Brighter
Server Details
Browse, backtest and write rule-based portfolios of tokenized US stocks.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 11 tools
Most tools target distinct resources: list/get/allocation for published strategies, find/asset_history for assets, and validation/formatting for custom rules. The main friction is backtest_code vs backtest_strategy (self-written vs published) and check_strategy vs format_strategy (both operate on strategy text), though descriptions do clarify each.
Consistent snake_case throughout, with verb_noun dominating (get_strategy, list_strategies, find_assets, check_strategy, format_strategy, backtest_code). A few noun-noun reference tools (asset_history, dsl_reference, strategy_schema) deviate but remain predictable and readable.
11 tools is well-scoped for a strategy backtesting and discovery platform; each tool earns its place across discovery, validation, reference, and execution. No redundant or filler tools inflate the set.
Strong coverage of the consume-and-backtest lifecycle: discover/read strategies, inspect assets, validate/format rules, and run backtests with references for authoring. The one notable gap is no way to save or publish a custom strategy, but core agent workflows are otherwise complete.
Available Tools
11 toolsasset_historyAInspect
Daily closing prices for one asset over a calendar year, for checking a rule's premise against what actually happened.
Inputs: year (required), ticker (required).
backtest_codeAInspect
Run a strategy you have written against real market history and return its figures. This is a real backtest against real prices — not a simulation and not cached per call — so run it deliberately, after check_strategy passes. Returns metrics only, never the curve.
Inputs: code (required), range.
backtest_strategyAInspect
Run a published strategy over real market history with parameters of your choosing. Returns its figures against its benchmark. Values outside a parameter's range are snapped into it. This is a real backtest, so make each one count.
Inputs: id (required), range, params.
check_strategyAInspect
Check a strategy written in Brighter's language: syntax, semantics, and whether every ticker it names is one Brighter can actually trade. Returns the faults with their line and column. Costs nothing and calls nothing upstream — check before you backtest.
Inputs: code (required).
dsl_referenceAInspect
How to write a Brighter strategy: the language's blocks, indentation rules, indicators and limits. Read this before writing any rule — the language is small and specific, and guessing its syntax wastes a turn.
Inputs: limits, indicators.
find_assetsAInspect
Search the assets a Brighter strategy can hold — tokenized US stocks, ETFs and T-bills. A rule may only name a ticker that appears here.
Inputs: limit, query, offset, tickers.
format_strategyBInspect
Rewrite a strategy in the language's canonical form — the spelling Studio's editor shows. Useful for checking that what you wrote means what you think it means.
Inputs: code (required).
get_allocationBInspect
What a published strategy's rule holds right now, in basis points of the portfolio. This is the live target, computed from the latest close.
Inputs: id (required), params.
get_strategyAInspect
One strategy in full: what its rule does, the parameters you can tune with their ranges and defaults, every asset it can hold, and its benchmark. Use the parameter keys with backtest_strategy.
Inputs: id (required).
list_strategiesAInspect
List the strategies published on brighter.fi, newest or best-performing first. Each carries its rebalance cadence, the assets it can hold, and its return over the chosen period against its benchmark. Strategies that can hold leveraged or inverse funds are excluded unless asked for.
Inputs: sort, limit, assets, offset, +4 more.
strategy_schemaAInspect
The JSON schema for a strategy as an object, for when you would rather build the rule tree than write the text. check_strategy and backtest_code both accept text, which is usually easier.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Trade and invest in tokenized stocks: prices, holdings, P&L, unsigned market/limit/recurring trades.
Research, build, simulate and run trading strategies on Hyperliquid, Base stocks and Polymarket.
AI-driven US equity strategies: catalog, returns, drawdowns, pricing and blog. Read-only.
Self-hostable index of AI financial agents — tokenized stocks + crypto, memory, LLM gateway.
Related MCP Servers
AlicenseAqualityBmaintenanceExposes tokenized-stock market data, screeners, backtests and AI-generated strategy plans on Robinhood Chain. Free tools need no setup, while paid tools settle per call in USDG via x402 from a caller-supplied wallet with built-in spend caps.11MIT
Tickerbot MCP Serverofficial
AlicenseAqualityBmaintenanceEnables scanning and querying stock market data across thousands of US tickers and top cryptos, with tools for signal analysis, historical replay, and webhook subscriptions.35316 npmMIT- AlicenseNot gradedqualityBmaintenanceConnects Claude, ChatGPT, Gemini, and IDE clients to institutional-grade quantitative portfolio data — target allocations, holdings history, sector and concentration breakdowns, published research, and BUY/SELL rebalancing calculations against a user's own holdings. A token-forwarding proxy enforces subscription entitlements, serving live books to subscribers and ~45-day-delayed public books to everyone else.MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to create and manage self-custodial ERC-4626 vaults holding a rebalanced basket of tokenized US stocks (NVDA, META, AAPL, GOOGL) on Base, with tools to quote, buy, sell, rebalance, redeem in USDC or in-kind, and transfer shares. Also provides USDC bridging between Base and Arc, gas sponsorship payable in USDC, and x402 payment utilities, with every write returned as unsigned calldata the agent signs itself.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.