Gogi

Unified financial infrastructure connecting AI agents to live/demo brokers (Alpaca, Charles Schwab, TradeLocker, Kraken, Coinbase), Web3 non-custodial…

От сообществаРаботаетБез входаГлобальныйБесплатноТолько чтение

Что умеет

Get Platform Disclosure: Return Gogi's mandatory trading / MCP risk disclosure. Call this when connecting or before trading. User controls permissions; Gogi is not responsible for external agent actio
Get Market Data: FMP market snapshot for stocks, crypto, FX, commodities, indices, and futures. Returns last price plus day OHLC, 52-week range, market cap/PE when present, profile, headlines, and com
Analyze Chart Structure: Detect chart patterns and support/resistance for stocks, crypto, FX, commodities, indices, and futures. Returns technical indicators, S/R pivots, Fibonacci levels, geometric p

Какие данные видит

Нужен ли аккаунт

Не нужен: сервер работает без входа

Unified financial infrastructure connecting AI agents to live/demo brokers (Alpaca, Charles Schwab, TradeLocker, Kraken, Coinbase), Web3 non-custodial wallets, real-time market data across equities, ETFs, crypto, forex, options, DeFi swaps, institutional research feeds, and algorithmic strategy backtesters.

Список инструментов сервера (37)

Технические названия из tools/list. Нужны только разработчикам.

get_platform_disclosure	Return Gogi's mandatory trading / MCP risk disclosure. Call this when connecting or before trading. User controls permissions; Gogi is not responsible for external agent actions; no investment advice; losses are the user's.
get_market_data	FMP market snapshot for stocks, crypto, FX, commodities, indices, and futures. Returns last price plus day OHLC, 52-week range, market cap/PE when present, profile, headlines, and compact technicals (RSI, SMA, EMA, MACD, ADX, Stoch). No broker account required. Tickers: AAPL, BTC-USD, EURUSD, GC, CL, XAUUSD, ^GSPC (slash forms like BTC/USD are accepted). Optional timeframe for technicals (default 1day). Not Marketplace SKUs — use get_data_feed for insider/congress/financials-pro. For chart patterns / S/R geometry use analyze_chart_structure.
analyze_chart_structure	Detect chart patterns and support/resistance for stocks, crypto, FX, commodities, indices, and futures. Returns technical indicators, S/R pivots, Fibonacci levels, geometric patterns, and an analysis_steps breakdown. When presenting analysis to the user, always state the key steps performed (e.g. timeframe analyzed, indicators computed, key levels identified) so the user knows what analysis was executed. Default overlay is patterns. Use get_market_data for quote + indicators.
execute_trade	Propose or execute a potentially money-moving trade on a connected broker. If instance_id is provided, executes on a LIVE trading instance (algo-tracked) under an agent LinkedAlgo. If instance_id is omitted, executes direct on-demand trade on the selected/default broker account. If mcp_require_confirm is true, returns pending_confirmation — user must Confirm in Gogi Activity; poll get_pending_trade_status. If false, executes immediately under policy and may place a real order. Call get_policy, get_portfolio, and get_platform_disclosure first; prefer paper accounts. Use close_positions for flattening an existing position rather than inventing a sell quantity.
close_positions	Close open broker positions on an enabled Connections account (no trading instance required). Supports all asset classes: Equities, US Options, Crypto, Forex/CFDs, and Prediction Markets. Omit symbol to flatten the account (requires confirm_close_all=true when multiple opens). Prefer this over inventing sell quantities. Broker flatten closes broker exposure; algo-tracked Gogi trade engine positions for the same symbol may still need execute_trade with instance_id or delete_instance with confirm_close_positions. When mcp_require_confirm is true, returns pending_confirmation for Activity Confirm.
get_pending_trade_status	Check status of a pending MCP trade awaiting in-app Confirm (pending, executed, cancelled, expired, failed).
cancel_pending_trade	Cancel a pending trade before in-app confirmation. This cannot cancel an already executed, expired, or previously resolved trade.
list_pending_trades	List pending trades for this agent awaiting in-app Confirm.
execute_prediction	Place a potentially money-moving prediction-market order on Kalshi or Polymarket. Call search_predictions first to identify the current contract, then verify the connected account, side, contracts, and price. This action may be irreversible; policy and in-app confirmation still apply when enabled.
search_predictions	Search public prediction markets (Kalshi and Polymarket). No connected Kalshi/Polymarket broker account required. To place a bet, use execute_prediction with a connected account.
get_portfolio	Get account-level balances, equity, buying power, positions, and Web3 wallet holdings across connected brokers and wallets. Use get_positions when you only need normalized open exposure.
get_positions	Get normalized current open positions and exposure across connected brokers. This is narrower than get_portfolio and does not replace account balances or wallet holdings.
list_my_algos	List saved algorithms owned by the user. Returns stable algo_id values, strategy summaries, symbols, timeframe, and whether each algorithm is archived. Call this before update_algo, delete_algo, or activate_algo when the user names an algorithm rather than supplying its ID.
get_algo	Retrieve one saved algorithm owned by the user by ID. Use list_my_algos first when the ID is unknown; use get_linked_algo for an instance-specific runtime copy.
list_brokers	List ALL connected broker accounts and wallets for this user (Alpaca, TradeLocker, Kalshi, Coinbase, etc. — never Alpaca-only). Call BEFORE create_instance / create_and_start_algo / execute_trade / close_positions. Show each display_label: broker name, paper OR live (each account is one environment, never both), and account_number_last5 (•••••93461). Ask the user which account to use by that label; then pass that account's integer `id` as broker_account_id (machine field only — do not call it a Gogi ID when speaking to the user). Prefer paper/demo. If none connected, send them to https://gogi.ai/voice-agent. Do not invent account IDs.
get_data_feed	Query a subscribed marketplace data feed by feed_id. Pass a ticker in query (e.g. AAPL). Returns FMP-backed data for financials/insider/congress feeds, or a text preview for uploaded file feed ids.
list_data_feeds	List all available data feeds (plan, marketplace subs, user uploads).
read_file	Read a user-uploaded file owned by this agent. Returns metadata plus a UTF-8 text preview (capped); binary files return metadata only.
get_policy	Fetch this agent's global policy constraints plus per-live-instance HITL/AITL overrides (instance_overrides). mcp_require_confirm on policy is the default; LinkedAlgo overrides apply only to that live binding.
get_linked_algo	Read a LinkedAlgo on a live instance owned by this agent: parameters, capital, symbols, mcp_require_confirm (null=inherit), and effective_confirm.
update_linked_algo	Update this agent's LinkedAlgo on an instance (parameters and/or mcp_require_confirm). Changing mcp_require_confirm overrides global Agent Policy for THAT live instance only — first call returns loop_mode_requires_confirm with disclosure; after user Continue, retry with confirm_loop_mode=true. New instances inherit policy until changed.
log_event	Log and persist a custom activity event. Writes a permanent, non-idempotent event record to Gogi's backend database (retained indefinitely) which is displayed to the user in the UI Activity Feed / agent timeline. Repeated calls with the same details will create duplicate timeline records. WHEN TO USE: Streaming inner thoughts, reasoning steps, heartbeat signals, current status, or execution milestones to provide an audit trail of the agent's thinking process. WHEN NOT TO USE: Do NOT use this tool for reporting trades, orders, or portfolio/position queries. Standard action tools (e.g., execute_trade, close_positions, execute_prediction) automatically emit their own rich timeline events; logging them again is redundant and creates database spam.
create_algo	Create a trading algorithm strategy with technical parameters. Use the strategy the user (or this conversation) specified. If indicators/entry conditions were not specified, ASK — do NOT invent EMA 9/21 or any favorite indicator pair. Only pick a concrete template when the user explicitly invites you (e.g. 'you pick', 'surprise me'); then prefer diverse types such as RSI(14), MACD, SMA 50/200, or EMA 12/26 — never always the same MA pair.
update_algo	Update a saved algorithm owned by the user. Only supplied fields change. This edits the saved definition and does not change any already-linked live instance; use update_linked_algo for an instance-specific runtime change.
delete_algo	Archive a saved algorithm owned by the user. Requires confirm=true. An algorithm linked to a trading instance cannot be archived until it is deactivated, preventing accidental disruption or loss of execution history.
list_instances	List the user's trading instances with id, name, status, is_live, and broker. Call this before start_instance / stop_instance / activate_algo / delete_instance to confirm instance_id (not algo_id). status pending/stopped means not live yet. Stopped/pending still count toward the max-10 limit until delete_instance.
create_instance	Create a trading instance bound to a broker account the user selected. ALWAYS call list_brokers first, show each display_label (broker · paper\|live · •••••last5 — each account is paper OR live, never both), wait for the user to pick an account by that label, then pass that row's integer `id` as broker_account_id. Prefer paper/demo unless the user explicitly chooses live. Default status is pending (not live). Use start_immediately=true only when the user wants live trading started now; otherwise call start_instance after activate_algo.
update_instance	Update an owned trading instance's name or runtime settings. This does not replace activate_algo or update_linked_algo; setting is_live=true can start live execution and requires explicit user intent.
activate_algo	Link an algorithm to a trading instance with capital allocation and start live trading. algo_id is the saved algo id (from create_algo / list_my_algos), not LinkedAlgo id. instance_id is from create_instance / list_instances. ALWAYS ask the user for capital_allocation — never invent a dollar amount. Capital is from broker buying power; the cumulative sum across this agent's live algos (allocated AI Trading Power) must stay ≤ policy max_total_capital. First call with confirm_allocation=false; server returns allocation_requires_confirm with broker_equity, allocation_pct_of_equity, and warning_level (high≥50%, critical≥90%). Show those to the user with risk settings; after explicit OK retry with confirm_allocation=true (acknowledge_capital_risk still accepted as alias). capital > equity is hard-blocked. Optional risk_preset override: conservative\|moderate\|aggressive\|custom. On success check engine_started (or utml_started), is_live, symbols, timeframe, and capital vs equity.
deactivate_algo	Deactivate and unlink an algorithm from a trading instance, stopping that linked strategy without deleting the saved algorithm. Use this before delete_algo; it is reversible with activate_algo, but inspect open positions first because deactivation does not automatically flatten broker exposure.
start_instance	Start automated execution for an existing stopped or pending trading instance. Call list_instances first to verify instance_id, linked algorithm, broker environment, and status. This can enable live trading; it does not replace activate_algo or create_instance.
stop_instance	Stop automated execution for a running trading instance. Call list_instances first and confirm the target; stopping is reversible with start_instance and does not necessarily close existing broker positions. Use close_positions when the user explicitly wants exposure flattened.
delete_instance	Permanently delete a trading instance and free a slot (max 10 per user). Stop ≠ delete. For live instances pass force=true. If open positions exist, the tool returns error_type=open_positions_require_confirm with open_positions — show them to the user, warn that delete will close all open positions, then retry with confirm_close_positions=true after explicit user OK.
create_and_start_algo	Create algo + instance + start trading. REQUIRED: call list_brokers first, show display_label (broker · paper/demo\|live · •••••last5), get the user's explicit choice, then pass that row's integer `id` as broker_account_id. Prefer paper/demo unless the user confirms live. Use the strategy the user (or this conversation) specified. If indicators/entry conditions were not specified, ASK — do NOT invent EMA 9/21 or any favorite indicator pair. Only pick a concrete template when the user explicitly invites you (e.g. 'you pick', 'surprise me'); then prefer diverse types such as RSI(14), MACD, SMA 50/200, or EMA 12/26 — never always the same MA pair. ALWAYS ask for capital_allocation (dollar amount from broker buying power). Cumulative allocated capital across this agent's live algos must stay ≤ policy max_total_capital. For risk, prefer the user's own numbers in strategy_params.risk (stopLossPercentage, takeProfitPercentage, riskPercentage, maxDrawdown) — those override presets. Optional risk_preset conservative\|moderate\|aggressive is only a shortcut when the user does not give custom numbers. Optionally risk_advanced for trailing stop / pyramiding. First call with confirm_allocation=false; on allocation_requires_confirm show broker_equity, allocation_pct_of_equity, warning_level, and risk summary; after explicit user OK retry with confirm_allocation=true (acknowledge_capital_risk still accepted as alias). On success present Instance Setup Details: instance, strategy, symbols, timeframe, broker, capital vs equity %, risk numbers, live status.
run_backtest	Run a policy-aware historical backtest for this agent. Results appear in the agent's Backtesting tab and Activity feed. Requires Backtesting Pro.
list_backtest_runs	List recent completed or running backtest runs for this agent across MCP, chat, voice, and API. Use get_backtest_run for one run's details; use run_backtest to start a new run.
get_backtest_run	Get details for a backtest run by run_id (must belong to this user's agent).