Riksbank Mcp – Swedish Monetary‑Policy Data Server

The Riksbank Mcp turns the Riksbank’s open API into a fully‑typed, asynchronous MCP micro‑service. By wrapping each time‑series endpoint as an individual MCP tool, the server removes the need for developers to craft HTTP requests or understand the intricacies of Riksbank’s data model. Instead, an AI assistant or any MCP‑compatible client can discover and invoke these tools with a simple JSON payload, enabling on‑demand access to both forecast vintages and realised observations for Swedish macroeconomic variables.

What Problem It Solves

Monetary‑policy data from central banks is notoriously fragmented: raw REST endpoints, versioned forecasts, and separate observation feeds require manual joins and careful handling of policy rounds. The Riksbank Mcp abstracts these complexities, presenting a unified, discoverable interface that automatically manages policy‑round selection and vintage resolution. This allows analysts, journalists, and developers to query “What did the Riksbank forecast for GDP in 2024?” or “What is the final realised inflation figure for 2022?” without writing custom parsers or dealing with HTTP plumbing.

Core Features and Capabilities

• Typed MCP Tools – Each economic series (≈30 in total) becomes a first‑class tool, complete with metadata such as frequency, decomposition, and units.
• Policy Round Awareness – Tools accept a parameter (, e.g., ) or the keyword . The server then returns the appropriate forecast vintage, optionally merged with any available realised observations.
• Realised Observations – When official figures are released, the server transparently overlays them onto the forecast data, giving users a single view that contains both projected and final values.
• Async FastAPI Architecture – The server runs on FastMCP, exposing tools over standard input/output, SSE, or HTTP. This makes it suitable for both command‑line workflows and cloud deployments.

Use Cases

• Economic Research – Researchers can pull historical forecast revisions to study bias or accuracy in monetary‑policy expectations.
• Financial Journalism – Journalists can embed live data queries into articles, automatically refreshing forecasts or comparing them to the latest observations.
• Policy Simulation – Developers building economic models can feed real‑time Riksbank data into simulations, ensuring that policy assumptions reflect the most recent forecasts.
• Educational Tools – Teachers can use the server to demonstrate how central‑bank expectations evolve over time, highlighting the impact of new policy rounds.

Integration with AI Workflows

Because every series is exposed as an MCP tool, any LLM that supports the Model‑Context Protocol can call these tools directly. For example, a Claude Desktop session might ask, “Show me the Riksbank’s latest forecast for Swedish inflation.” The assistant translates that request into a tool invocation, receives the typed response, and renders it in context—all without leaving the chat. This tight integration streamlines data retrieval within conversational AI, eliminating the need for external API keys or manual request construction.

Standout Advantages

• Unified Vintage Handling – The server automatically resolves which forecast version to return, relieving users from tracking policy‑round dates manually.
• Realised Data Overlay – By merging forecasts with final observations, the MCP provides a single, coherent dataset that reflects both expectations and outcomes.
• Developer‑Friendly – With a clean, async Python API and automatic tool discovery, developers can integrate Riksbank data into existing MCP pipelines or build new applications with minimal friction.

In sum, the Riksbank Mcp offers a powerful, developer‑centric gateway to Swedish monetary‑policy data, enabling rapid, accurate, and contextually rich access for AI assistants, analysts, journalists, and researchers alike.