://app.relvo.si
MCP: https://app.relvo.si/mcp
Setup guide: https://app.relvo.si/SKILL.md

## Core Pages
- [Relvo](https://relvo.si/): Connect AI agents to external data, tools, and action APIs through one gateway. Relvo routes requests across providers and switches automatically when one fails
- [Tool catalog](https://relvo.si/catalog): Browse platforms and tools and inspect per-call pricing.
- [Connections](https://relvo.si/connections): Connect your own accounts and provider keys.
- [Pricing](https://relvo.si/pricing): Free, Hobby and Pro plans, included tool runs and metered usage.
- [Documentation](https://relvo.si/docs): Getting started, permissions, execution and billing.
- [Agent connections](https://relvo.si/agents): Connect Claude, ChatGPT, Cursor, Codex and other MCP clients.
- [Providers](https://relvo.si/tools): Explore providers and their available tools.
- [Use cases](https://relvo.si/use-cases): Find tools by the task you want to accomplish.
- [Blog](https://relvo.si/blog): Product updates and guides from the Relvo team.
- [Support](https://relvo.si/support): Help with setup, billing and tool execution.
- [Terms](https://relvo.si/terms): Terms for the hosted Relvo service.
- [Privacy](https://relvo.si/privacy): How Relvo handles your information.
- [Relvo · 日本語](https://relvo.si/ja): Connect AI agents to external data, tools, and action APIs through one gateway. Relvo routes requests across providers and switches automatically when one fails
- [Tool catalog · 日本語](https://relvo.si/ja/catalog): Browse platforms and tools and inspect per-call pricing.
- [Connections · 日本語](https://relvo.si/ja/connections): Connect your own accounts and provider keys.
- [Pricing · 日本語](https://relvo.si/ja/pricing): Free, Hobby and Pro plans, included tool runs and metered usage.
- [Documentation · 日本語](https://relvo.si/ja/docs): Getting started, permissions, execution and billing.
- [Agent connections · 日本語](https://relvo.si/ja/agents): Connect Claude, ChatGPT, Cursor, Codex and other MCP clients.
- [Providers · 日本語](https://relvo.si/ja/tools): Explore providers and their available tools.
- [Use cases · 日本語](https://relvo.si/ja/use-cases): Find tools by the task you want to accomplish.
- [Blog · 日本語](https://relvo.si/ja/blog): Product updates and guides from the Relvo team.
- [Support · 日本語](https://relvo.si/ja/support): Help with setup, billing and tool execution.
- [Terms · 日本語](https://relvo.si/ja/terms): Terms for the hosted Relvo service.
- [Privacy · 日本語](https://relvo.si/ja/privacy): How Relvo handles your information.

## Documentation
- [Getting started](https://relvo.si/docs/getting-started): From your first project to your first result.
- [Core concepts](https://relvo.si/docs/concepts): Tools, platforms, providers and projects.
- [Connect an agent](https://relvo.si/docs/connect-an-agent): Set up an MCP client and discover tools.
- [API keys & access](https://relvo.si/docs/api-keys): Create, scope and rotate your credentials.
- [Teams & projects](https://relvo.si/docs/teams-and-projects): Keep people, access and work organized.
- [Running tools](https://relvo.si/docs/running-tools): Inputs, execution progress and results.
- [Workflows & triggers](https://relvo.si/docs/automations): Saved sequences, events and webhook deliveries.
- [Using the HTTP API](https://relvo.si/docs/http-api): Base URL, endpoints and the request lifecycle.
- [MCP server & CLI](https://relvo.si/docs/mcp-and-cli): MCP tools and settings, CLI commands.
- [Usage & billing](https://relvo.si/docs/usage-and-billing): Understand estimates and recorded usage.
- [Troubleshooting](https://relvo.si/docs/troubleshooting): Find the cause and recover your work.
- [はじめに · 日本語](https://relvo.si/ja/docs/getting-started): 最初のプロジェクトから、最初の結果まで。
- [基本コンセプト · 日本語](https://relvo.si/ja/docs/concepts): ツール、プラットフォーム、プロバイダー、プロジェクト。
- [エージェントを接続 · 日本語](https://relvo.si/ja/docs/connect-an-agent): MCPクライアントを設定し、ツールを見つけます。
- [APIキーとアクセス · 日本語](https://relvo.si/ja/docs/api-keys): 認証情報の作成、スコープ設定、ローテーション。
- [チームとプロジェクト · 日本語](https://relvo.si/ja/docs/teams-and-projects): 人、アクセス、作業を整理して保ちます。
- [ツールの実行 · 日本語](https://relvo.si/ja/docs/running-tools): 入力、実行の進捗、結果。
- [ワークフローとトリガー · 日本語](https://relvo.si/ja/docs/automations): 保存した手順、イベント、Webhookの配信。
- [HTTP APIの使い方 · 日本語](https://relvo.si/ja/docs/http-api): ベースURL、エンドポイント、リクエストのライフサイクル。
- [MCPサーバーとCLI · 日本語](https://relvo.si/ja/docs/mcp-and-cli): MCPのツールと設定、CLIのコマンド。
- [利用状況と請求 · 日本語](https://relvo.si/ja/docs/usage-and-billing): 見積もりと記録された利用量を理解します。
- [トラブルシューティング · 日本語](https://relvo.si/ja/docs/troubleshooting): 原因を見つけて、作業を再開します。

## Articles
- [How to Build an MCP Server: A Python Tutorial](https://relvo.si/blog/how-to-build-an-mcp-server-a-python-tutorial): To build an MCP server, define a tool, register it with an MCP SDK, test it with an MCP client, and connect it to the application that will use it. Start with a local, read-only tool; add real data, credentials, and state-changing operations only after you have defined how access and failures will b
- [What Is Tool Calling? How AI Models Use External Tools](https://relvo.si/blog/what-is-tool-calling-how-ai-models-use-external-tools): Tool calling lets an AI model request a named tool with structured arguments so an application can retrieve information or perform an action. The model proposes the call; trusted application code decides whether to execute it, returns the result, and controls when the process stops. Key Takeaways A
- [Agent-Friendly API Design Specification: A Practical Guide](https://relvo.si/blog/agent-friendly-api-design-specification-a-practical-guide): An agent-friendly API design specification tells an agent what an operation does, which inputs it accepts, what it returns, and what to do when the outcome is uncertain. Start with a valid machine-readable API contract, then make the details an agent needs to choose, execute, and recover from a call
- [5 Best AI Orchestration Tools: How to Choose the Right Layer](https://relvo.si/blog/5-best-ai-orchestration-tools-how-to-choose-the-right-layer): The right AI orchestrator depends on what you need to control. Choose a workflow orchestrator for a defined process, an agent framework for model-directed decisions within a task, and a tool-access router when the main problem is connecting those applications to external services. Many teams need mo
- [API vs MCP: What’s the Difference for AI Applications?](https://relvo.si/blog/api-vs-mcp-what-s-the-difference-for-ai-applications): A service API defines how software interacts with a particular service. The Model Context Protocol (MCP) defines how an AI application communicates with a server that offers tools or context. They are different layers, not mutually exclusive choices: an application can call a service API directly, c
- [How Does an API Timeout Work? Causes, Diagnosis, and Safe Retries | Relvo](https://relvo.si/blog/how-does-an-api-timeout-work-causes-diagnosis-and-safe-retries-relvo): An API timeout occurs when a caller or intermediary stops waiting because a time limit has been reached. It means a response did not arrive within that boundary—not that the remote operation necessarily failed or never ran. Before retrying a request that changes data or triggers an action, determine
- [What Are Agentic Workflows? A Practical Guide to Design and Evaluation](https://relvo.si/blog/what-are-agentic-workflows-a-practical-guide-to-design-and-evaluation): An agentic workflow is a sequence of steps in which an AI agent makes some decisions about how to reach a defined outcome, while the surrounding application sets the task, checks results, and controls when work ends. The design challenge is not to make every step autonomous; it is to decide where ju
- [How to Expose APIs to AI Agents Safely: A Developer Checklist](https://relvo.si/blog/how-to-expose-apis-to-ai-agents-safely-a-developer-checklist): The safest way to expose an existing API to an AI agent is to put a controlled execution layer between the model and the API. The model proposes a tool call; your application validates it, checks the user’s authority, obtains the right credential, and decides whether to execute or request approval.
- [Introducing Relvo: The Smart Router Unifying External Tool Integrations for AI Agents](https://relvo.si/blog/introducing-relvo-the-smart-router-unifying-external-tool-integrations-for-ai-agents): Building production-grade AI agents requires connecting foundational models to real-world data and action APIs, yet integrating dozens of external services quickly introduces fragile codebases, sprawling vendor contracts, and unexpected downtime. We built Relvo as an intelligent gateway and router f
- [MCP実装の始め方｜Pythonでサーバーを作る手順と安全な接続方法](https://relvo.si/ja/blog/mcp-python-server-secure-connections): MCP実装は、まず読み取り専用の小さなサーバーを作り、MCP対応クライアントからツールの一覧取得と実行を確認するところから始めます。Pythonの公式SDKを使えば、通信処理を一から書かずにツールを公開できますが、入力検証やアクセス権限、安全な停止は別途設計が必要です。 この記事では、ローカルで動く検索ツールのコードから、クライアント接続、テスト、本番運用に向けた注意点まで解説します。 この記事の要点 まずは一つの操作を実装する：読み取り専用の検索を公開し、入力から結果まで確認します。 SDKのバージョンをそろえる：この記事はPython公式SDKのv2系を使います。v1系とはクラス名やインポ
- [AIエージェントの活用例10選｜業務別の使い方と企業事例、導入手順](https://relvo.si/ja/blog/ai-agent-use-cases-business-examples-implementation): AIエージェントの活用例には、社内問い合わせへの回答、営業前の情報収集、請求書の照合、システム障害の調査などがあります。まずは情報を集めて下書きや候補を作り、人が確認する業務から選ぶと、実行範囲と成果を検証しやすくなります。 この記事では、業務別の具体例と実際の企業事例を分けて紹介し、自社に合う用途の選び方、必要な連携、安全に試す手順を解説します。 この記事の要点 活用例は身近な業務から探す：問い合わせ対応、営業、経理、調査、開発などで、情報収集から次の行動の提案までを組み合わせられます。 AIに任せる範囲を決める：候補の抽出や文章の下書きはAIに任せ、支払い、外部送信、重要な判断は人の承認を