Openbb Data Fetcher logo

Openbb Data Fetcher

Community
monarchjuno
openbb-data-fetcher

Fetch financial, market, economic, fundamental, news, options, crypto, ETF, index, and macro data through the OpenBB Python interface instead of the OpenBB MCP server. Use when an agent needs current or historical data from OpenBB-supported providers, needs to replace OpenBB MCP calls with direct Python/OpenBB usage, or must return source-tagged, reproducible datasets with clear query parameters, provider details, and data-quality notes.

Overview

Publishermonarchjuno
Repositoryvibe-investing
Skill nameopenbb-data-fetcher
Stars
301
Forks
59
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by monarchjuno on GitHub. Read the source before you install it.

Installation

Install the Openbb Data Fetcher AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/monarchjuno/vibe-investing/tree/main/skills/data-access/openbb-data-fetcher
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/monarchjuno/vibe-investing.git /tmp/vibe-investing
mkdir -p .claude/skills
cp -r /tmp/vibe-investing/skills/data-access/openbb-data-fetcher .claude/skills/openbb-data-fetcher
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Openbb Data Fetcher in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Openbb Data Fetcher on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Openbb Data Fetcher is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

OpenBB Data Fetcher

Role

Use OpenBB as a standalone data access layer. Retrieve requested data, preserve provenance, normalize it into a usable structure, and make uncertainty explicit in the returned dataset package.

Default Behavior

  • Use the OpenBB Python package directly with from openbb import obb.
  • Do not use the OpenBB MCP server unless the user explicitly asks for MCP.
  • Prefer the bundled scripts/fetch_openbb.py helper for simple endpoint calls instead of ad hoc shell heredocs.
  • Prefer official OpenBB endpoints and provider extensions over web scraping.
  • Do not substitute ordinary web search just because OpenBB is not installed; install OpenBB, retry the request, or report the installation blocker.
  • Use web search as a fallback only after OpenBB installation, import, endpoint, provider, or credential setup has failed and the requested task still needs an answer.
  • When using fallback web research, label it clearly as non-OpenBB fallback data and cite sources; do not imply it came from OpenBB.
  • Return structured data first: DataFrame, CSV, JSON, or a concise schema/sample when the dataset is large.
  • Keep raw provider fields unless the user asks for a transformed model-ready dataset.

Quick Start

  1. Identify the data domain: equity, ETF, index, crypto, fixed income, options, economics, fundamentals, news, analyst estimates, calendar events, or regulatory filings.
  2. Identify the instrument identifiers, date range, frequency, provider preference, and required fields.
  3. Check whether OpenBB is installed. If it is missing, install it into the active Python environment and retry the same request.
  4. Use the reusable helper when a simple endpoint call is enough. Do not force provider="yfinance" unless that endpoint supports it:
bash
python skills/data-access/openbb-data-fetcher/scripts/fetch_openbb.py \
  --install-if-missing \
  --endpoint equity.price.historical \
  --params '{"symbol":"AAPL","start_date":"2024-01-01","provider":"yfinance"}' \
  --output /tmp/aapl_prices.csv
  1. For exploratory work, use Python directly:
python
from openbb import obb

result = obb.equity.price.historical(
    symbol="AAPL",
    start_date="2024-01-01",
    provider="yfinance",
)
df = result.to_dataframe()

For provider-specific fundamentals such as segment or geography revenue, do not assume yfinance works:

bash
python skills/data-access/openbb-data-fetcher/scripts/fetch_openbb.py \
  --install-if-missing \
  --endpoint equity.fundamental.revenue_per_segment \
  --params '{"symbol":"NVDA","provider":"fmp"}' \
  --output /tmp/nvda_segment_revenue.csv

Installation Guidance

  • Official current baseline: pip install openbb.
  • When this skill is triggered, treat missing OpenBB as a setup step, not as permission to use generic web search.
  • Prefer python -m pip install openbb in the same interpreter that will run the data request.
  • Use pip install openbb[all] only when broad provider coverage is needed and installation size is acceptable.
  • For a narrow provider, prefer installing the relevant extension package instead of all extras.
  • OpenBB currently supports Python 3.10+; if installation fails, verify the active Python version and OpenBB docs before changing code.
  • Never commit API keys or credential files.
  • Web browsing is allowed to inspect official OpenBB documentation, provider setup requirements, or to provide fallback data after OpenBB has genuinely failed.

Minimal install-and-retry pattern:

bash
python -m pip install openbb
python skills/data-access/openbb-data-fetcher/scripts/fetch_openbb.py \
  --endpoint equity.price.historical \
  --params '{"symbol":"AAPL","start_date":"2024-01-01","provider":"yfinance"}' \
  --output /tmp/aapl_prices.csv

Credentials

  • Use provider credentials only from the user's existing environment, OpenBB .env, OpenBB user_settings.json, or explicit session-only Python assignment.
  • Prefer existing credentials in this order: active process environment, ~/.openbb_platform/.env, ~/.openbb_platform/user_settings.json, then session-only assignment.
  • If credentials are missing, try a no-key provider such as yfinance only when it can satisfy the request.
  • If a requested provider requires a key, stop and report the missing credential by provider and field name.
  • Keep ~/.openbb_platform/.env, ~/.openbb_platform/user_settings.json, and runtime credential values out of repo files.

Environment Variables

OpenBB can read environment variables from the active process and from ~/.openbb_platform/.env, located next to user_settings.json.

For provider API keys, use uppercase environment variable names ending in _API_KEY when the provider follows that pattern:

bash
mkdir -p ~/.openbb_platform
printf 'FMP_API_KEY="replace_with_key"\n' >> ~/.openbb_platform/.env
printf 'FRED_API_KEY="replace_with_key"\n' >> ~/.openbb_platform/.env

OpenBB exposes these as lowercase credential fields, for example FMP_API_KEY becomes obb.user.credentials.fmp_api_key.

For current-session-only use, set environment variables before importing OpenBB:

python
import os

os.environ["FMP_API_KEY"] = "replace_with_key"

from openbb import obb

Some credentials do not end in _API_KEY, such as tokens or account-type flags. For those, prefer user_settings.json or session-only assignment after inspecting the provider's required credential field.

If No Environment Variable Exists

Use one of these paths:

  1. Use a no-key provider if it covers the request:
python
from openbb import obb

prices = obb.equity.price.historical(
    symbol="AAPL",
    start_date="2024-01-01",
    provider="yfinance",
)
  1. Set the key for the current Python session only:
python
from openbb import obb

obb.user.credentials.fmp_api_key = "replace_with_key"
data = obb.equity.fundamental.metrics(symbol="AAPL", provider="fmp")
  1. Store the key locally in ~/.openbb_platform/user_settings.json:
json
{
  "credentials": {
    "fmp_api_key": "replace_with_key",
    "fred_api_key": "replace_with_key",
    "polygon_api_key": "replace_with_key"
  }
}

Restart the Python process after adding credentials to .env or user_settings.json.

Fallback Policy

OpenBB is the primary path. Before falling back, make a real attempt to:

  • Import OpenBB.
  • Install OpenBB into the active Python environment if it is missing.
  • Retry the same endpoint call.
  • If validation says the provider is invalid and names an allowed provider, retry with that provider.
  • Inspect the installed route tree if the endpoint is missing.
  • Try an available no-key provider when credentials are unavailable and it can satisfy the request.

Use web search only after those steps fail or are blocked by environment, package, provider, credential, or route limitations. In the final output, state:

  • That OpenBB failed or was unavailable.
  • The failure reason at a practical level.
  • That the returned data is non-OpenBB fallback data.
  • The sources, timestamps, and any comparability limits.

Endpoint Selection

Use OpenBB's route hierarchy directly:

  • Prices: obb.equity.price.historical, obb.crypto.price.historical, index or ETF price routes when available.
  • Fundamentals: obb.equity.fundamental.* routes for statements, ratios, metrics, profile, and related company data.
  • Economics and macro: FRED, IMF, OECD, ECB, BLS, Federal Reserve, or Trading Economics provider routes when available.
  • News and filings: news routes, SEC routes, or provider-specific routes when a verifiable source is needed.
  • Options and derivatives: options routes only after confirming symbol format, expiration, and provider support.

If the exact route is unclear, inspect the installed OpenBB interface:

python
from openbb import obb

dir(obb.equity)
dir(obb.equity.price)
help(obb.equity.price.historical)

Provider Selection

  • Treat provider compatibility as endpoint-specific. A provider that works for prices may not work for fundamentals, estimates, segments, filings, or macro data.
  • Do not use yfinance as a universal fallback. It is often useful for prices and some estimates, but many fundamental routes require providers such as fmp.
  • If OpenBB raises a validation error like provider -> input: yfinance -> Input should be 'fmp', retry the same endpoint with provider="fmp".
  • If the corrected provider requires credentials, check environment variables and user_settings.json before falling back.
  • For revenue_per_segment and revenue_per_geography, expect fmp unless the installed OpenBB route says otherwise.
  • Record provider changes in the output so the user can see that the request started with one provider and succeeded or failed with another.

Output Contract

For every returned dataset, include:

  • Query intent and endpoint used.
  • Provider and credential status when known.
  • Symbols or identifiers requested.
  • Date range, frequency, and timezone assumptions.
  • Row count, column list, and a small sample.
  • Any missing fields, provider limits, stale data warnings, or survivorship-bias concerns.

For returned values and derived fields, tag numbers as:

  • [actual] for data returned by a named provider or official filing/source.
  • [derived] for calculations made from fetched data.
  • [assumption] for user-provided or scenario inputs.
  • [unavailable] for fields the provider did not return.

Data Quality Rules

  • Validate symbols and date ranges before interpreting results.
  • Check for empty DataFrames, duplicated timestamps, missing close values, split-adjustment assumptions, and currency mismatches.
  • For multi-provider comparisons, do not merge series until calendar, timezone, currency, adjustment basis, and frequency are aligned.
  • For fundamentals, preserve fiscal period, filing date, currency, restatement status if available, and provider provenance.
  • For macro data, preserve release date, vintage, frequency, seasonal adjustment, and units when available.
  • Treat OpenBB output as provider data, not as guaranteed truth; mention source limitations.

Failure Handling

  • If OpenBB is not installed, install it and retry. If installation fails, report the exact install command, active Python version, and failure output.
  • If an endpoint is missing, inspect the installed route tree; OpenBB routes can differ by package version and installed extensions.
  • If a provider validation error names an allowed provider, retry once with that provider before giving up or falling back.
  • If the provider returns no data, retry only after checking ticker format, date range, and provider support.
  • If the user requested real-time data, state whether the provider appears delayed or end-of-day.
  • If provider terms, rate limits, or credentials block the request, explain the blocker without inventing substitute data.
  • If OpenBB cannot be installed or the route cannot return the requested dataset, use web fallback only when the task can still be answered responsibly from cited public sources.
  • If fallback data would be unreliable, unavailable, or not comparable to the requested OpenBB dataset, stop with a blocker instead of inventing or over-smoothing the result.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Openbb Data Fetcher AI skill do?

Fetch financial, market, economic, fundamental, news, options, crypto, ETF, index, and macro data through the OpenBB Python interface instead of the OpenBB MCP server. Use when an agent needs current or historical data from OpenBB-supported providers, needs to replace OpenBB MCP calls with direct Python/OpenBB usage, or must return source-tagged, reproducible datasets with clear query parameters, provider details, and data-quality notes.

Why use Openbb Data Fetcher on TypingMind?

Because you install it once and use it with any model. Openbb Data Fetcher is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Openbb Data Fetcher in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/monarchjuno/vibe-investing/tree/main/skills/data-access/openbb-data-fetcher. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Openbb Data Fetcher?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Openbb Data Fetcher?

As many as you like. As long as a model supports skills, you can use Openbb Data Fetcher with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Openbb Data Fetcher AI skill free?

Yes. It is published on GitHub by monarchjuno under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇