imf-data-mcp
This MCP server integrates with the free IMF data API to provide a set of tools and resources for retrieving and processing economic data. It enables users to query datasets, fetch time series data, and list available indicators and countries, making it easier to work with IMF data in a structured and programmatic way.
Documentation
IMF Data MCP
A Model Context Protocol server for IMF economic data, built on
imfp and the
IMF SDMX API at `data.imf.org`.
> v0.2.0 — Breaking change: The old server called `dataservices.imf.org`,
> which the IMF decommissioned in 2025. All requests timed out as a result.
> This version migrates to `imfp`, which targets the current `data.imf.org`
> SDMX 3.0 API and is actively maintained.
Installation
Using `uv` (recommended)
uvx --from git+https://github.com/c-cf/imf-data-mcp imf-data-mcpUsing pip
pip install git+https://github.com/c-cf/imf-data-mcp.gitClaude Desktop configuration
{
"mcpServers": {
"imf": {
"command": "uvx",
"args": ["--from", "git+https://github.com/c-cf/imf-data-mcp", "imf-data-mcp"]
}
}
}Or, if installed via pip:
{
"mcpServers": {
"imf": {
"command": "imf-data-mcp"
}
}
}Available tools
| Tool | Description |
|---|---|
| `imf_list_databases` | List all ~155 IMF databases with their IDs |
| `imf_search_databases` | Filter databases by keyword (e.g. `"inflation"`, `"trade"`) |
| `imf_get_parameter_defs` | List query dimensions for a database |
| `imf_get_parameter_codes` | List valid codes for a dimension, with optional search |
| `imf_fetch_data` | Fetch time series data with year range and dimension filters |
Typical workflow
1. imf_search_databases(keyword="consumer price")
→ CPI, CPI_WCA, ...
2. imf_get_parameter_defs(database_id="CPI")
→ country, index_type, coicop_1999, frequency, ...
3. imf_get_parameter_codes(database_id="CPI", parameter="country", search="austria")
→ AUT
4. imf_fetch_data(
database_id="CPI",
start_year=2015, end_year=2023,
filters={"country": ["AUT"], "frequency": ["M"]}
)Common database IDs
| Topic | ID |
|---|---|
| Consumer Prices | `CPI` |
| Producer Prices | `PPI` |
| National Accounts (Annual) | `ANEA` |
| National Accounts (Quarterly) | `QNEA` |
| Balance of Payments | `BOP_AGG` |
| Exchange Rates | `ER_2026_JAN_VINTAGE` |
| Commodity Prices | `PCPS` |
| Fiscal Monitor | `FM` |
| Gov. Finance Statistics | `GFS_COFOG` |
| Monetary Statistics | `MFS_CBS`, `MFS_MA`, `MFS_IR` |
| Financial Soundness | `FSIC` |
| Trade in Services | `ITS` |
| SDG Data | `SDG` |
Rate limits
The IMF API allows roughly 10 requests / 5 seconds. `imfp` handles
rate limiting and retries automatically.
Debugging
npx @modelcontextprotocol/inspector imf-data-mcpLicense
Apache 2.0
Frequently asked questions
What is imf-data-mcp?
imf-data-mcp is This MCP server integrates with the free IMF data API to provide a set of tools and resources for retrieving and processing economic data. It enables users to query datasets, fetch time series data, and list available indicators and countries, making it easier to work with IMF data in a structured and programmatic way.
How do I install imf-data-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is imf-data-mcp open source?
Yes — it is hosted on GitHub at https://github.com/c-cf/imf-data-mcp and has 4 stars.
Related MCP tools
Browse the web, directly from Cursor etc. Built for the Model Context Protocol to enhance AI capabilities. Python-based implementation.
🙌 OpenHands: Code Less, Make More for the Model Context Protocol. Enhance AI assistants with powerful integrations. Python-based implementation.
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management. Python-based implementation.
基于大模型搭建的聊天机器人,同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入,可选择ChatGPT/Claude/DeepSeek/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Kimi/LinkAI,能处理文本、语音和图片,访问操作系统和互联网,支持基于自有知识库进行定制企业智能客服。
An LLM agent that conducts deep research (local and web) on any given topic and generates a long report with citations. Built for the Model Context Protocol to
🚀 The fast, Pythonic way to build MCP servers and clients Trusted by 19900+ developers. Trusted by 19900+ developers. Trusted by 19900+ developers.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP