OECD MCP Server

Public Hosted Server: https://oecd.caseyjhand.com/mcp

Overview

OECD statistical data via the SDMX 2.1 REST API — 1,500+ dataflows spanning national accounts, employment, trade, education, and health. Search datasets, inspect their dimensions, resolve codes, and query observations, with large multi-country time-series spilling to a queryable DataCanvas table for SQL analysis. Runs as a stdio process, a local Streamable HTTP server, or the public hosted endpoint above.

Tools

Five discovery and data tools plus three DataCanvas tools for large query results:

Resources

All resource data is also reachable via tools. Use oecd_get_dataset_info for the same content.

Related MCP server: OECD Stats MCP

Capability reference

oecd_list_agencies tool

• No inputs; returns every agency ID (e.g. OECD.SDD.NAD) with its directorate name and dataflow count, sorted by count

• Publishers outside OECD that ship dataflows through the same catalog (ESTAT, IAEG-SDGs) carry no directorate

oecd_search_datasets tool

• query token-matched across dataflow names and descriptions; optional agency_id scope; limit (1–100) and offset paging with total_matches

• Each result carries its flow_ref — the identifier every other tool takes — and matched_in (name, description, or both)

oecd_get_dataset_info tool

• Takes a flow_ref; returns every dimension in key order with its concept name and codelist reference, plus a key_example for oecd_query_dataset

• Fails invalid_flow_ref for a string that is not a flow reference and dataflow_not_found for one OECD does not publish

oecd_get_dimension_values tool

• Takes a flow_ref and dimension_id; optional query substring-matches both code and label

• limit (1–500, default 50) and offset page the matches, with the full match count when more remain

oecd_query_dataset tool

• flow_ref plus a dot-delimited key (+ for multiple values, empty segments as wildcards) and optional start_period / end_period

• One row per observation with every dimension and attribute as its own column; value is pre-multiplied by value_scale

• Large results spill to DataCanvas with truncated: true, canvas_id, and table_name; without a canvas every row stays in structuredContent and only the rendered table is capped (content_table_capped)

oecd_dataframe_describe tool

• Takes the canvas_id oecd_query_dataset returned; lists each staged table and view with its row count and column names and types

oecd_dataframe_query tool

• canvas_id plus one read-only SQL SELECT; writes, DDL, and system-catalog access are rejected

• Returns rows capped at the canvas row limit, with row_count reporting the full count

oecd_dataframe_drop tool

• canvas_id plus a table_name as oecd_dataframe_describe lists it; returns the dropped object's kind and the remaining_tables

• Opt-in: listed but not callable unless OECD_DATAFRAME_DROP_ENABLED=true

oecd://dataflow/{agency_id}/{flow_id} resource

• Same content as oecd_get_dataset_info, as application/json

• {flow_id} is {dsd_id}@{df_id} with @ encoded as %40 (e.g. oecd://dataflow/OECD.SDD.NAD/DSD_NAAG%40DF_NAAG_I), or the bare {df_id}

Features

Built on @cyanheads/mcp-ts-core: stdio and Streamable HTTP transports, pluggable auth (none / jwt / oauth), swappable storage (in-memory, filesystem, Supabase, Cloudflare KV/R2/D1), structured logging with optional OpenTelemetry tracing.

OECD-specific:

• Keyless access — no API key required; OECD SDMX 2.1 REST API is fully public

• Covers 1,500+ dataflows across 20+ OECD statistical departments (national accounts, employment, inflation, trade, education, health, environment, taxation, inequality)

• Delegated dataflows and codelist revisions resolved end to end — a dataflow OECD catalogues on one service root but defines on another follows the catalog's own link for structure, codes, and observations, and codes come from the revision the datastructure names rather than the endpoint's current latest

• AllDimensions observation mode — one-pass SDMX-JSON decoding into flat row objects, no nested series key reconstruction

• oecd_query_dataset materializes large observation sets (multi-country time-series) on a DuckDB DataCanvas for in-conversation SQL analytics; the three oecd_dataframe_* tools work on it and need CANVAS_PROVIDER_TYPE=duckdb

Agent-friendly output:

• Workflow-aware tool surface — flow_ref from search flows directly into info, values, and query tools without reconstruction

• Spill signaling — truncated: true + canvas_id tells the agent to switch to SQL instead of parsing a truncated inline list

• Full SDMX decoding server-side — agents see { REF_AREA: "United States", MEASURE: "Gross domestic product", UNIT_MULT: "Billions", value: 26054614000000, value_scale: 1000000000 }, not raw index arrays

Getting started

Public Hosted Instance

A public instance is available at https://oecd.caseyjhand.com/mcp — no installation required. Point any MCP client at it via Streamable HTTP:

{
  "mcpServers": {
    "oecd-mcp-server": {
      "type": "streamable-http",
      "url": "https://oecd.caseyjhand.com/mcp"
    }
  }
}

Self-Hosted / Local

Add the following to your MCP client configuration file.

{
  "mcpServers": {
    "oecd-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/oecd-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with npx (no Bun required):

{
  "mcpServers": {
    "oecd-mcp-server": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@cyanheads/oecd-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "MCP_LOG_LEVEL": "info"
      }
    }
  }
}

Or with Docker:

{
  "mcpServers": {
    "oecd-mcp-server": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run", "-i", "--rm",
        "-e", "MCP_TRANSPORT_TYPE=stdio",
        "ghcr.io/cyanheads/oecd-mcp-server:latest"
      ]
    }
  }
}

To enable DataCanvas SQL analytics for large query results, add CANVAS_PROVIDER_TYPE=duckdb:

{
  "mcpServers": {
    "oecd-mcp-server": {
      "type": "stdio",
      "command": "bunx",
      "args": ["@cyanheads/oecd-mcp-server@latest"],
      "env": {
        "MCP_TRANSPORT_TYPE": "stdio",
        "CANVAS_PROVIDER_TYPE": "duckdb"
      }
    }
  }
}

For Streamable HTTP, set the transport and start the server:

MCP_TRANSPORT_TYPE=http MCP_HTTP_PORT=3010 bun run start:http
# Server listens at http://localhost:3010/mcp

Prerequisites

• Bun v1.4.0 or higher (or Node.js v24+).

• No API key required — OECD SDMX is a free, public API.

Installation

1. Clone the repository:

git clone https://github.com/cyanheads/oecd-mcp-server.git

2. Navigate into the directory:

cd oecd-mcp-server

3. Install dependencies:

bun install

4. Configure environment:

cp .env.example .env
# edit .env — most vars are optional; no API key required

Configuration

All configuration is validated at startup via Zod schemas in src/config/server-config.ts. Key environment variables:

See .env.example for the full list of optional overrides.

Running the server

Local development

• Build and run:

  # One-time build
  bun run rebuild
  
  # Run the built server
  bun run start:stdio
  # or
  bun run start:http

• Run checks and tests:

  bun run devcheck   # Lint, format, typecheck, security
  bun run test       # Vitest test suite
  bun run lint:mcp   # Validate MCP definitions against spec

Docker

docker build -t oecd-mcp-server .
docker run --rm -p 3010:3010 oecd-mcp-server

The Dockerfile defaults to HTTP transport, stateless session mode, and logs to /var/log/oecd-mcp-server. OpenTelemetry peer dependencies are installed by default — build with --build-arg OTEL_ENABLED=false to omit them.

Project structure

Development guide

See CLAUDE.md for development guidelines and architectural rules. The short version:

• Handlers throw, framework catches — no try/catch in tool logic

• Use ctx.log for request-scoped logging, ctx.state for tenant-scoped storage

• Register new tools and resources via the barrels in src/mcp-server/*/index.ts

• Wrap external API calls: validate raw SDMX-JSON → normalize to domain type → return output schema; never fabricate missing fields

Contributing

Issues are welcome — see CONTRIBUTING.md for what makes one actionable, and CODE_OF_CONDUCT.md for how we work together. Run checks and tests before submitting:

bun run devcheck
bun run test

License

Apache-2.0 — see LICENSE for details.