Home / MCP registry index / io.github.MangroveTechnologies/mangroveai
MangroveAI
io.github.MangroveTechnologies/mangroveai in the official MCP registry.
Endpoint https://api.mangrovedeveloper.ai/mcp/. Source: github.com/MangroveTechnologies/mangrove-agent.
The registry describes it as: Backtest and paper-trade crypto strategies. Free API key or pay per call in USDC (x402).
We read its 76 tools on 2026-10-27. Nothing in them matched our tool-poisoning rules.
A clean read means these rules found nothing, not that the server is harmless. A server can change its tools at any time, which is why the index reads it again every week.
Tools it advertises
delete_strategy update_strategy_status get_trades_for_strategy list_positions evaluate_strategy list_evaluations build_strategy_for_regime classify_market_segment evaluate_multiple_signals_series evaluate_signal 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_marketplace_strategy 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 get_smart_money_netflows get_smart_money_perp_trades get_smart_money_sentiment get_social_mentions get_social_sentiment get_stablecoin_metrics get_strategy get_symbol_exchanges get_token_dex_trades get_token_flows get_token_holders get_token_unlocks get_treasuries get_trending kb_get_document kb_get_signal_quick_reference kb_glossary_get kb_list_documents kb_search list_approved_assets list_backtest_markets list_backtests list_exchanges list_playground_datasets list_signal_labels list_signals and 16 more
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/io-github-mangrovetechnologies-mangroveai)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.
Related
| The Stall ai.intuitek.the-stall/the-stall | 200 tools, nothing matched 2026-10-22 |
| SAP MCP Server ai.oobeprotocol.sap.mcp/sap-mcp | 200 tools, nothing matched 2026-10-22 |
| Citiview Agent Market com.citiviewgroup.mcp/agent-market | 200 tools, nothing matched 2026-10-26 |
| ScorpTech x402 API com.it.scorptech/x402 | 200 tools, nothing matched 2026-10-26 |
| Apex Edge — x402-paid machine services dev.pages.nonsynthetic/apex-edge | 200 tools, nothing matched 2026-10-23 |
| io.github.praneeth12098/x402-factory io.github.praneeth12098/x402-factory | 200 tools, nothing matched 2026-10-26 |