Hive Intelligence integrates across three layers — AI clients (where the agent runs), agent frameworks (where multi-step workflows are coordinated), and the builder ecosystem (the teams shipping production crypto AI on Hive). Every integration uses the same managed MCP endpoint with one API key, so adding a new client or framework is a config change, not an integration project.

AI clients with native MCP support

Hive ships dedicated install guides for every major MCP-compatible AI client. Each install is a single JSON config block (or a one-line CLI command) plus an Authorization: Bearer YOUR_HIVE_API_KEY header — no per-tool integration, no schema work, no boilerplate. The root MCP endpoint uses tools/list for compact discovery and routing; the full live catalog is available through hive://tools, category endpoints, and GET /api/v1/tools.

Claude Desktop — Anthropic's macOS/Windows desktop app
Claude Code — Anthropic's terminal-native coding agent
Cursor — AI code editor with native MCP support
Windsurf — Codeium's AI-native IDE with the Cascade agent
VS Code — Visual Studio Code with GitHub Copilot Chat
ChatGPT Desktop — OpenAI's desktop ChatGPT app with custom MCP Connectors
Codex CLI — OpenAI's terminal-native coding agent
Gemini CLI — Google's open-source AI coding agent
All clients index — pick your client for the full setup walk-through

For local CLI credentials, run npx -y -p hive-intelligence@latest hive init. For MCP in an AI client, use the dedicated install guide for that client so the transport and auth shape match what the client supports.

Agent frameworks

For multi-step agent workflows (research, trading, monitoring, alerting), Hive integrates with the major agent orchestration frameworks via the REST API and language SDKs. The MCP endpoint can be wrapped as a tool provider in any framework that supports HTTP function calling.

LangChain & CrewAI — wire Hive tools as LangChain Tool objects or CrewAI agent tools
REST API tutorial — POST /api/v1/execute with { "tool": "...", "args": { ... } }
MCP integration tutorial — connect any MCP-compatible agent
CLI tutorial — terminal workflows for tool discovery and execution

Eliza (ai16z) and other agent-character frameworks consume Hive via the same MCP endpoint — point the agent's MCP config at https://mcp.hiveintelligence.xyz/mcp, set the auth header, and the full tool catalog becomes available.

Language SDKs and integrations

For applications embedding Hive into broader products (dashboards, mobile apps, server-side pipelines):

JavaScript / TypeScript SDK — npm install hive-intelligence (official, hive-intel/hive-sdk)
Python SDK — pip install hive-intelligence (community-maintained on PyPI; production workloads should call the REST API directly until the official Python SDK ships)
Go integration — REST quickstart with net/http
Java integration — REST quickstart with java.net.http.HttpClient
Rust integration — REST quickstart with reqwest

Other languages can call POST /api/v1/execute — same auth header, same response envelope.

What makes Hive a good fit for AI integrations

Three properties differentiate Hive from single-provider crypto APIs in agent contexts:

Federated coverage. One MCP endpoint surfaces tools from CoinGecko, DefiLlama, GoPlus, Moralis, Alchemy, Codex, Helius, Tenderly, and CCXT — agents get cross-provider context (price + DeFi yield + security score + wallet history) in one tool call instead of stitching multiple APIs together.
Agent-shaped responses. Every tool returns a normalized envelope with fetched_at ISO-8601 timestamps, structured error codes, and machine-readable result shapes. Agents don't have to reason over per-provider REST quirks.
Curated workflows on top of primitives. Beyond raw tool calls, Hive ships synthesis tools — analyze_coin, market_briefing, find_opportunities, get_arbitrage_* — that span multiple providers in one request. Agents get a synthesized answer instead of having to compute it themselves.

See the comparisons hub for side-by-side breakdowns of Hive vs CoinGecko MCP, Moralis Cortex, Alchemy, Codex, Birdeye, Helius, QuickNode, DexScreener, and CoinMarketCap.

Builder ecosystem

35+ named teams currently ship production crypto AI products on Hive — research agents, trading bots, wallet analyzers, security scanners, DeFi yield comparators, and prediction-market interfaces. Selected projects:

Get listed

Building something on Hive that should be in this list? Open a pull request on the Hive GitHub org or contact us — projects shipping in production with active monthly usage are eligible.

Quick Start — connect to Hive in minutes via REST, MCP, or CLI
API Integration Guide — auth, discovery, transport patterns
Tools Reference — full tool catalog across 10 categories
Glossary — definitions for MCP, tool calls, agent skills, and crypto terminology
Comparisons — Hive vs CoinGecko, Moralis, Alchemy, Codex, Birdeye, Helius, and more