A
licenseA
qualityD
maintenanceCompliance and guardrails infrastructure for AI agents, enabling safe operations within regulatory boundaries like GDPR and EU AI Act.
6
MIT
Agent Financial Advisor
Server Details
Compliance, risk, tax and audit checks for AI trading agents: pre-trade, sizing, wash sales, Reg BI.
If you are the author of this connector, you can claim ownership by verifying the domain or GitHub account it belongs to. Claimed connector authors can inspect health checks, view analytics, and manage their listing.
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- mytomclinic/agent-financial-advisor
- GitHub Stars
- 0
TDQS
Score is being calculated.
Available Tools
7 toolsportfolio_reviewPortfolio reviewInspect
A periodic advisor review of a portfolio: weights, concentration (HHI and effective number of holdings), sector and asset-class exposure, drift from targets with the trades to rebalance, and, given return history, volatility, Sharpe, Sortino, drawdown, VaR/CVaR and beta. Ends with prioritized findings. Price: $0.05.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| cash | No | ||
| limits | No | ||
| returns | No | Periodic portfolio returns as decimals. | |
| targets | No | Target weights by symbol or asset_class, summing to 1. | |
| holdings | Yes | ||
| rebalance_band | No | Absolute drift that triggers a rebalance, default 0.05. | |
| risk_free_rate | No | ||
| periods_per_year | No | ||
| benchmark_returns | No |
position_sizePosition sizingInspect
Size a position the way a risk manager would: fixed-fractional risk to a stop, volatility targeting (ATR or annualized vol), or fractional Kelly from your edge statistics. Applies a max-position cap and round lots, and explains the binding constraint. Price: $0.005.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| atr | No | volatility: average true range in price units. | |
| side | No | long | |
| equity | Yes | ||
| method | Yes | ||
| avg_win | No | kelly: average win (any unit, same as avg_loss). | |
| avg_loss | No | kelly: average loss as a positive number. | |
| lot_size | No | Round down to this multiple, default 1. | |
| risk_pct | No | fixed_fractional: fraction of equity to risk, default 0.01. | |
| win_rate | No | kelly: probability of a win (0-1). | |
| annual_vol | No | volatility: annualized volatility of the asset (e.g. 0.35). | |
| stop_price | No | fixed_fractional: protective stop. | |
| entry_price | Yes | ||
| atr_multiple | No | volatility: stop distance in ATRs, default 2. | |
| kelly_fraction | No | kelly: fraction of full Kelly to use, default 0.25. | |
| allow_fractional | No | ||
| max_position_pct | No | Cap on position value / equity, default 0.2. | |
| target_annual_vol_contribution | No | volatility: target vol contribution as fraction of equity, default 0.02. |
pre_trade_checkPre-trade compliance and risk checkInspect
Run an order past a compliance officer and risk manager before sending it to the broker. Checks buying power, cash-account settlement violations, FINRA intraday margin (post-PDT) or legacy PDT limits, Reg SHO short-sale rules, wash-sale exposure, position concentration, per-trade risk versus stop, liquidity, spread, fat-finger prices, leverage and market hours. Returns approve / approve_with_warnings / reject with reasons and a resized quantity when useful. Price: $0.005.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| order | Yes | ||
| market | No | ||
| policy | No | Override risk limits. Defaults: {"max_position_pct":0.2,"max_order_risk_pct":0.02,"max_adv_pct":0.05,"max_spread_pct":0.01,"max_gross_leverage":2,"max_limit_deviation_pct":0.1,"allow_short":true,"allow_extended_hours":false,"require_stop":false} | |
| account | Yes | Account state before the order. |
rules_digestCurrent trading rules digestInspect
Free. The current US trading, margin, settlement and tax rules an agent must follow, with effective dates and sources. Includes changes your training data may predate, such as the June 2026 replacement of the Pattern Day Trader rule. Price: free.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| topic | No |
strategy_auditStrategy audit and overfitting checkInspect
An independent performance auditor for a trading strategy or backtest. From a trade list and/or periodic returns it computes win rate, expectancy, profit factor, streaks, Sharpe/Sortino/drawdown, and tests whether the edge is real: t-stat, Probabilistic Sharpe Ratio and the Deflated Sharpe Ratio that corrects for how many variants you tried. Returns a verdict and red flags. Price: $0.1.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| trades | No | Closed trades. | |
| returns | No | Periodic strategy returns as decimals. | |
| n_trials | No | How many strategy/parameter variants were tested before picking this one. Default 1. | |
| starting_equity | No | For risk-of-ruin and drawdown in dollars from trades. | |
| periods_per_year | No | ||
| trial_sharpe_variance | No | Variance of per-period Sharpe across trials, if known. |
suitability_checkBest-interest suitability reviewInspect
The compliance review a robo-advisor or advisory agent should run before recommending a portfolio to a person: compares the proposal with the client's age, horizon, risk tolerance, liquidity needs and experience under Reg BI / fiduciary standards, flags complex products, and returns a timestamped, hashed suitability memo for the audit file. Price: $0.03.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| client | Yes | ||
| products | No | Complex products included. | |
| allocation | Yes | Weights by asset class: equity, bonds, cash, alternatives, crypto... summing to 1. | |
| annual_fee_pct | No | All-in annual cost (advisory + fund expenses). | |
| max_single_position_pct | No |
tax_lot_planTax lot selection and wash-sale checkInspect
Act as the tax advisor for a sale: compares FIFO, LIFO, HIFO and minimum-tax lot selection, splits short- and long-term gains, estimates tax, flags wash sales, and notes lots about to turn long-term. With mode=harvest it scans positions for tax-loss harvesting. Price: $0.02.
ParametersJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| lots | Yes | ||
| mode | No | sell | |
| sell | No | mode=sell | |
| as_of | No | mode=harvest: date, default today | |
| prices | No | mode=harvest: {SYMBOL: current price} | |
| symbol | No | ||
| tax_rates | No | ||
| min_harvest_loss | No | mode=harvest: ignore losses smaller than this (USD), default 100. | |
| recent_transactions | No |
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
7 tool updates
- First observed
portfolio_review - First observed
position_size - First observed
pre_trade_check - First observed
rules_digest - First observed
strategy_audit - First observed
suitability_check - First observed
tax_lot_plan
Related MCP Connectors
Deterministic decision guardrail for AI agents and bots. Verifies pre-trade economics (long-only).
Deterministic pre-trade risk checks for AI agents on Robinhood Chain. Returns allow/warn/deny.
Compliance MCP for AI agents: sanctions & KYT screening on 50+ chains, stablecoin-freeze, oracle.
OFAC, LEI, EU VAT, AI Act, and company compliance preflight for agents.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceProvides risk guardrails for AI trading agents by analyzing portfolio risk, checking trades against policies, and generating risk policies.47 PyPI2MIT
- AlicenseAqualityBmaintenancePre-action compliance server that lets AI agents check whether an action is allowed, blocked, or flagged before executing, with signed evidence records for auditability.23268 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables algorithmic trading compliance with MiFID II Article 17, providing tools for strategy classification, RTS 6 testing, and best execution audits. Also supports EU AI Act compliance.33 PyPIMIT
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd
Glama MCP Gateway
Add one secure layer between your agents and this server.