How to Add Live Market Data to Your Grok Bot
Give your Grok Bot a live market data feed in about two minutes: one free API key, one install message, and your agent can screen stocks, read sentiment, and track insider and institutional activity on its own.
To add live market data to a Grok Bot, get a free SentiSense API key and send your agent one message telling it to install the SentiSense skills. From there it can screen stocks, check sentiment, and pull insider, institutional, options, and earnings data on its own, without you wiring anything up.
We verified this path ourselves while testing Grok Bot for our review: the agent installed the skills into its own sandbox, followed them correctly, and did real research unprompted. This post is the short version of how to set that up.
What is a Grok Bot?
Grok Bot is xAI's always-on agent product: you name an agent, and it arrives with its own cloud computer where it can browse, run commands, and keep files. Agents keep working while you are away and can message each other to hand off tasks, so xAI pitches them as coworkers rather than a chat window. It has been in beta since early August, and access is bundled with the premium tiers on either side of the product: Cursor Ultra, Pro+, and Teams Premium, or a linked SuperGrok Plus or Heavy subscription.
The part that matters for this guide: your agent can install tools for itself. You do not need to open a config file. You ask, it installs.
Why does your bot need a market data feed?
Out of the box, an agent asked about markets will guess from its training data or scrape whatever it can reach. Training data is months old, and scraped pages are unreliable in ways the agent cannot see. A bot that connects dots from stale or broken data is worse than one that admits it does not know. A data feed fixes both: the agent looks numbers up instead of remembering or improvising them.
How do you set it up?
Two minutes, three steps:
- Get a free API key. Create one at sentisense.ai/get-api-key. No sales call, and a free key is enough to try everything in this post.
- Tell your agent to install the skills. Send your Grok Bot a message like: "Install the SentiSense skills by running
npx skills add SentiSenseApp/skills, then use this API key for them: [your key]." The agent handles the rest inside its own computer. - Ask a market question. That is the whole setup.
What can it actually do?
Everything below is something a Grok Bot did on its own during our testing, given only a question:
- "Screen for large-cap stocks with a rising SentiSense Score."
- "Is the insider selling in [ticker] real conviction selling or routine tax withholding?"
- "How does [ticker]'s options positioning compare to its own history?"
- "Which members of Congress traded [ticker] recently?"
- "What is sentiment doing on [ticker], and what news is driving it?"
- "What is on the earnings calendar next week for the stocks I follow?"
The feed behind these covers live sentiment, insider, institutional, options, and earnings data for the roughly 960 most-watched US stocks. It is read-only by design: your agent can look things up, and nothing more.
The teammate pattern
Because Grok Bot agents message each other, the setup above composes: give one agent the data feed and make it the analyst. Your research bot screens the market and checks positioning, then hands its findings to a writer bot that drafts your notes, or to a planner bot that watches the earnings calendar. One key, one installed skill set, and every agent on the team can ask the analyst instead of guessing.
The same skills work in Claude, Claude Code, Codex, and Hermes, so the analyst moves with you if your runtime does. Data is provided for research and education, not investment advice.