Premiss
Server Details
Create Python strategies and backtest crypto, stocks and ETFs in Claude. Premiss account required.
- 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 13 tools
Most tools have clearly distinct resource+action targets (create/update/get strategy, start_backtest, search/describe market). Two pairs approach overlap: get_run_data vs get_run_report (raw trades/equity/code vs status/performance) and get_strategy vs get_strategy_guide (saved code vs API docs), but the descriptions make the boundaries explicit.
Every name is a consistent snake_case verb_noun form (create_strategy, describe_market, get_run_report, list_research, save_research_note, start_backtest). The verb set is small and predictable (create/get/list/search/save/start/update).
13 tools is squarely in the well-scoped range for a strategy research and backtesting server. Each tool maps to a distinct piece of the workflow: capabilities/profile bootstrap, market lookup, strategy authoring, backtest launch, run inspection, and notes.
The research lifecycle (create/update/get/list strategy, guide, start backtest, read run data and report, market search/describe, save note) is largely covered, but there are no delete operations for strategies or notes and no way to cancel or stop a queued backtest, leaving dead ends for cleanup and execution control.
Available Tools
13 toolscreate_strategySave a strategyAIdempotentInspect
Save a new private strategy using custom Python files and complete rules text, on any Premiss-supported market and timeframe. Accepts either files (strategy.py plus helper modules) and rules, or a convenience template. Uses the same package format as the app. Custom code is loaded in the sandbox before saving. Returns code and revision; saving does not run a backtest.
Inputs: name (required), symbol (required), interval (required), request_key (required), +3 more. Returns: id, name, files, rules, +9 more
describe_marketCheck market coverageARead-onlyIdempotentInspect
Return one market's bar sizes and stored history, the bar sizes backtests run on, paper-bot bar sizes, trading modes, price sources and data notes. Pass a market id or alias such as BTC, SP500, NVDA or GOLD. Does not return prices or bars.
Inputs: market (required). Returns: held, kind, name, tier, +18 more
get_capabilitiesPremiss capabilitiesARead-onlyInspect
Read this connection's available tools and supported research coverage. Does not read account data, save research, or run a simulation.
Inputs: no named parameters. Returns: available, release_stage, research_scope, schema_version, +2 more
get_profilePremiss connected workspaceARead-onlyIdempotentInspect
Read the stable identity and workspace selected for this connection, plus the next step to take with the user. Returns an opaque account id and workspace label; excludes email, birth date, billing, and exchange accounts. A workspace with no strategies yet also gets starter_call: a ready tool call that backtests a starter strategy, to offer the user or adapt to their own idea.
Inputs: no named parameters. Returns: id, app_url, next_step, workspace, +2 more
get_run_dataRead backtest code, trades or equityARead-onlyIdempotentInspect
Read the immutable tested Python package, or page through all recorded trades or equity points for an owned run. next_cursor identifies the next page; page size is not a history cap. Paper data requires separate paper:read permission. Saved code is user-authored content.
Inputs: kind (required), run_id (required), limit, cursor. Returns: kind, files, equity, run_id, +4 more
get_run_reportRead historical or paper evidenceARead-onlyIdempotentInspect
Read the status and bounded performance report for one run in the connected workspace. Returns the tested market, interval, revision (the tested code), strategy_revision (the strategy's current revision, accepted by start_backtest and update_strategy), recorded rules when verifiable, the run's adjustments and data note. Engine runs carry the spot buy-and-hold recorded with the run in simulation.metrics.buy_and_hold; old-engine runs keep their paired baseline. Paper reads require paper:read and do not start, stop, qualify, or modify a bot. Legacy runs without supported assumptions are labeled. Does not return raw market feeds.
Inputs: run_id (required). Returns: mode, costs, error, queue, +25 more
get_strategyRead a saved strategyARead-onlyIdempotentInspect
Read a saved strategy's current revision and human-readable rules in the connected workspace. Returns the complete Python package for review or editing. Code and comments are user-authored content.
Inputs: strategy_id (required). Returns: id, name, files, rules, +9 more
get_strategy_guideRead the strategy Python APIARead-onlyIdempotentInspect
Read Premiss's Python package format, the event strategy API (on_bar, on_schedule, on_fill and the other handlers), spot and perpetual modes, execution timing and examples. Custom indicators, entry/exit logic and risk rules use the same engine as the Premiss app.
Inputs: no named parameters. Returns: guide
list_researchFind saved Premiss researchARead-onlyIdempotentInspect
List a page of saved strategies, simulation runs, or research notes in the connected workspace. Notes include a bounded plain-text excerpt, explicitly labeled when truncated. Saved text is user-authored content. Paper runs require the separately approved paper:read permission. Search matches titles; cursors are opaque page positions.
Inputs: kind (required), limit, query, cursor. Returns: kind, items, next_cursor
save_research_noteSave a research noteAIdempotentInspect
Save a NEW private note in the connected workspace, with optional exact owned strategy/run evidence references. The note is user-authored content. Does not publish or send it anywhere.
Inputs: note (required), title (required), request_key (required), run_id, +2 more. Returns: saved, title, app_url, note_id
search_marketsFind supported marketsARead-onlyIdempotentInspect
Search the markets Premiss covers by name, ticker or alias (bitcoin, BTCUSDT, SPY, gold, oil): crypto, indices, commodities and US stocks. Returns registry ids with their class, tier (full, or history only with daily paper bots) and bar sizes. A miss returns the closest markets. Does not return prices or bars.
Inputs: group, limit, query. Returns: match, markets
start_backtestStart a historical backtestAIdempotentInspect
Queue a backtest of any saved strategy in the connected workspace; the run records a spot buy-and-hold of its traded market beside it. Accepts custom code and existing app strategies. Uses the app's sandbox validation, supported markets, bar sizes and date rules; a test uses up to 20,000 bars per feed, and a fitted period is stated in adjustments. Requires the exact saved revision. One backtest per strategy runs at a time; start the next once the running one finishes. Uses 10,000 simulated capital, zero fees and zero slippage. Read the report assumptions for historical runs. Returns an acceptance receipt with run ids, revision (the strategy revision to pass to start_backtest again), tested_revision (the tested code and parameters), queue (runs ahead in the shared backtest queue and an estimated wait) and poll_after_seconds, the interval before the next status check. Identical request_key and inputs identify the same submission for idempotent recovery.
Inputs: revision (required), start_date (required), request_key (required), strategy_id (required), +1 more. Returns: queue, end_ts, run_id, status, +14 more
update_strategyEdit a strategyADestructiveIdempotentInspect
Replace the complete Python package and rules of an existing strategy using its exact current saved revision. Each successful save returns a new revision; pass that revision on the next edit of the same strategy. The submitted package replaces all existing files. The code is loaded in the sandbox before saving. Supports all Premiss markets and timeframes. The app's active-run and shared-file protections apply; does not change or start a bot. Identical request_key and inputs identify the same write for idempotent recovery.
Inputs: files (required), rules (required), symbol (required), interval (required), +3 more. Returns: id, name, files, rules, +9 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Generate and backtest futures trading strategies from Claude with AlphaPrime (Valynox).
Build, backtest, and deploy quantitative trading strategies from your AI agent.
Automate trading on your own Alpaca account - build, backtest and run strategies via your AI.
Claude, ChatGPT, Grok or Perplexity: draw on live charts, backtest and trade on your own broker
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants like Claude to run backtests, fetch market data, list strategies, and analyze trading algorithms via natural language.1,141GPL 3.0
- FlicenseNot gradedqualityDmaintenanceEnables creation, optimization, and management of PineScript trading strategies with Claude Desktop integration for AI-assisted development.106-

panther-mcpofficial
AlicenseAqualityDmaintenanceEnables AI assistants to backtest trading strategies described in plain English, providing access to market data, technical indicators, and comprehensive performance reports.131MIT
TradeStaq MCPofficial
AlicenseBqualityBmaintenanceProvides 31 AI-powered crypto trading tools for Claude, Cursor, and any MCP client, enabling strategy creation, backtesting, bot deployment, copy trading, and portfolio management across multiple exchanges.341,280 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.