FactIQ - a real-time finance and economy database for AI Agents

Turn your agent into a finance and economy analyst. This plugin for Claude
(web, desktop, and Cowork), ChatGPT (web and desktop), Claude Code, and Codex gives the
agent direct access to
FactIQ's warehouse of official statistics — SEC filings, US, China, India, Korea, IMF,
World Bank, and more — plus live market data, earnings-call transcripts,
executive media appearances, central-bank speeches, minutes, and statements,
and satellite-derived data (fire detections,
air-quality activity signals,
rainfall, nighttime lights, shipping and port activity, reservoir levels).
The agent discovers series, runs read-only SQL, computes derived metrics, and
returns a sourced answer, chart JSON, or report JSON.

No codebase or hosted database is required — only a free
FactIQ account.

Want to contribute? The highest-leverage addition is a domain playbook that
teaches the agent a whole class of questions — see
Contributing.

Install

FactIQ supports four client paths. The website guides are canonical for app
setup and plan requirements, which can change faster than this repository:

Client	Supported surfaces	Setup guide
Claude	Web, desktop, and Cowork	factiq.com/claude
ChatGPT	Web and desktop app (including Codex in the app)	factiq.com/chatgpt
Claude Code	CLI, desktop app, and IDE extensions	factiq.com/claude-code
Codex	CLI	factiq.com/codex

Claude (web, desktop, and Cowork)

FactIQ is listed in the official Claude directory. Open
claude.ai/directory/factiq while signed
in to Claude, click Connect, complete the FactIQ sign-in, and start a new
chat. You can also find it under Customize → Plugins by searching for
FactIQ. For the best experience, use Cowork. The plugin requires a paid Claude
plan.

To install from this repository instead, open Customize → Plugins, add
defog-ai/factiq-plugin as a personal marketplace, install FactIQ, and
complete the browser sign-in. Organizations that approve plugins centrally can
mirror this repository as a private marketplace. See the
Claude guide for the current steps and
organization-policy notes.

ChatGPT (web and desktop)

FactIQ is listed in the official ChatGPT plugin directory. Open the
FactIQ listing
while signed in to ChatGPT, click Install plugin, complete the FactIQ
sign-in, and start a new chat. Type @FactIQ to select it explicitly. This
works on ChatGPT Plus, Pro, Business, Enterprise, and Edu plans, on the web and
in the desktop app. On Business, Enterprise, and Edu, a workspace admin may need
to allow FactIQ first. The install also covers Codex inside the ChatGPT app;
Codex CLI uses the separate setup below.

To install from this repository instead, open Plugins in the ChatGPT
desktop app, add defog-ai/factiq-plugin as a marketplace, and install FactIQ
from the Personal tab. This path works only in the desktop app, on a Pro,
Business, Enterprise, or Edu plan. See the
ChatGPT guide for the current plan matrix and
troubleshooting steps.

Claude Code

/plugin marketplace add defog-ai/factiq-plugin
/plugin install factiq@factiq
/reload-plugins

Run /reload-plugins after installing so Claude Code picks up the new
skill and MCP server in the current session (otherwise they only appear the
next time you start Claude Code).

This adds the FactIQ skill (Claude invokes it automatically for
economic/financial data questions) and the bundled FactIQ MCP server. Claude
Code namespaces skills installed from plugins, so its manual invocation is:

Command	Purpose
/factiq:factiq <question>	Run an analysis and get a sourced answer, chart JSON, or report

Finally, authenticate the MCP server:

1. Run /mcp.
2. Select factiq from the list of servers.
3. Choose Authenticate (or Connect) to open the browser sign-in.
4. Complete the FactIQ login (email, Google, or passkey) and return to Claude
   Code — the FactIQ tools are now authorized.

Enable auto-updates

So you always get the latest skill and MCP tools without
reinstalling, turn on auto-updates for the marketplace:

1. Run /plugin.
2. Select Marketplaces.
3. Select factiq.
4. Toggle auto-updates on.

Claude Code will then refresh the plugin automatically whenever this
marketplace changes.

Codex

codex plugin marketplace add defog-ai/factiq-plugin
codex plugin add factiq@factiq

Then authorize the MCP server:

codex mcp login factiq

Complete the browser sign-in (the same FactIQ login: email, Google, or
passkey). Start a new Codex thread after installation; the skill auto-invokes
for economic/financial data questions.

Update an existing Codex install

To update after this marketplace changes, refresh the configured marketplace
name (factiq), then reinstall the plugin:

codex plugin marketplace upgrade factiq
codex plugin add factiq@factiq

Alternative: install as a standalone MCP server (no plugin)

Add the MCP server directly to your Codex config (~/.codex/config.toml):

[mcp_servers.factiq]
url = "https://api.factiq.com/mcp"

Then codex mcp login factiq. The skill won't auto-invoke without the plugin,
but the MCP tools are available for manual use.

For Claude Code without the plugin:

claude mcp add --transport http factiq https://api.factiq.com/mcp

Then authorize with /mcp.

Without a browser: scripts, CI, and headless agents

Every FactIQ tool also works with a personal API key instead of the browser
sign-in. Create the key at factiq.com/settings/security.
The guide at factiq.com/docs/api shows how
to call the REST endpoints and the MCP server with the key, and how to register
the server in Claude Code or Codex without a browser. Keep the key out of
source control. Regenerating it on the settings page revokes the old one
immediately.

What the plugin sends and runs

• One remote MCP server. The plugin adds https://api.factiq.com/mcp
  (see .mcp.json), which you sign in to with OAuth. Each tool call sends its
  arguments (search terms, SQL statements, series IDs, tickers, regions) to
  that server and returns FactIQ data. FactIQ records connector tool inputs
  and outputs for reliability and support, as described in the
  privacy policy.
• One tool that sends a message. send_feedback sends a short report,
  written by the agent, to the FactIQ team when a FactIQ result looks wrong.
  It changes no data. Every other tool only reads data.
• Local scripts with no network access. The skill can run the Python
  scripts in scripts/ (hs_codes.py, trade_sql.py, comext_sql.py,
  series_math.py). They read only their arguments, files you pass them, and
  the bundled files in scripts/data/, and they print their result. They make
  no network calls.
• Local outputs only. Charts and reports are files written in your own
  workspace. The plugin does not publish them anywhere.
• The plugin has no hooks and runs nothing when it is installed.

Try it

Once installed and authenticated, ask a question:

/factiq:factiq How has India's trade deficit with China evolved since 2020?

The agent finds the relevant series, runs the SQL, and replies with a sourced
answer, chart JSON, or full report, depending on what you ask for. You
don't need the slash command: any
economic or financial data question in any supported client auto-invokes the
skill.

For an earnings question such as "What did Micron management say on its latest
call?", the skill checks live transcript coverage first, pins the exact fiscal
quarter, and then retrieves bounded management-claim and Q&A-pressure rows for
that same call. It keeps spoken remarks separate from formal guidance and SEC
filed actuals; the tool does not return a raw transcript.

For a media question such as "How has Jensen Huang discussed export controls
outside earnings calls?", the skill checks company-level structured coverage,
runs deterministic lexical retrieval with relevance ordering, and uses explicit
newest ordering only for a timeline. Results are public-safe paraphrases with
timestamped YouTube links, not quotations; the workflow verifies the linked
source when exact wording or tone is material. A dedicated playbook also keeps
media-vs-earnings comparisons aligned by company, person, topic, and date.
The same tool covers documents published by central banks and monetary
authorities (the Federal Reserve, the European Central Bank, the Bank of
England, the Bank of Japan, the Reserve Bank of India, and others): a question
such as "What has the Bank of Japan said about the inflation outlook?" filters
by institution or country and reports the meeting or speech date that each
document carries.

How it works

Your coding agent is the analyst: it finds the data, does the math, and
authors a local output. Data access uses the FactIQ MCP server bundled in
.mcp.json over one OAuth connection.

┌─────────────────────────────┐
│  Claude / ChatGPT /         │
│  Claude Code / Codex        │
│  + factiq skill (SKILL.md)  │      the agent orchestrates everything
└──────────────┬──────────────┘
               │  MCP over HTTP (one OAuth connection)
┌──────────────▼──────────────┐
│  FactIQ MCP server          │
│                             │
│  discover   search_datasets, describe_dataset, search_series,
│             get_data_catalog
│  fetch      run_sql (read-only), get_series, get_market_data,
│             search_company_filings, search_earnings_transcripts,
│             search_media_appearances, search_news
└──────────────┬──────────────┘
               │
┌──────────────▼──────────────┐
│  FactIQ data warehouse      │      official and derived data sources
└─────────────────────────────┘

The reason a single skill can query BLS unemployment, Chinese customs flows,
RBI monetary data, and World Bank indicators with the same SQL idioms: every
data source in the backend is normalized into the same three core tables,
identical in every schema:

Table	What it holds
series	The catalog — one row per series: id, title, description, dataset, frequency, units, seasonality, geography, time coverage
data_points	The values — (series_id, time, value), indexed for fast retrieval
dimensions	Faceted metadata — (series_id, dimension_type, dimension_code, dimension_name), e.g. partner, flow, commodity, hs_level for trade data

Our ingestion pipelines do the hard work of flattening each source's bespoke
format — BLS flat files, BEA APIs, customs records, RBI releases — into this
shape, so the agent learns the model once and it works everywhere. Discovery,
pivoting, and filtering follow the same patterns across all ~20 schemas; the
recipes live in references/data/sql-guide.md.

What's in the warehouse

Region	Schemas
United States	SEC filings data, BLS (employment, CPI, JOLTS, OEWS), Census (trade incl. HS-level, retail, housing), BEA (GDP, income), EIA (energy), USDA ERS, BTS (transportation), earnings-call transcripts, executive media appearances, Federal Reserve speeches, testimony, statements, minutes, and press-conference transcripts
China	NBS macro indicators, GACC customs (HS-level trade)
India	MOSPI (CPI, WPI, IIP, GDP), RBI (banking, rates, forex), DGCI&S trade (HS-level), Bengaluru road traffic (2026 onward, that one city only), RBI speeches and press releases
South Korea	KCS customs (HS-level trade)
European Union	Eurostat Comext monthly trade for all 27 member-state reporters, by CN8 product and partner country; European Central Bank and national central-bank speeches, interviews, statements, and minutes
Global	IMF (including the recent earlier releases of its forecasts, so a revision can be traced), World Bank, Singapore SingStat, live market data (quotes, fundamentals, FX, commodities), central-bank documents from the UK, Japan, China, Korea, Hong Kong, and Taiwan

references/data/schemas.md has the static overview; the get_data_catalog tool
returns the live, authoritative version.

Repo map

Where the behavior lives — the files contributors will touch:

• skills/factiq/SKILL.md — the skill definition and single source of truth
  for the workflow. Auto-discovered by supported plugin clients from the
  skills/ directory
• references/data/ — the data layer: SQL idioms (sql-guide.md) and the
  dataset schema overview (schemas.md)
• references/output/ — local output formats: ChartSpec (chart-spec.md) and
  report JSON (report-spec.md)
• references/report-patterns/ — domain playbooks (monetary policy,
  bilateral trade, bilateral economic policy, fiscal-policy revenue, business
  formation, earnings intelligence, media-appearance intelligence).
  report-patterns/README.md is the single entry point SKILL.md
  references: it teaches the dialectical method (thesis → antithesis →
  synthesis) all reports follow and routes each domain to its playbook, so
  adding a playbook doesn't touch SKILL.md

Plugin plumbing — you shouldn't need to touch these:

• .mcp.json — declares the bundled FactIQ MCP server (Streamable HTTP,
  OAuth). Read by both Claude Code and Codex plugin loaders
• .claude-plugin/ — Claude and Claude Code plugin + marketplace manifests
• .codex-plugin/ — ChatGPT and Codex plugin manifest
• .codex-plugin/plugin.json uses the registered FactIQ app ID as its plugin
  name for ChatGPT app association
• .agents/plugins/marketplace.json — Codex marketplace entry for
  codex plugin marketplace add defog-ai/factiq-plugin

Contributing

Contributions are welcome — this plugin is meant to grow with its community.
Open an issue or a pull request.

Bespoke skills (domain playbooks) — the highest-leverage contribution

The most valuable thing you can add is a domain playbook: a reference file
that teaches the agent how to answer a whole class of questions well. A
playbook is a domain's dialectic written down in advance — the headline
reading a question invites, the contradictions a competent skeptic would
raise against it, and the SQL to fetch both (see the method in
references/report-patterns/README.md).
The existing ones live in
references/report-patterns/ and are the
pattern to follow:

• monetary-policy.md —
  central bank policy stance, administered rates, OMO, balance-sheet context
• bilateral-trade.md —
  country-pair trade trends, product drivers, mirror-statistics caveats
• fiscal-policy-revenue.md
  — government receipts, tax composition, distributional detail

A good playbook contains:

1. A trigger — which question shapes it covers ("latest trend in trade
   between A and B", "explain the Fed's stance"), added as a row to the
   routing table in
   references/report-patterns/README.md
   so the agent reads the playbook before fetching. SKILL.md points at
   that router, so it doesn't need to change.
2. Required coverage — the domain's canonical antitheses: the
   counter-checks a complete answer must fetch (mirror statistics, real vs
   nominal, composition, the counterparty's ledger), so the agent doesn't
   stop at the first obvious chart.
3. Ready SQL templates — tested queries against the three-table schema for
   the key computations (latest-month YoY, YTD comparisons, top-N drivers).
4. Caveats and guardrails — unit normalization, base-year changes,
   national-vs-subnational traps, data gaps to disclose explicitly.

Ideas we'd love to see: labor-market health, inflation decomposition, energy
markets, housing, sovereign debt, sector earnings analysis, country
macro-risk snapshots.

Other welcome contributions

• SQL idioms and pitfalls — additions to references/data/sql-guide.md
  from real usage.
• Docs and fixes — anything that makes the agent's first attempt land.

Test a playbook by running its questions end to end and checking the saved
chart or report output. Include exact before-and-after examples in the PR.

Security

No secrets belong in this repo, and the plugin holds none — interactive
access goes through the MCP server's OAuth flow, so the coding agent holds the
token and nothing is written here. Headless use relies on a personal API key
that you create on the FactIQ settings page and keep in your own environment;
it is never stored in this repo. All SQL runs read-only against FactIQ's data
warehouse.

License

MIT