xyz.hiveintelligence/mcp

Est-ce que xyz.hiveintelligence/mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « xyz.hiveintelligence/mcp » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 8 outils

• check_token_safety≈ 590 tokens

  Token security screen for a contract address: honeypot, taxes, ownership, and related GoPlus risk datapoints, plus a summary of LP lock status, top-holder concentration, and creator/owner balances with plain-language verdicts. EVM chains use chain + address; Solana addresses are detected automatically.

  Paramètres, retour & exemple (3)

  Paramètres

  • chain · string · optionnel
    Chain name or EVM chain id, for example "eth", "bsc", "8453", or "solana". Defaults to eth for 0x addresses; Solana is auto-detected.
  • address · string · optionnel
    Required. Token contract address (0x… for EVM, base58 for Solana).
  • response_format · string · optionnel · concise | detailed | json | markdown
    concise (default) returns the trimmed essentials; detailed returns the full provider payload. json and markdown, the platform-wide values every other tool advertises, are accepted and treated as concise.

  Exemple d'appel

  {"name": "check_token_safety", "arguments": {"chain": "texte", "address": "texte", "response_format": "concise"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "chain": "texte", "address": "texte", "summary": {}, "risk_flags": {}, "token_name": "texte", "holder_count": "texte", "source_receipt": {}}}

• get_api_endpoint_schema≈ 1398 tokens

  Returns the full input schema, operation type, and correct root invoker for any Hive tool by name. Tool names come from search_tools; inspect this contract before execution.

  Paramètres, retour & exemple (3)

  Paramètres

  • endpoint · string · optionnel
    The name of the endpoint to get the schema for.
  • endpoint_name · string · optionnel
    Alias for 'endpoint', accepted for symmetry with invoke_api_endpoint. Provide one of the two.
  • response_format · string · optionnel · json | markdown
    Output format: 'json' for structured data (default) or 'markdown' for human-readable text.

  Exemple d'appel

  {"name": "get_api_endpoint_schema", "arguments": {"endpoint": "texte", "endpoint_name": "texte", "response_format": "json"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"name": "texte", "_hive": {}, "title": "texte", "category": "texte", "provider": "texte", "toolsets": [], "operation": "read", "annotations": {}, "callPattern": "texte", "description": "texte", "inputSchema": {}, "outputSchema": {}}}

• get_token_price≈ 502 tokens

  Current price for one token. Pass token as a CoinGecko id or symbol ("bitcoin", "BTC"), or pass chain + address for a specific contract. Returns price, market cap, and 24h change with provider provenance.

  Paramètres, retour & exemple (5)

  Paramètres

  • chain · string · optionnel
    Chain name for the contract-address variant, for example "eth", "base", "bsc", or "solana".
  • token · string · optionnel
    CoinGecko coin id or ticker symbol, for example "bitcoin" or "BTC". Omit when passing chain + address.
  • address · string · optionnel
    Token contract address; requires chain.
  • vs_currency · string · optionnel
    Quote currency. Default "usd".
  • response_format · string · optionnel · concise | detailed | json | markdown
    concise (default) returns the trimmed essentials; detailed returns the full provider payload. json and markdown, the platform-wide values every other tool advertises, are accepted and treated as concise.

  Exemple d'appel

  {"name": "get_token_price", "arguments": {"chain": "texte", "token": "texte", "address": "texte", "vs_currency": "texte", "response_format": "concise"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"price": 1, "token": "texte", "market_cap": 1, "vs_currency": "texte", "source_receipt": {}, "change_24h_percent": 1}}

• get_wallet_portfolio≈ 598 tokens

  Token holdings for a wallet with balances, USD values, and 24h price change where available. Likely spam airdrops are hidden and counted (include_spam=true shows them). EVM chains route through CoinGecko (eth, base, bsc, polygon_pos, arbitrum, optimism, avax, linea, stable, robinhood, arc) with Alchemy as the fallback; Solana wallets are detected automatically and route through Helius.

  Paramètres, retour & exemple (4)

  Paramètres

  • chain · string · optionnel
    Chain name, for example "eth", "base", "arbitrum", or "solana". Defaults to eth for 0x addresses; Solana is auto-detected.
  • address · string · optionnel
    Required. Wallet address (0x… for EVM, base58 for Solana).
  • include_spam · boolean · optionnel
    Show likely spam airdrops (tokens with a URL or claim lure in the name, and on EVM chains tokens with no market price). Default false; the response says how many were hidden.
  • response_format · string · optionnel · concise | detailed | json | markdown
    concise (default) returns the trimmed essentials; detailed returns the full provider payload. json and markdown, the platform-wide values every other tool advertises, are accepted and treated as concise.

  Exemple d'appel

  {"name": "get_wallet_portfolio", "arguments": {"chain": "texte", "address": "texte", "include_spam": true, "response_format": "concise"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"note": "texte", "chain": "texte", "tokens": [], "address": "texte", "token_count": 1, "source_receipt": {}}}

• invoke_api_endpoint≈ 1521 tokens

  Invokes only read-only Hive endpoints by name. First discover the tool, inspect get_api_endpoint_schema, and pass bounded schema-valid arguments. State-changing endpoints are rejected and must use invoke_stateful_endpoint after explicit user approval.

  Paramètres, retour & exemple (4)

  Paramètres

  • args · object · optionnel
    The arguments to pass to the endpoint. This must match the schema returned by the `get_api_endpoint_schema` tool. You may also pass arguments as flat top-level keys alongside endpoint_name.
  • endpoint · string · optionnel
    Alias for 'endpoint_name', accepted by both root invokers. Provide one of the two.
  • endpoint_name · string · optionnel
    The name of the endpoint to invoke.
  • response_format · string · optionnel · json | markdown
    Output format: 'json' for structured data (default) or 'markdown' for human-readable text.

  Exemple d'appel

  {"name": "invoke_api_endpoint", "arguments": {"args": {}, "endpoint": "texte", "endpoint_name": "texte", "response_format": "json"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": "texte", "_hive": {}, "_type": "texte", "error": "texte", "items": [], "result": "texte", "status": "texte", "message": "texte", "_degraded": "texte", "_metadata": {}, "_provider": "texte", "_truncated": true}}

• invoke_stateful_endpoint≈ 1534 tokens

  Invokes a Hive-native state-changing endpoint after explicit user approval. This router can create, update, archive, remember, forget, acknowledge, or resolve durable Hive state, so clients must not auto-approve it. Inspect get_api_endpoint_schema first and verify the saved result after execution.

  Paramètres, retour & exemple (4)

  Paramètres

  • args · object · optionnel
    The arguments to pass to the endpoint. This must match the schema returned by the `get_api_endpoint_schema` tool. You may also pass arguments as flat top-level keys alongside endpoint_name.
  • endpoint · string · optionnel
    Alias for 'endpoint_name', accepted by both root invokers. Provide one of the two.
  • endpoint_name · string · optionnel
    The name of the endpoint to invoke.
  • response_format · string · optionnel · json | markdown
    Output format: 'json' for structured data (default) or 'markdown' for human-readable text.

  Exemple d'appel

  {"name": "invoke_stateful_endpoint", "arguments": {"args": {}, "endpoint": "texte", "endpoint_name": "texte", "response_format": "json"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"data": "texte", "_hive": {}, "_type": "texte", "error": "texte", "items": [], "result": "texte", "status": "texte", "message": "texte", "_degraded": "texte", "_metadata": {}, "_provider": "texte", "_truncated": true}}

• search_tools≈ 2366 tokens

  Search canonical task toolsets, compact user-intent routes, and the full Hive coverage catalog. Select a matching route first, follow its ordered primary calls and conditional fallbacks, then inspect each exact schema. Execute reads with invoke_api_endpoint and explicitly approved Hive state changes with invoke_stateful_endpoint.

  Paramètres, retour & exemple (12)

  Paramètres

  • limit · integer · optionnel
    Maximum tools to return. Default 20.
  • query · string · optionnel
    Search text matched against tool name, title, category, provider, and summary.
  • cursor · string · optionnel
    Pagination cursor from the previous response.
  • detail · string · optionnel · compact | standard | full
    Toolset detail level. Defaults to compact. Use full only when the task output schema is needed.
  • category · string · optionnel
    Optional category filter, for example Portfolio & Wallet.
  • provider · string · optionnel
    Optional provider filter such as CoinGecko, Tenderly, Helius, GoPlus, CCXT, Alchemy, DeFiLlama, Hyperliquid, or Open Data Fetch.
  • route_id · string · optionnel
    Optional exact task-shaped route id. Use the matched route's ordered calls and conditional fallbacks instead of choosing from the coverage catalog.
  • toolset_id · string · optionnel
    Optional exact canonical task toolset id. Use this after an initial compact result to inspect one workflow.
  • toolset_limit · integer · optionnel
    Maximum matching task toolsets to return. Default 3, max 5.
  • evidence_phase · string · optionnel
    Optional exact workflow evidence phase. Supported values: activity, alerts, approvals, assets, authenticity, balances, blocks, bridges, derivatives, discovery, enrichment, evidence, fees, funding, gas, history, holders, identity, infrastructure, liquidity, logs, market, markets, memory, monitoring, ohlcv, owners, positions, reports, risk, routing, sales, schema, simulation, stablecoins, trades, transactions, tvl, yields.
  • toolset_cursor · string · optionnel
    Pagination cursor for task toolset matches.
  • response_format · string · optionnel · json | markdown
    Output format: 'json' for structured data (default) or 'markdown' for human-readable text.

  Exemple d'appel

  {"name": "search_tools", "arguments": {"limit": 1, "query": "texte", "cursor": "texte", "detail": "compact", "category": "texte", "provider": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"_hive": {}, "query": "texte", "tools": [], "category": "texte", "provider": "texte", "route_id": "texte", "toolsets": [], "pagination": {}, "toolset_detail": "compact", "toolset_pagination": {}}}

• validate_task_result≈ 1435 tokens

  Validates a proposed workflow answer against Hive's typed task-output and evidence-receipt contract before it is shown to the user. It checks the selected route id, ordered route-only calls, conditional fallback use, the four-call route budget, claim-to-receipt citations, canonical phase coverage, and internal receipt consistency. It cannot authenticate invented receipts or turn SHA-256 self-checks into signatures, so every call entry must be copied exactly from the server-minted _hive block returned by that execution.

  Paramètres, retour & exemple (3)

  Paramètres

  • result · object · requis
    The proposed task result envelope. Each receipt.calls entry must be copied exactly from a material call's _hive object.
  • response_format · string · optionnel · json | markdown
    Output format: 'json' for structured data (default) or 'markdown' for human-readable text.
  • task_toolset_id · string · requis
    Canonical task toolset id returned by search_tools.

  Exemple d'appel

  {"name": "validate_task_result", "arguments": {"result": {}, "task_toolset_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"_hive": {}, "valid": true, "errors": [], "route_id": "texte", "warnings": [], "call_count": 1, "receipt_ids": [], "task_toolset_id": "texte"}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://mcp.hiveintelligence.xyz/mcp