MCP servers › io.github.MangroveTechnologies › mangroveai
MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23
io.github.MangroveTechnologies/mangroveai
Backtest and paper-trade crypto strategies. Free API key or pay per call in USDC (x402). — the publisher's description
Summary
io.github.MangroveTechnologies/mangroveai is a remote MCP server listed in the official MCP registry at version 1.0.0. On 2026-10-23 ProtocolProbe connected to it in read-only mode and read its inventory: 76 tools, 0 resources and 0 prompts.
Record checks
4 of 5 record checks met · 4 do not apply
- met: Registry entry is active and says how to run it
- met: Source repository link opens
- met: Repository is not archived
- met: Code pushed to the repository in the 90 days before our check
- not met: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: 5 stars (ranked from 10)
From public records, not a safety rating. Each check with its reason · Is it safe to install?
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Sign-in
- none needed to open a session
- Repository
- public
- Tools
- 76
- Described as changing data
- 6 of 76 toolsAI-classified
- Mainly works on
- accounts and data in outside web services; money, payments or tradingAI-classified
- Topic
- finance-and-paymentsAI-classified
- Pricing
- freemiumAI-classified
- Last tested
- 2026-10-23
Observed fact
This server accepted a session without any credential and lists 4 tools whose name or declaration suggests they change data (delete_strategy, update_strategy_status, save_strategy, update_strategy). That is our reading of the names; we did not call them. Source: our connection, 2026-10-23.
Worth knowing before you connect it
- 6 tools are described as changing something (delete_strategy, update_strategy_status, build_strategy_for_regime, …): our AI model's reading of the descriptions, not something we tested, and the server opened a session without any credential. We did not call them.
Each line comes from a section below, with its source and date.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-10-23
- Mode
- read-only (no tool calls)
- Latest version
- 1.0.0, published 2026-10-22 (registry, as of the 2026-10-23 snapshot)
- First listed version
- 2026-10-22 (earliest version still in the registry; older removed versions would be earlier)
- Registry data
- snapshot 2026-10-23
- Package and repository
- checked 2026-10-23
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Changes since the last refresh
New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 1.0.0 (published 2026-10-22).
Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.
What it is
What does this server offer?
Observed inventoryWhat it mainly works on, as our AI model read its tool descriptions: accounts and data in outside web services; money, payments or trading.
6 of 76 tools are described as changing something (creating, editing, deleting, sending or running). For 18 the reading was uncertain, so no mark is shown.
“Permanently delete a strategy by its ID.”
1 input, 1 required
strategy_idstringrequired
- update_strategy_statuscreates or changes datadescribed as changing data
“Update the status of a strategy.”
2 inputs, 2 required
new_statusstringrequiredstrategy_idstringrequired
- get_trades_for_strategyreads or searches
“Get trade records for a specific strategy by its ID.”
2 inputs, 1 required
limitintegerstrategy_idstringrequired
“List open (or all) positions for the current user.”
4 inputs
assetstringlimitintegeropen_onlybooleanstrategy_idstring
- evaluate_strategyreads or searches
“Evaluate a strategy against current live market data to check if entry or exit signals are active — read-only signal check, does NOT place any orders.”
1 input, 1 required
strategy_idstringrequired
“Bar-by-bar decision log for a strategy — every time the agent checked signals for this strategy.”
3 inputs, 1 required
limitintegeroffsetintegerstrategy_idstringrequired
- build_strategy_for_regimedescribed as changing data
“Run the Strategy Engine route in one call.”
2 inputs, 1 required
assetstringrequired“Asset symbol, e.g.”candle_sizestring“Duration of one candle, e.g.”
- classify_market_segmentreads or searches
“Classify one stretch of market: a date range, or a catalog window by file name.”
8 inputs
assetstring“Asset symbol, e.g.”candle_sizestring“Duration of one candle, e.g.”end_datestring“ISO end of the window.”market_data_venuestring“Exact venue of the requested market.”providerstring“Optional upstream override; omitted uses the existing server default.”quote_tokenstring“Quote currency of the requested market.”start_datestring“ISO start of the window, e.g.”window_filestring“A catalog window's file name, classified as it stands.”
- evaluate_multiple_signals_seriesreads or searches
“Evaluate chart data and optional signal triggers over a specific range.”
9 inputs
chart_timeframestring“Live chart timeframe; dataset mode uses its bundled timeframe”dataset_keystring“Bundled dataset key; replaces symbol and date range”end_datestring“Live-mode chart end timestamp; required unless dataset_key is provided”market_data_venuestring“Live-data exchange; supply with quote_token”providerstring“Explicit external history provider”quote_tokenstring“Live-data quote; supply with market_data_venue”signalsarray“Up to 20 registered signals to evaluate”start_datestring“Live-mode chart start timestamp; required unless dataset_key is provided”symbolstring“Live-mode asset symbol; required unless dataset_key is provided”
- evaluate_signalcalculates or converts
“Evaluate a signal against provided market data and parameters.”
3 inputs, 2 required
market_dataarrayrequiredparametersobjectsignal_namestringrequired“Signal name”
- find_sweep_runsreads or searches
“Runs from one sweep, or from every sweep this person has, filtered and sorted by the engine.”
39 inputs
assetstring“Asset symbol, e.g.”atr_periodinteger“Only runs that used this ATR period.”beats_benchmarksboolean“Only runs that beat all three benchmarks over the same”beats_crypto_benchmarksboolean“Only runs that beat the crypto benchmarks rather than only their own asset.”candle_sizestring“Duration of one candle, e.g.”cooldown_barsinteger“Only runs that used this cooldown.”coveringstring“Only runs over windows covering this single date, as YYYY-MM-DD.”covering_fromstring“Only runs whose window OVERLAPS this date onwards.”covering_tostring“Only runs whose window overlaps up to this date.”experiment_idstring“The sweep, as create_sweep returned it.”generationstring“Only runs from this engine generation, so runs made under different engine behaviour are not compared as though alike.”limitinteger“Maximum results.”market_directionstring“Only runs from windows of this market character, e.g.”max_delta_vs_assetnumber“Only runs beating their own asset by at most this much.”max_delta_vs_benchmarknumber“Only runs beating their benchmark by at most this much, so "between 3 and 8" is one question rather than a page fetched and thrown away.”max_irrnumber“Only runs at or below this annualised IRR.”max_returnnumber“Only runs at or below this total return.”max_risk_per_tradenumber“Only runs that risked this fraction per trade.”max_sharpenumber“Only runs at or below this Sharpe ratio.”max_tradesinteger“Only runs at or below this trade count.”max_win_ratenumber“Only runs at or below this win rate.”min_delta_vs_assetnumber“Only runs beating buy-and-hold on their own asset by at least this much.”min_delta_vs_benchmarknumber“Only runs that beat their benchmark by at least this much.”min_irrnumber“Only runs at or above this annualised IRR.”min_returnnumber“Only runs at or above this total return.”
and 14 more not listed here.
“Full metadata and risk profile for one crypto asset on the Mangrove platform: approval status, risk score breakdown, regulatory status and identifiers.”
1 input, 1 required
symbolstringrequired“Asset symbol, e.g.”
Show 64 more tools
“Fetch a backtest that already ran, by id, with the execution config it used.”
1 input, 1 required
backtest_idstringrequired“The run's UUID, as run_backtest returned it.”
“The individual trades a backtest made -- entry and exit prices and times, profit or loss, and why each one closed.”
3 inputs, 1 required
backtest_idstringrequired“The run's UUID, as run_backtest returned it.”limitinteger“Maximum results.”offsetinteger“Pagination offset in the result units documented by the tool; zero starts the first page.”
“Buy-and-hold return for an asset between two dates, as a percentage.”
6 inputs, 3 required
assetstringrequired“Asset symbol, e.g.”base_tokenstring“Canonical base token; supply with quote_token and market_data_venue.”end_datestringrequired“ISO end of the window.”market_data_venuestring“Exact venue of the requested market.”quote_tokenstring“Quote currency of the requested market.”start_datestringrequired“ISO start of the window, e.g.”
“Total Value Locked for a whole blockchain such as Ethereum, Base or Solana.”
1 input, 1 required
chainstringrequired“Chain name or slug, e.g.”
“Crypto ETF net flows -- institutional inflows and outflows for spot BTC and ETH ETFs.”
Takes no inputs.
- get_execution_config_schemareads or searches
“Every execution-config parameter a strategy can carry: the platform default, what it does, the effect of raising or lowering it, its legal bounds, and whether it is a strategy-character knob, an acco…”
Takes no inputs.
“Global crypto market snapshot -- total market cap, BTC dominance, total 24h volume and the 24h change.”
Takes no inputs.
- get_influence_scorereads or searches
“Influence score for a single X/Twitter account: a 0-100 score and follower count.”
1 input, 1 required
usernamestringrequired“X/Twitter handle, with or without the leading @.”
“Per-pool borrow rates across DeFi lending protocols such as Aave, Compound and Morpho.”
Takes no inputs.
“Latest trade price for a selected market, plus aggregate market cap and 24h volume.”
4 inputs, 1 required
market_data_venuestring“Exact venue of the requested market.”providerstring“Optional upstream override; omitted uses the existing server default.”quote_tokenstring“Quote currency of the requested market.”symbolstringrequired“Asset symbol, e.g.”
“Classify an asset's regime using a lookback of 1-365 days of daily closes: the return and a bull/neutral/bear band over 90, 180 and 365 days, plus annualised volatility as a percentage, a bucket, and…”
5 inputs, 1 required
assetstringrequired“Asset symbol, e.g.”lookback_daysinteger“Number of days of history to request.”market_data_venuestring“Exact venue of the requested market.”providerstring“Optional upstream override; omitted uses the existing server default.”quote_tokenstring“Quote currency of the requested market.”
- get_marketplace_strategyreads or searches
“One marketplace listing in full: its metrics, the signals it is built from (names only; the creator's tuning is never exposed), its backtest summary, and whether it is already in this account.”
1 input, 1 required
strategy_idstringrequired“The strategy's UUID.”
“Daily OHLCV (open, high, low, close, volume) history for one crypto asset over the requested lookback (1-3650 days).”
5 inputs, 1 required
lookback_daysinteger“Number of days of history to request.”market_data_venuestring“Exact venue of the requested market.”providerstring“Optional upstream override; omitted uses the existing server default.”quote_tokenstring“Quote currency of the requested market.”symbolstringrequired“Asset symbol, e.g.”
- get_onchain_seriesreads or searches
“Per-bar on-chain metric time series for a token.”
8 inputs, 2 required
chainstring“Chain name or slug, e.g.”date_fromstring“ISO date string for the start of the window.”date_tostring“ISO date string for the end of the window.”intervalstring“Candle size, e.g.”metricsarrayrequired“Metric names to include in the series.”providerstring“Optional upstream override; omitted uses the existing server default.”symbolstringrequired“Asset symbol, e.g.”top_ninteger“Return only the first this many.”
- get_perp_funding_ratesreads or searches
“Aggregated DeFi perpetual funding rates across venues.”
Takes no inputs.
- get_playground_datareads or searches
“Return OHLCV chart data for a specific playground dataset.”
1 input, 1 required
dataset_keystringrequired
“Total Value Locked for a single DeFi protocol such as Aave, Uniswap or Curve.”
1 input, 1 required
protocol_namestringrequired“Protocol slug or display name, e.g.”
“Get complete metadata for an exact registered signal name.”
1 input, 1 required
signal_namestringrequired“Signal name”
- get_smart_money_dex_tradesreads or searches
“Recent DEX trades from smart-money wallets across chains.”
5 inputs
chainsarray“Optional list of chains to include.”filtersobject“Optional filter object passed through to the upstream provider.”order_byarray“Optional ordering list passed through to the upstream provider.”pageinteger“Page number for pagination.”per_pageinteger“Page size for pagination.”
“One-token flow intelligence snapshot: returns net USD flows and wallet counts for smart traders, whales, exchanges, fresh wallets and public figures together in ONE response.”
3 inputs, 1 required
chainstring“Chain name or slug, e.g.”symbolstringrequired“Asset symbol, e.g.”timeframestring“Aggregation window, e.g.”
- get_smart_money_historical_holdingsreads or searches
“Historical snapshots of what smart-money wallets held on specific dates.”
7 inputs
chainsarray“Optional list of chains to include.”date_fromstring“ISO date string for the start of the window.”date_tostring“ISO date string for the end of the window.”filtersobject“Optional filter object passed through to the upstream provider.”order_byarray“Optional ordering list passed through to the upstream provider.”pageinteger“Page number for pagination.”per_pageinteger“Page size for pagination.”
- get_smart_money_holdingsreads or searches
“Current smart-money holdings: what funds and smart traders are holding right now, sorted by USD value.”
4 inputs
chainsarray“Optional list of chains to include.”include_labelsarray“Smart-money wallet labels; omitted uses Fund and Smart Trader.”limitinteger“Maximum results.”min_value_usdnumber“Minimum USD value to include.”
- get_smart_money_netflowsreads or searches
“Aggregated smart-money netflows across all tokens market-wide: which tokens funds and smart traders are accumulating or distributing.”
4 inputs
chainsarray“Optional list of chains to include.”include_labelsarray“Smart-money wallet labels; omitted uses Fund and Smart Trader.”limitinteger“Maximum results.”timeframestring“Aggregation window, e.g.”
- get_smart_money_perp_tradesreads or searches
“Perpetual futures trades from smart-money wallets on Hyperliquid.”
4 inputs
filtersobject“Optional filter object passed through to the upstream provider.”order_byarray“Optional ordering list passed through to the upstream provider.”pageinteger“Page number for pagination.”per_pageinteger“Page size for pagination.”
- get_smart_money_sentimentreads or searches
“On-chain sentiment read for a token derived from smart-money wallet net flows.”
2 inputs, 1 required
chainstring“Chain name or slug, e.g.”symbolstringrequired“Asset symbol, e.g.”
- get_social_mentionsreads or searches
“Recent X/Twitter posts about a crypto asset or topic: post text, id and time, at most 10 posts, plus how many posts the search matched.”
3 inputs, 1 required
hours_backinteger“Lookback window in hours.”limitinteger“Maximum results.”topicstringrequired“Asset symbol, project name or free-form topic.”
“Keyword-polarity sentiment for a crypto cashtag on X/Twitter.”
2 inputs, 1 required
hours_backinteger“Lookback window in hours.”topicstringrequired“Asset symbol, project name or free-form topic.”
- get_stablecoin_metricsreads or searches
“Global stablecoin metrics -- total supply, per-chain breakdown and the top stablecoins by market cap.”
Takes no inputs.
“Fetch one saved strategy in full -- its entry and exit signals, asset, timeframe and status.”
2 inputs
namestring“Its name, if the id is unknown.”strategy_idstring“The strategy's UUID.”
- get_symbol_exchangesreads or searches
“The exchanges that list one specific token, with per-venue metadata.”
1 input, 1 required
symbolstringrequired“Asset symbol, e.g.”
- get_token_dex_tradesreads or searches
“DEX trades for a specific token across all participants in a date window.”
8 inputs, 1 required
chainstring“Chain name or slug, e.g.”date_fromstring“ISO date string for the start of the window.”date_tostring“ISO date string for the end of the window.”filtersobject“Optional filter object passed through to the upstream provider.”order_byarray“Optional ordering list passed through to the upstream provider.”pageinteger“Page number for pagination.”per_pageinteger“Page size for pagination.”symbolstringrequired“Asset symbol, e.g.”
- get_token_flowsreads or searches
“Paginated historical flow records for one non-stablecoin token between explicit start and end dates, optionally filtered by one wallet label.”
9 inputs, 1 required
chainstring“Chain name or slug, e.g.”date_fromstring“ISO date string for the start of the window.”date_tostring“ISO date string for the end of the window.”filtersobject“Optional filter object passed through to the upstream provider.”labelstring“Wallet category: smart_money, exchange, whale, public_figure, or top_100_holders.”order_byarray“Optional ordering list passed through to the upstream provider.”pageinteger“Page number for pagination.”per_pageinteger“Page size for pagination.”symbolstringrequired“Asset symbol, e.g.”
“On-chain token holder distribution for a token: total on-chain holder count, top-10 concentration percentage and a concentration score.”
1 input, 1 required
symbolstringrequired“Asset symbol, e.g.”
“Token unlock schedules and supply metrics -- upcoming vesting cliffs and total supply movement per token.”
Takes no inputs.
“DeFi protocol treasury holdings -- how much a protocol holds in its own treasury and what tokens it owns.”
Takes no inputs.
“The crypto assets trending right now by 24h search volume.”
Takes no inputs.
“Read a requested KB guide or a known source section by slug.”
6 inputs, 1 required
fullboolean“Explicit full content download; cannot combine with offset or max_chars.”max_charsinteger“Page size, default 6000, capped at 12000 and the response budget.”offsetinteger“Pagination offset in the result units documented by the tool; zero starts the first page.”section_anchorstring“Exact anchor from overview or search, required only for section view.”slugstringrequired“The document slug.”viewstring“Use overview for a brief summary and headings; section for a specific topic; content for document pages.”
- kb_get_signal_quick_referencereads or searches
“Read the Signals Quick Reference guide when the user asks for that guide or its documented entries.”
5 inputs
fullboolean“Explicit full content download; cannot combine with offset or max_chars.”max_charsinteger“Page size, default 6000, capped at 12000 and the response budget.”offsetinteger“Pagination offset in the result units documented by the tool; zero starts the first page.”section_anchorstring“Exact anchor from overview or search, required only for section view.”viewstring“Use overview for a brief summary and headings; section for a specific topic; content for document pages.”
- kb_glossary_getreads or searches
“Return the KB glossary entry for an explicitly requested glossary definition or exact glossary term.”
1 input, 1 required
termstringrequired“The term to look up, case-insensitive.”
“Reads the Mangrove Knowledge Base package: every document's slug, title and summary.”
Takes no inputs.
“Locate KB articles or source sections using short topic keywords.”
5 inputs, 1 required
expandboolean“Whether to expand synonyms; ignored when tags are set.”limitinteger“Maximum results.”qstringrequired“The search text, in ordinary words.”tagstring“Restrict to one tag category; disables synonym expansion.”tagsarray“Restrict to any of these tag categories; cannot combine with tag.”
- list_approved_assetsreads or searches
“List assets approved by Mangrove, including supported stablecoins and tokens.”
1 input
top_ninteger“Return only the first this many.”
- list_backtest_marketsreads or searches
“List available execution venue and quote-token choices for a backtest.”
1 input, 1 required
assetstringrequired“Asset symbol, e.g.”
“The user's recent backtest runs, newest first, optionally just the ones for one strategy.”
2 inputs
limitinteger“Maximum results.”strategy_idstring“The strategy's UUID.”
“Every exchange the Mangrove platform tracks, with per-exchange tier and 24h volume.”
Takes no inputs.
- list_playground_datasetsreads or searches
“Return metadata for all available playground CSV datasets.”
Takes no inputs.
- list_signal_labelsreads or searches
“Every signal's friendly name, display name and short description, keyed by code name.”
Takes no inputs.
“List available trading signals: names, types (TRIGGER or FILTER) and short descriptions.”
5 inputs
categorystring“Filter by category (momentum, trend, volume, volatility, patterns, onchain)”limitinteger“Page size: default 30, maximum 30.”offsetinteger“Pagination offset”regime_directionstring“Filter to signals admissible for a regime band (mega_bull, super_bull, bull, neutral, bear, super_bear, mega_bear)”rolestring“Filter by the part a signal plays in a strategy (TRIGGER or FILTER)”
“List the strategy definitions saved HERE, in this service -- drafts and backtested strategies authored through chat.”
1 input
limitinteger“Maximum results.”
“The trades a person's strategies have closed -- what was made or lost on each, why it exited, and what the fees and slippage cost.”
4 inputs
assetstring“Asset symbol, e.g.”limitinteger“Maximum results.”outcomestring“Only "win" or only "loss".”strategy_idstring“The strategy's UUID.”
“Load one of your skills: the full instructions for doing something, which the turn only announced by name.”
3 inputs, 1 required
resourcestring“One file the skill carries, by name, as `resources` lists them.”sectionstring“One section of it, by heading.”skillstringrequired“Which skill, by the name the turn announced.”
- match_signalsreads or searches
“Match a trading description to ranked signals.”
6 inputs, 1 required
descriptionstringrequired“Natural language description of the desired signal/rule”regime_directionstring“Market regime band”rolestring“Signal role”similarity_thresholdnumber“Minimum similarity score to include”top_kinteger“Number of matches to return”user_intentobject“Optional intent dict (e.g., from intent extractor)”
“Explain trading concepts, definitions, relationships, comparisons and when signals work or fail using Michael's knowledge graph.”
23 inputs, 1 required
boundedboolean“outputs: only values with a fixed range.”directionstring“neighbors: in = what reads this, out = what this depends on.”hopsinteger“ask: how far to walk from each match.”kindstring“The class: what a computation measures.”limitinteger“Maximum results.”max_depthinteger“path, paths: how long a route may be.”max_nodesinteger“walk: stop expanding once this many nodes are collected.”opstringrequired“Which question you are asking.”paramstring“find: a parameter name -- every signal that takes it.”primitivestring“neighbors: keep only neighbours of this node primitive, e.g.”qstring“The search text, in ordinary words.”radiusinteger“walk: how many hops out the neighbourhood reaches.”relationstring“neighbors: follow only this one relation.”relation_categorystring“neighbors: follow only edges of this whole relation category (structural, descriptive, associative, meta) -- see stats for the list.”relationsarray“path, paths, ask: follow only these relations.”requiresstring“An input column it needs.”rolestring“The part a signal plays in a strategy.”seedsinteger“ask: how many top matches to expand from before re-ranking.”sibling_hopsboolean“paths: include routes that pass through a shared parent (both nodes are, say, Signal) rather than a direct connection.”statusstring“Whether the thing is current or withdrawn.”tostring“path, paths: the destination node.”unitsstring“The unit an output is measured in.”whystring“neighbors, walk, ask: keep only edges whose own stated reason matches these words -- the same relation can carry different claims.”
- query_signal_behaviorreads or searches
“Query measured signal behaviour: describe, pick, find or gap_probability.”
14 inputs, 1 required
categorystring“find: restrict to one family, e.g.”limitinteger“Maximum results, 1-100”lookupstringrequired“describe: one signal -- parameter meanings, measured span, what its default measures.”max_gap_barsnumber“pick/find, TRIGGER only: median gap at most this many bars”max_gap_range_barsnumber“gap_probability: high end of the gap range, inclusive (required)”max_ratenumber“find: high end of the band, same units (required)”max_run_barsnumber“pick/find, FILTER only: mean run at most this many bars”min_gap_barsnumber“pick/find, TRIGGER only: median gap at least this many bars”min_gap_range_barsnumber“gap_probability: low end of the gap range, inclusive (required)”min_ratenumber“find: low end of the band, same units (required)”min_run_barsnumber“pick/find, FILTER only: mean run at least this many bars”signalstring“Signal name, e.g.”signal_typestring“FILTER (an ongoing state) or TRIGGER (a one-bar event); measured separately”target_ratenumber“pick: rate to aim for -- FILTER selectivity 0-1, TRIGGER firings per 1,000 bars.”
“Start a backtest of one saved strategy over a window of history.”
7 inputs, 3 required
acknowledge_defaultsboolean“Pass True to submit even though signal parameters are at their library defaults -- an explicit statement that the defaults were considered and stood by, never …”end_datestringrequired“ISO end of the window.”engine_generationinteger“Only set when the person specifies an engine generation; omitted uses latest.”market_data_venuestring“Exact venue of the requested market.”quote_tokenstring“Quote currency of the requested market.”start_datestringrequired“ISO start of the window, e.g.”strategy_idstringrequired“The strategy's UUID.”
“To promote a sweep pick, pass source_experiment_id and source_run_index; the service loads its authorized configuration and checks coverage before saving.”
12 inputs, 2 required
assetstringrequired“Asset symbol, e.g.”constraintsobject“Execution values the person stated, e.g.”entry_signalsarray“The signals that open a position.”exit_signalsarray“The signals that close one, same shape.”market_data_venuestring“Exact venue of the requested market.”quote_tokenstring“Quote currency of the requested market.”regime_directionstring“The direction band from get_market_regime, e.g.”regime_overrideboolean“Save anyway when the regime check refuses.”source_config_hashstring“The selected row's config_hash, as find_sweep_runs reported it.”source_experiment_idstring“For a sweep pick, its experiment ID.”source_run_indexinteger“The selected sweep row, including zero.”strategy_namestringrequired“What to call it, in plain words a person reads -- the entry trigger's friendly_name from the knowledge graph, then the asset and timeframe, e.g.”
“Rank several candidate strategies by how likely each is to trade at all, before spending backtests on them.”
2 inputs, 2 required
assetstringrequired“Asset symbol, e.g.”candidatesarrayrequired“Each {entry: [{name, params?, timeframe?}], exit: [...]}.”
- screen_smart_moneyreads or searches
“Screen the market for tokens that smart-money wallets are currently accumulating or distributing.”
3 inputs
chainsarray“Optional list of chains to include.”limitinteger“Maximum results.”timeframestring“Aggregation window, e.g.”
“Search the public strategy marketplace -- the platform's own listings, which are digital-asset strategies on crypto pairs -- over every dimension the marketplace page filters on: free text, asset, ti…”
24 inputs
assetstring“Asset symbol, e.g.”asset_classarray“Keep listings in these asset classes.”backtest_directionstring“Keep listings backtested in this market direction, e.g.”backtest_trendstring“Keep listings backtested in this trend character, e.g.”backtest_volatilitystring“Keep listings backtested in this volatility band, e.g.”beats_all_benchmarksboolean“Keep only listings whose return beat BTC, ETH and the S&P over their own window.”candle_sizestring“Duration of one candle, e.g.”free_onlyboolean“Keep only listings with no subscription price.”limitinteger“Maximum results.”max_drawdown_pctnumber“Keep listings whose max drawdown is at or below this, in percent.”min_calmar_rationumber“Keep listings at or above this Calmar ratio.”min_gain_to_pain_rationumber“Keep listings at or above this gain-to-pain ratio.”min_irr_pctnumber“Keep listings at or above this annualised IRR, in percent.”min_sharpe_rationumber“Keep listings at or above this Sharpe ratio.”min_sortino_rationumber“Keep listings at or above this Sortino ratio.”min_total_return_pctnumber“Keep listings at or above this total return, in percent.”min_total_tradesinteger“Keep listings with at least this many trades.”min_trades_per_weeknumber“Keep listings trading at least this often, per week.”min_win_rate_pctnumber“Keep listings at or above this win rate, in percent.”offsetinteger“Pagination offset in the result units documented by the tool; zero starts the first page.”orderstring“desc for best-first on that metric, asc for worst-first.”risk_levelarray“Keep listings at any of these risk levels, e.g.”searchstring“Free text matched against listing name, description and creator.”sortstring“The column to order by.”
“Search signal names, parameters or description keywords.”
7 inputs, 1 required
categorystring“Signal library module”limitinteger“Maximum results”offsetinteger“Pagination offset”querystringrequired“Search query string”regime_directionstring“Market regime band”rolestring“Signal role”search_typestring“Type of search”
“Change a DRAFT strategy in place: its signals, their parameters, or a stated execution value.”
7 inputs, 1 required
constraintsobject“Execution values the person stated, e.g.”entry_signalsarray“The signals that open a position.”exit_signalsarray“The signals that close one, same shape.”regime_directionstring“The direction band from get_market_regime, e.g.”regime_overrideboolean“Save anyway when the regime check refuses.”strategy_idstringrequired“The strategy's UUID.”strategy_namestring“What to call it, in plain words a person reads -- the entry trigger's friendly_name from the knowledge graph, then the asset and timeframe, e.g.”
- validate_signal_paramscalculates or converts
“Validate parameters for a signal.”
2 inputs, 1 required
parametersobjectsignal_namestringrequired“Signal name”
“Check a saved strategy against everything that has to be true for it to run: the signal names and their parameter keys, the roles composing, a timeframe on every signal, and a timeframe on the strate…”
1 input, 1 required
strategy_idstringrequired“The strategy's UUID.”
“Discover Mangrove managed tools without executing them.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
areasarray“Functional area names returned by detail=areas.”detailstring“Output detail.”namesarray“One or any number of exact advertised tool names.”
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
- Says what the tool does
- 100% of 76 tools
- Says what it returns
- 97% of 76 tools
- States limits, defaults or errors
- 25% of 69 tools
- Says when to use it
- 100% of 74 tools
- Items covered per tool
- 3.3 of 4 on average
Counted from the listing
- Parameters with a description
- 95% of 313
- Tools with a description
- 100% of 76
- Typical description length
- 566 characters
The tool set
Counted from the listing
- Tools
- 76
- Size of the list
- about 22,750 tokens for an agent to load (characters ÷ 4)
- Naming
- 76 of 76 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 76 of 76 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the remote endpoint (Streamable HTTP)
We connected to this URL on 2026-10-23 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste: https://api.mangrovedeveloper.ai/mcp/
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"mangroveai": {
"url": "https://api.mangrovedeveloper.ai/mcp/"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"mangroveai": {
"type": "http",
"url": "https://api.mangrovedeveloper.ai/mcp/"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"mangroveai","type":"http","url":"https://api.mangrovedeveloper.ai/mcp/"}'Claude Code
claude mcp add --transport http mangroveai https://api.mangrovedeveloper.ai/mcp/
Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://api.mangrovedeveloper.ai/mcp/ --transport http
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
Does the registry listing match what we found?
Feature #6The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint api.mangrovedeveloper.ai/mcp/ | Session opened | matches | our test · 2026-10-23 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-10-23 |
| Repository github.com/MangroveTechnologies/mangrove-agent | Opens publicly | matches | api.github.com · 2026-10-23 |
Who made it?
Feature #7 · lineage
Facts about the publisher. We do not turn them into a trust score.
- Namespace
- io.github.MangroveTechnologies
- GitHub owner
- an organization (MangroveTechnologies)
- Repository
- github.com/MangroveTechnologies/mangrove-agent
- Stars
- 5
- Repository age
- 181–365 days
- Last push
- 0–30 days ago
- Archived
- no
- Security policy
- none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)
Source: the registry entry and api.github.com · 2026-10-23; security policy read from GitHub · 2026-10-23.
Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.
Choosing
Record checks
Public records · not a safety rating4 of 5 record checks met · 4 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: 5 stars (ranked from 10)
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- MetSource repository link opensThe linked GitHub repository is public.
- MetRepository is not archivedNot archived.
- MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
- Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-23. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards
Common questions about io.github.MangroveTechnologies/mangroveai
Answered from the data aboveIs io.github.MangroveTechnologies/mangroveai safe to install?
We do not rate servers as safe or unsafe. 4 of its 5 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. 6 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Is io.github.MangroveTechnologies/mangroveai free to use?
Its website (mangrove.ai/pricing/) describes a freemium pricing model. This is an AI-classified reading of the page on 2026-10-23, so check the page itself before relying on it.
Does io.github.MangroveTechnologies/mangroveai need an API key or sign-in?
It opened a session without any credential on 2026-10-23. The registry entry declares no required credential; no declaration is not a guarantee.
Has io.github.MangroveTechnologies/mangroveai been security tested?
Partly. 2 of the 14 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security verdict is published before verification.
What can io.github.MangroveTechnologies/mangroveai do?
It lists 76 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, delete, run code or commands and calculate or convert. We did not call any tool, so this describes the text, not the behaviour.
Can io.github.MangroveTechnologies/mangroveai change or delete data?
6 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.
Does io.github.MangroveTechnologies/mangroveai publish a security policy?
We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.
Where is the source code of io.github.MangroveTechnologies/mangroveai?
In github.com/MangroveTechnologies/mangrove-agent, which opens publicly.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Similar servers
Same topic · AI-read
- io.github.longsizhuo/openinvestopenInvestalso has tools that calculates or converts, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
- io.github.valuein/mcp-sec-edgarValuein — SEC EDGAR Fundamentals & Smart-Money Dataalso has tools that calculates or converts, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
- exchange.merx/mcpMERX - TRON Resource Exchangealso has tools that calculates or converts, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
- ai.betslipdoctor/mcpBetSlip Doctoralso has tools that calculates or converts, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
- io.github.Marginpad/sdkalso has tools that calculates or converts, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
- ing.crank/crankCrank Protocolalso has tools that calculates or converts, creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
Active servers whose topic is also “finance-and-payments” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Open without sign-in
It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: not run · nothing to check it against
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: not applicable
2 exercised12 not run (reason given)4 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable
Source: our own test, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted a read-only session with the server's remote endpoint
- 1,078 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 76 tools, 0 resources, 0 prompts.
- 5,086 msFinished: 2 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Free forever”
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “io.github.MangroveTechnologies/mangroveai: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/io.github.MangroveTechnologies/mangroveai
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/io.github.MangroveTechnologies/mangroveai)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.
Write to hello@protocolprobe.com · corrections log · methodology