mcpwatch

← All servers

Grade B

MangroveAI

io.github.MangroveTechnologies/mangroveai · v1.0.2 · score 89/100 · checked 2026-11-22

Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works

Guardrails for trading agents. Built-in risk management, 100+ tools for strategy R&D, 12+ venues.

Source: https://github.com/MangroveTechnologies/mangrove-agent

Findings

SeverityRuleDetail
LowMW005Remote endpoint lists 84 tool(s) to anyone, no credentials needed.
MediumMW1021 tool(s) can execute commands or delete data (delete_strategy). Require confirmation before the agent calls them.

What was checked

Public tools: build_strategy_for_regime, classify_market_segment, create_sweep, delete_strategy, evaluate_multiple_signals_series, evaluate_signal, evaluate_strategy, find_sweep_runs, get_asset, get_backtest, get_backtest_trades, get_benchmark, get_chain_tvl, get_etf_flows, get_execution_config_schema, get_global_market, get_influence_score, get_lending_rates, get_market_data, get_market_regime, get_ohlcv, get_onchain_series, get_perp_funding_rates, get_playground_data, get_protocol_tvl, get_signal, get_smart_money_dex_trades, get_smart_money_flows, get_smart_money_historical_holdings, get_smart_money_holdings

Maintainer? Add the badge

Grades refresh daily. Think a finding is wrong? Dispute this grade.

[![mcpwatch](https://www.mcpwatch.io/badge/io-github-mangrovetechnologies-mangroveai-00a8ced8.svg)](https://www.mcpwatch.io/s/io-github-mangrovetechnologies-mangroveai-00a8ced8)