fomo-family-cli
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@fomo-family-cliRun my daily FOMO research and summarize the top coins and their theses."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
From a busy feed to a focused research brief
The interesting part of a coin is rarely just its price. It is the traders building positions, the thesis behind their conviction, and the change in attention around it. Following all of that means moving between lists, filters, profiles and charts.
FOMO.family CLI gives your AI a repeatable way to do that work. It operates FOMO.family through your own logged-in browser and brings back a focused set of observations. Your AI can turn those observations into a brief, explore a promising lead, or help maintain your watchlist.
You choose the model and the final format. The toolkit handles the browser steps.
Related MCP server: fidelity-mcp
What you can do
Your question | What the toolkit brings back |
Where is attention moving? | Watchlist, Trending and Most held discovery, plus Crypto, Graduated and Bonding views. |
Who is involved? | Holders, followed traders, displayed positions and leaderboard context. |
What is the story? | Theses filtered by Fomo's native minimum size, with position details for selected authors. |
What changed since my last read? | Newly observed thesis text, with previously seen content filtered out. |
What deserves a closer look? | Chart snapshots, timeframe controls and trader overlays for your AI or your own review. |
What do I want to keep following? | Explicit watchlist additions and removals, verified after reloading. |
One command. A repeatable starting point.
fomo daily --limit 3 --rows 5 --min-size-usd 10000This combines Watchlist, Trending and Most held, prioritizes overlap, and examines up to three candidates. For each, it collects an overview, Friends-only holders and a small sample of filtered theses. Your AI receives structured context with sources, timestamps and coverage limits.
Then ask your connected AI:
Run my FOMO.family research. Show me which coins deserve attention, which traders I follow are involved, and the thesis and counterargument for each. Keep it short and tell me what is still uncertain.
The command collects the evidence; your AI writes the brief. The workflow does not place trades or automatically edit your watchlist.
Read the relevant theses, not the entire history
A coin can have thousands of theses. Start with a native minimum-size filter, read a limited sample, and open the position details for the authors that merit attention. On the next run, --since-last avoids sending unchanged observed thesis text again.
This is selective research, not a complete historical archive. A displayed position value is also not proof of a fresh purchase for that amount. How filters and evidence work →
Quick start
You need Node.js 22+, Google Chrome, Git and a FOMO.family account. Windows and macOS are the intended browser environments. Use a terminal with access to this repository.
1. Install the toolkit
git clone https://github.com/Trilokx/fomo-family-cli.git
cd fomo-family-cli
npm ci
npm install --global .2. Connect your FOMO.family account
fomo loginSign in in the dedicated Chrome window, then close that window only. Your regular Chrome profile stays separate.
3. Run your first research pass
fomo start
fomo account
fomo daily --limit 3The browser session is reused between commands. No model API key is required by the collector. Installation and login help →
Connect your AI
Use the CLI with an agent that can run terminal commands, or connect the MCP server to a compatible AI client. Both use the same 17 tools and the same browser session.
fomo mcp-configCopy the generated configuration into your AI client's MCP settings. It contains the correct paths for your installation. Give the agent the included FOMO.family skill so it knows which tools to use, how to read selectively, and how to interpret the results.
An optional Codex plugin package is included. Connection details → · All commands →
Built to spend model work on interpretation
Navigation, clicking, filtering and extraction run as predefined code. The collector makes zero LLM calls. Your model reads the collected context instead of deciding every browser action from scratch.
Small result budgets and thesis deduplication keep routine reads focused. Your AI's prompts, tool results, reasoning and chart interpretation still use tokens; no comparative cost-saving percentage is claimed. Cost model and measured examples →
Your account. Your workflow.
Local session: sign in on your machine; browser state and evidence stay in the local runtime directory.
Flexible output: use your AI to produce a short brief, a research dossier or your own downstream format.
Schedule when ready: the daily workflow is available to your scheduler; the package creates no background schedule by itself.
Explicit actions: watchlist changes have their own commands. Orders, transfers, posts and follows are outside this toolkit.
Built, tested, and clear about its limits
The beta has live verification for discovery lists, thesis filters, holders, trader profiles, charts, layouts and watchlist changes. Automated checks cover installation, TypeScript, parsing, tool contracts and MCP transport across Windows, macOS and Linux.
Fomo UI changes and session expiry can require attention. Results describe the rows actually collected; full history and reliable unattended operation are not guaranteed. See the verification matrix and current limitations →
Explore further
Guide | Start here when you want to… |
Explore individual tools and filters. | |
Understand what the data does and does not establish. | |
Adapt the research prompt to your own routine. | |
Configure sessions, MCP and troubleshooting. | |
Report a problem or improve a workflow. |
Found a broken flow? Open an issue with the command and redacted error. Never include browser profiles, cookies or private account evidence.
Built by TRLX. Open-source beta under the MIT License. Independent tooling for FOMO.family, without affiliation or endorsement. The Fomo name and visual identity belong to their respective owners; the software license grants no rights to third-party trademarks or branding. Banner artwork illustrates the workflow.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Stealth web browser for agents: search, fetch, click, download and type in persistent MCP sessions.
Stealth web automation for AI agents. Login, signup, navigate, screenshot.
Stealth web automation for AI agents. Login, signup, navigate, screenshot.
AI-powered browser automation — navigate, click, fill forms, and extract data from any website.
Related MCP Servers
- AlicenseAqualityCmaintenanceProvides persistent browser tabs with tools to read, click, type, and interact with web pages, enabling local LLM agents to perform multi-step web tasks.151MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to read balances, positions, and transaction history, and place limit sell orders on Fidelity Investments accounts via Playwright browser automation.MIT
- AlicenseAqualityAmaintenanceEnables AI agents to control a real web browser (Firefox) via Selenium WebDriver, supporting page navigation, interaction, and inspection through natural language.434MIT
- AlicenseAqualityDmaintenanceEnables AI agents to interact with Robinhood brokerage accounts via browser automation, supporting portfolio viewing, quotes, trading, and account management.816MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Trilokx/fomo-family-cli'
If you have feedback or need assistance with the MCP directory API, please join our Discord server