Model Context Protocol (MCP)

MCP — the Model Context Protocol — is the open standard for letting AI agents talk to tools and data sources. Restura plays both sides.

As an MCP client

Point Restura at any MCP server and explore it like any other request target.

• streamable-http transport — the modern wire shape.
• http-sse transport — older shape, also supported.
• stdio subprocess transport — desktop only (requires spawning a child process).
• List tools — see the server’s exposed tool catalogue with schemas.
• Invoke a tool — fill in the JSON schema, send, watch the streamed result.
• List prompts / list resources — for servers that expose them.

As an MCP server

Restura can be an MCP server, exposing your saved data to an agent like Claude.

The desktop app exposes these tools:

• list_collections — enumerate your collections.
• list_requests — browse requests inside a collection (filterable by folder).
• list_environments — list environments and their currently active variables.
• get_environment — fetch one environment’s details, with secrets auto-redacted.
• get_history — query past request executions with filters and a limit.

Every tool is consent-gated (the user approves the connecting agent) and every response is redacted so secrets, tokens, and auth headers don’t leak into agent context.

See the MCP server mode guide for setup.

Related

• AI assistant — Restura’s built-in chat with OpenAI / Anthropic / OpenRouter, which can use request context and tools.
• MCP server mode — set up Restura as an MCP server in your agent.