Allows an AI client to search and retrieve economic time series data from the Federal Reserve Bank of St. Louis, including historical vintage data.
Also known as mcpwright/fred-mcp, fred-mcp, mcpwright-fred
- Stars
- 0
- Tools
- 6
- Downloads, 30 days
- 163
- Latest version
- 0.1.1
- Last commit
- Aug 20, 2026
- License
- MIT
What is FRED MCP?
FRED allows an AI client to search and retrieve economic time series data from the Federal Reserve Bank of St. Louis, including historical vintage data. It exposes 6 tools, such as search_series, get_series, get_observations.
Summary generated from the project's README
About FRED MCP server
Accessing economic time series data from the Federal Reserve Bank of St. Louis is possible through this MCP server, which connects AI agents to over 800,000 U.S. and international datasets. It allows users to search for specific series, retrieve the latest values, follow release calendars, and compare multiple datasets on a single axis. The server is designed for read-only access and requires a personal FRED API key to function.
What distinguishes this tool is its ability to query ALFRED vintage data, enabling agents to see economic numbers exactly as they were published on a specific past date. This prevents errors in reasoning that occur when an AI uses current, revised figures to analyze historical decisions. Users can also track the full revision history of a single data point from its initial print to its current value. The server uses a volatility-aware cache to manage live API calls efficiently while keeping vintage data immutable.
What you can do with it
- 1Analyze historical economic decisionsRetrieve what a specific economic indicator looked like on a past date to understand the information available to policymakers at that time.
Written from the project's README. Every use case is checked against a quote from it.
How to install FRED MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall FRED MCP in Claude Code
$ claude mcp add --env 'FRED_API_KEY=<FRED_API_KEY>' fred-mcp -- uvx mcpwright-fredInstall FRED MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"fred-mcp": {
"command": "uvx",
"args": [
"mcpwright-fred"
],
"env": {
"FRED_API_KEY": "<FRED_API_KEY>"
}
}
}
}Install FRED MCP in VS Code
.vscode/mcp.json
{
"servers": {
"fred-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"mcpwright-fred"
],
"env": {
"FRED_API_KEY": "<FRED_API_KEY>"
}
}
}
}Install FRED MCP in VS Code CLI
$ code --add-mcp '{"name":"fred-mcp","type":"stdio","command":"uvx","args":["mcpwright-fred"],"env":{"FRED_API_KEY":"<FRED_API_KEY>"}}'Install FRED MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"fred-mcp": {
"command": "uvx",
"args": [
"mcpwright-fred"
],
"env": {
"FRED_API_KEY": "<FRED_API_KEY>"
}
}
}
}Install FRED MCP in Codex
$ codex mcp add fred-mcp --env 'FRED_API_KEY=<FRED_API_KEY>' -- uvx mcpwright-fredInstall FRED MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.fred-mcp] command = "uvx" args = ["mcpwright-fred"] [mcp_servers.fred-mcp.env] FRED_API_KEY = "<FRED_API_KEY>"
Install FRED MCP in Gemini CLI
$ gemini mcp add -s user -e 'FRED_API_KEY=<FRED_API_KEY>' fred-mcp uvx -- mcpwright-fredInstall FRED MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"fred-mcp": {
"command": "uvx",
"args": [
"mcpwright-fred"
],
"env": {
"FRED_API_KEY": "<FRED_API_KEY>"
}
}
}
}FRED MCP tools 6
Detected from the READMEsearch_seriesget_seriesget_observationsget_latestcompare_seriesget_release_calendar
| search_series | — | |
| get_series | — | |
| get_observations | — | |
| get_latest | — | |
| compare_series | — | |
| get_release_calendar | — |
Configuration
FRED_API_KEYRequiredYour own free FRED API key (get one at fred.stlouisfed.org/docs/api/api_key_request.html). Keys are personal under the FRED API Terms of Use.
FRED_MCP_USER_AGENTDescriptive User-Agent identifying your deployment. Optional.
| Name | Description | |
|---|---|---|
| FRED_API_KEY | Your own free FRED API key (get one at fred.stlouisfed.org/docs/api/api_key_request.html). Keys are personal under the FRED API Terms of Use. | Required |
| FRED_MCP_USER_AGENT | Descriptive User-Agent identifying your deployment. Optional. |
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablemcpwright/fred-mcp is public and reachablegithub.com/mcpwright/fred-mcp ↗Pass
- Package names this repository as its sourcemcpwright-fred names mcpwright/fred-mcp as sourcepypi.org/project/mcpwright-fred/ ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-08-20github.com/mcpwright/fred-mcp ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from mcpwright-fredPass
- No critical advisory in the package or its dependencies38 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model6 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubfred-mcp
FRED® economic data inside your AI agent — including what the numbers said before the revisions. An MCP server for the Federal Reserve Bank of St. Louis's FRED® API: search and read 800,000+ U.S. and international time series, follow the release calendar, and — the distinctive part — query ALFRED® vintage data: any series exactly as it was known on a past date, and any single data point's full revision history from its initial print to today's value.
Read-only, built on public endpoints, powered by your own free FRED API key. Live API calls with a volatility-aware cache (vintage reads are immutable and cache long; current data stays fresh) — no bulk mirroring.
This product uses the FRED® API but is not endorsed or certified by the Federal Reserve Bank of St. Louis. By using this server you agree to the FRED® API Terms of Use.
Status: v0.1.0 — live on PyPI
(uvx mcpwright-fred) and the official MCP Registry
(io.github.mcpwright/fred-mcp). 9 tools, CI-gated, built on
mcpwright-core.
Why vintage data matters
Economic numbers get revised — sometimes dramatically. The advance estimate
of Q4-2008 real GDP told policymakers the economy was shrinking far more
slowly than the number that stands today. If an agent reasons about what
decision-makers knew at the time using current data, it is quietly wrong.
get_series_as_of and get_revision_history make as-published data a
first-class question.
Tools
| Tool | What it does |
|---|---|
search_series |
Find series IDs by free text, best matches first |
get_series |
One series' full metadata + verbatim notes |
get_observations |
A date window of values; transforms (pct_change_yoy, …) + downsampling |
get_latest |
The most recent value + the next scheduled release date |
compare_series |
2–5 series aligned on one date axis |
get_release_calendar |
Upcoming data releases ("when's the next jobs report?") |
get_series_as_of ⭐ |
A series exactly as known on a past date (ALFRED vintage) |
get_revision_history ⭐ |
One data point's life: initial print → every revision → today |
get_vintage_dates ⭐ |
When a series was released/revised; bounds the vintage tools |
All tools are read-only and annotated as such.
What can you ask?
Every question below was run live against the real FRED API through these tools (answers as of June 2026 — ask again and they'll be current).
Everyday questions:
- "What's the unemployment rate right now, and when's the next jobs
report?" —
get_latest(UNRATE)→ 4.3% (May 2026), next release 2026-07-02. - "What's the 10-year Treasury yield today?" —
get_latest(DGS10)→ 4.53% (it correctly skips the.rows daily series publish on holidays). - "How has inflation trended over the past year?" —
get_observations(CPIAUCSL, transform=pct_change_yoy)→ 2.4% → 3.3% → 3.8% → 4.2% over Feb–May 2026. - "Find me data on median household income." —
search_series→MEHOINUSA672N(real) andMEHOINUSA646N(nominal), annual. - "Is the labor market loosening? Compare unemployment and job openings
since 2024." —
compare_series([UNRATE, JTSJOL])→ one aligned table. - "What economic data comes out this week?" —
get_release_calendar(7)→ 241 release dates, CPI included. - "What was real GDP growth each quarter of 2025?" —
get_observations(A191RL1Q225SBEA)→ −0.6, +3.8, +4.4, +0.5%. - "Give me CPI as annual averages for the 2020s." —
get_observations(CPIAUCSL, frequency=annual)→ one row per year.
Questions only the vintage tools can answer:
- "How bad did Q4-2008 GDP look to policymakers in early 2009, versus what
we know now?" —
get_series_as_of(GDPC1, "2009-02-15")→ a −3.8% annualized decline as known then (in chained-2000 dollars — the metadata is vintage-pinned too) versus −8.5% in today's data. Policy ran on the first number. - "Was the May 2020 COVID unemployment rate ever revised?" —
get_revision_history(UNRATE, "2020-05-01")→ first published as 13.3 (2020-06-05), currently 13.2, with each revision dated. - "What mortgage rate did the Fed see going into the March 2022 liftoff
meeting?" —
get_series_as_of(MORTGAGE30US, "2022-03-16")→ 3.85% as known then; 6.48% today. - "How often does GDP actually get revised?" —
get_vintage_dates(GDPC1)→ 415 vintages since 1991-12-04.
Install
You need a free FRED API key (takes seconds): https://fred.stlouisfed.org/docs/api/api_key_request.html. Keys are personal under the FRED terms — bring your own.
uvx (any MCP client)
{
"mcpServers": {
"fred": {
"command": "uvx",
"args": ["mcpwright-fred"],
"env": { "FRED_API_KEY": "your-key-here" }
}
}
}
Claude Code
claude mcp add fred -e FRED_API_KEY=your-key-here -- uvx mcpwright-fred
Claude Desktop
Use the one-click .mcpb extension from the
latest release (it prompts
for your API key), or add the uvx JSON above to your
claude_desktop_config.json.
OpenAI Agents SDK / other clients
Any MCP-capable client works — point it at uvx mcpwright-fred over stdio
with FRED_API_KEY in the environment.
Notes
- Revisions: current values often differ from what was originally published; for "what was known at the time", use the vintage tools.
- Copyrighted series: some FRED series are owned by third parties; their
notes carry the owner's terms (surfaced verbatim, flagged via
copyrighted). You are responsible for complying with them beyond personal use. - Caching & rate limits: responses are cached in-memory (vintage reads
long, live reads short) and requests are throttled well under FRED's rate
limit. Set
FRED_MCP_CACHE=0to disable caching,FRED_MCP_USER_AGENTto identify your own deployment.
Develop
git clone https://github.com/mcpwright/fred-mcp && cd fred-mcp
uv sync
uv run pytest # tests
uv run mypy # types
uv run ruff check src/ && uv run ruff format --check src/ # lint + format
uv run pre-commit run --all-files # everything, like CI
Dev loop: feature branch → PR → Code Quality & Tests green → squash-merge.
Roadmap
- v1 tool surface (9 tools incl. the ALFRED vintage lane)
- Publish to PyPI (
mcpwright-fred) + the MCP Registry - Site page at mcpwright.com/fred
-
.mcpbone-click Claude Desktop extension (v0.1.0 release) - GeoFRED / maps (pairs with census-mcp)
Questions & feedback
Discussions for questions and ideas · Issues for bugs.
Part of mcpwright — polished MCP servers for authoritative public data · built by Devender Gollapally. FRED® and ALFRED® are registered trademarks of the Federal Reserve Bank of St. Louis. This project is not affiliated with, endorsed, or certified by the Federal Reserve Bank of St. Louis.
FRED MCP questions
How do I add FRED MCP to Claude Code?
Run claude mcp add --env 'FRED_API_KEY=<FRED_API_KEY>' fred-mcp -- uvx mcpwright-fred in your terminal. Add --scope user to make it available in every project.
How do I add FRED MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does FRED MCP provide?
It exposes 6 tools, including search_series, get_series, get_observations, get_latest, compare_series.
What is the difference between FRED and ALFRED data?
FRED provides current economic time series, while ALFRED provides vintage data, allowing you to see data exactly as it was published before any revisions.