panther-mcp
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PANTHER_API_KEY | Yes | Your Panther API key, obtained from https://panther.watch |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| tool_list_available_assetsA | List tradeable assets available for backtesting. Filter by asset type (crypto, forex, commodity) and/or search by symbol or name. |
| tool_get_price_dataA | Fetch historical OHLCV price data for an asset. Returns summary statistics and a preview of the data (not the full dataset). Use this to examine price history before defining a backtest strategy. Timeframes: 1m, 5m, 15m, 1h, 4h, 1d, 1w |
| tool_run_backtestA | Define and execute a trading strategy backtest. The strategy object must include:
Each rule has:
Returns a backtest_id. Use get_backtest_status to poll for completion, then get_backtest_results for the full results. |
| tool_get_backtest_statusA | Check the status of a running backtest. Returns status (queued, running, completed, failed) and progress percentage. |
| tool_optimize_strategyA | Run a strategy optimization / parameter sweep. Tests multiple parameter combinations and ranks results by a metric. param_ranges: List of parameter ranges to sweep. Each has:
constraints: Optional list of cross-parameter constraints, e.g. [{"left": "entry_rules[0].params.period", "op": "<", "right": "exit_rules[0].params.period"}] rank_by: Metric to rank results by (default "sharpe_ratio"). Options: total_return, sharpe_ratio, max_drawdown, win_rate, profit_factor, total_trades Returns an optimization_id. Use get_optimization_status to poll, then get_optimization_results for ranked results. |
| tool_get_optimization_statusB | Check the status of a running optimization. Returns status, progress percentage, total and completed combinations. |
| tool_get_optimization_resultsA | Get the results of a completed optimization. Returns:
|
| tool_get_backtest_resultsA | Get the results of a completed backtest. Returns:
IMPORTANT: Always share the results_url link with the user so they can view the full results with equity curve and trade details on panther.watch. |
| tool_list_backtestsA | List your previous backtests with summary info. Use this to review past experiments and compare strategies. |
| tool_list_optimizationsA | List your previous optimizations / parameter sweeps. Use this to review past optimization runs and their best parameters. |
| tool_run_portfolio_backtestA | Run a portfolio backtest across multiple assets with weighted allocation. Test how a strategy performs across a diversified portfolio. Each asset gets a weighted allocation of the total capital. assets: List of asset allocations. Each has:
Example: [{"symbol": "BTC/USDT", "weight": 0.6}, {"symbol": "ETH/USDT", "weight": 0.4}] The same strategy is applied to all assets. Returns a portfolio_backtest_id. Use get_portfolio_backtest_status to poll, then get_portfolio_backtest_results for results. |
| tool_get_portfolio_backtest_statusB | Check the status of a running portfolio backtest. Returns status (queued, running, completed, failed) and progress percentage. |
| tool_get_portfolio_backtest_resultsB | Get the results of a completed portfolio backtest. Returns:
IMPORTANT: Always share the results_url link with the user so they can view the full results with equity curve, per-asset breakdown, and trade details on panther.watch. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| strategies_doc | Documentation on supported indicators, conditions, and example strategies. |
| getting_started_doc | Quick start guide for backtesting with Panther. |
TDQS
Scored across 13 tools
Each tool targets a distinct resource or lifecycle stage: asset discovery, price data retrieval, backtest execution/status/results, optimization execution/status/results, and portfolio backtest execution/status/results. Run versus optimize versus list versus get operations are clearly separated, and the three status/result pairs are unambiguous.
All tools follow a consistent verb_prefix + resource pattern such as list_, get_, run_, and optimize_, with the shared tool_ prefix applied uniformly. Related workflows use parallel naming, e.g. get_backtest_status/get_backtest_results and get_optimization_status/get_optimization_results, making the API predictable.
13 tools is well-scoped for a backtesting platform, covering asset exploration, single backtests, parameter optimization, portfolio backtests, and result/history retrieval. Each tool serves a distinct purpose without unnecessary sprawl or redundancy.
The toolset covers the full backtesting lifecycle: discover assets, inspect price data, run and monitor backtests, run and monitor optimizations, run portfolio backtests, retrieve detailed results, and list historical runs. No critical dead ends are apparent for the stated domain.