AI & Machine Learning

hiveintelligence.xyz

A remote MCP server for connecting to Hive's intelligence services.

1 endpoint8 known toolsFirst detected June 5, 2026Last detected September 6, 2026

ENDPOINT 1

https://mcp.hiveintelligence.xyz/mcp

No auth detected

MCP server metadata

Name: hive-mcp-server
Version: 1.5.2

Capabilities

tools.listChangedresourcespromptscompletions

Server instructions

Hive serves live crypto market data to AI agents over a compact 8-tool root. Loop: search_tools -> get_api_endpoint_schema -> invoke_api_endpoint for reads (invoke_stateful_endpoint only after explicit user approval; validate_task_result before structured answers). Every material response carries a _hive receipt (provider, fetched_at, runtime_status, _hive.receipt_id); cite it when answering. For the three dominant intents call the hero tools directly: get_token_price, check_token_safety, get_wallet_portfolio (response_format "concise" default, "detailed" available). Degraded providers are reported, not hidden: search_tools marks each tool's availability, and unavailable tools return runtime_status with cause and next_action instead of data. Follow next_action; never retry an unchanged failing call in a loop. Discovery is free and cheap: resources hive://toolsets, hive://providers, hive://tools; the 607-tool catalog stays reachable through search_tools or scoped category endpoints. Use limit/page/per_page to keep responses small; a material execution costs 1 credit on the hosted service.

Known tools 8

get_token_price

Current price for one token.

Inferred read-only

check_token_safety

Token security screen for a contract address: honeypot, taxes, ownership, and related GoPlus risk datapoints.

Inferred read-only

get_wallet_portfolio

Token holdings for a wallet with balances and USD values where available.

Inferred read-only

search_tools

Search canonical task toolsets, compact user-intent routes, and the full Hive coverage catalog.

Inferred read-only

get_api_endpoint_schema

Returns the full input schema, operation type, and correct root invoker for any Hive tool by name.

Inferred read-only

invoke_api_endpoint

Invokes only read-only Hive endpoints by name.

Inferred read-only

invoke_stateful_endpoint

Invokes a Hive-native state-changing endpoint after explicit user approval.

Inferred read-only

validate_task_result

Validates a proposed workflow answer against Hive's typed task-output and evidence-receipt contract before it is shown to the user.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.hive-mcp-server]
url = "https://mcp.hiveintelligence.xyz/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "hive-mcp-server": {
      "type": "http",
      "url": "https://mcp.hiveintelligence.xyz/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: hive-mcp-server
Remote MCP URL: https://mcp.hiveintelligence.xyz/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "hive-mcp-server": {
      "url": "https://mcp.hiveintelligence.xyz/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "hive-mcp-server": {
      "type": "http",
      "url": "https://mcp.hiveintelligence.xyz/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "hive-mcp-server",
  "transport": "streamable-http",
  "url": "https://mcp.hiveintelligence.xyz/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for hiveintelligence.xyz was fetched 2026-08-04T02:41:00.320Z and is being refreshed.

Trust status Trusted

hiveintelligence.xyz is assessed as Trusted: Domain has an established technology history spanning over a year.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.