Click on "Deploy 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., "@Tally Run my morning checkup and show me active 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.
Every trading connector makes your AI more capable. Tally makes it accountable.
Tally (tally.markets) is a trading-discipline layer that mounts inside Claude, ChatGPT, Claude Code, and any MCP-capable agent. Your AI is the analyst — it researches, monitors, and gathers evidence. Tally holds the record neither you nor the model can rewrite: pre-registered theses, exit rules that freeze before capital moves, a 24-hour cooling-off, an override ledger for rule-breaking exits, and a public receipt for every closed trade.
Tally never executes trades. Every broker and venue connection is read-only at the API level — no order placement, no custody, by architecture and by policy.
Server URL (Streamable HTTP · OAuth 2.0 with dynamic client registration):
https://tally.markets/api/mcpClient | How |
Claude | Settings → Connectors → Add custom connector → name it |
ChatGPT | Listed app — one click from the directory, no developer mode. (Manual fallback: developer mode → Plugins → New plugin, the URL as Server URL, OAuth.) |
Claude Code |
|
Any MCP agent | Point it at the URL above; OAuth discovery does the rest. |
Then say: "Get started with Tally, then run my checkup." The server teaches your AI the whole protocol on first contact.
Full walkthrough (skill, scheduled morning checkup, broker linking): tally.markets/connect
Related MCP server: TradingWizard No-Chase MCP
Tool | What it does |
| Returns the discipline protocol — the AI teaches itself |
| Morning briefing: active theses, deadlines, evidence, closed history and lifetime R |
| Read the journal |
| Pre-register a trade: statement, mechanism, risk budget, exit criteria (starts the 24h cooling-off) |
| Freeze the criteria after cooling-off — from here they fire, never edit |
| Log evidence against a criterion (the generic sensor primitive) |
| Mark a rule objectively triggered, with cited evidence — one-way |
| Close a trade; discretionary closes require a written justification, logged forever |
| The public receipt for a closed thesis |
Reads are safe to always-allow; writes are guarded by the protocol itself (cooling-off, criteria minimums, override justifications).
Clients with a prompt picker get the three jobs Tally exists for, ready to run:
Prompt | What it does |
| The daily run — what needs action, fresh readings against every active thesis's criteria, anything that fired. This is the one to put on a schedule. |
| Turns an idea into a pre-registered thesis, interviewing you until it is falsifiable |
| Walks a thesis to its exit — what the written rules demand, and the justification the override ledger requires if you are closing early |
A real receipt — pre-registered thesis, venue-verified entry and exit, −0.22R, graded Process B / Outcome D, closing note verbatim: "Wrong on thesis, right on process."
Market-data connectors inform your AI. Execution connectors let it trade. Journal connectors show it your past. Tally is the one built to constrain — it runs alongside all of them: tally.markets/compare
OAuth per user; your AI sees your journal only, under a grant you can revoke any time.
Brokerage data (via SnapTrade) is read-only; broker credentials never touch Tally.
Details: privacy · terms · support@tally.markets
Tally is a hosted service. This repository is its documentation and public manifest, not its source — there is nothing here to install or run. Point your AI at the connector URL above; OAuth does the rest.
This server cannot be deployed
Deterministic pre-trade risk checks for autonomous AI trading agents.
Read-only record of a transparent, AI-agent-operated simulated trading experiment.
Unified financial infrastructure connecting AI agents directly to trade live/demo brokerage accounts, Web3 non-custodial wallets, real-time market data across equities, ETFs, crypto, forex, options, DeFi swaps, and prediction markets, institutional research feeds, and algorithmic strategy backtesters.
Live trading-pipeline intelligence for AI agents: signal scoring, calibration, recorded outcomes.
