hive-crypto-mcp

> Try it now, with no account and no key. The hosted endpoint's anonymous lane

> answers 25 material calls per IP per day; discovery, schema lookup, and

> validation are always free:

>

> ```text

> https://mcp.hiveintelligence.xyz/mcp

> ```

>

> Guided setup · Install guides · Example prompts

Connect

Hive is a hosted MCP server for clients that support remote Streamable HTTP.

Once the hosted OAuth deployment is enabled, interactive clients discover it

from the public endpoint and open browser authorization. Headless agents can

use an API key from secret storage:

https://mcp.hiveintelligence.xyz/mcp

One-click config prefills, URL-only with no key or secret embedded:

The prefills carry only the public endpoint URL. The setup pages check the live

protected-resource metadata, server card, release version, and required client

redirect profiles before showing a native install action. Until that gate

passes, use the API-key fallback from a trusted backend/client; never put a key

in an install link. Per-client config blocks are below.

What is Hive Intelligence?

A managed MCP server, REST API, and CLI that give AI agents one evidence-backed

workflow surface over live crypto market data, DeFi, wallets, token security,

DEX flows, NFTs, prediction markets, and on-chain network data. Agents receive

the provider, Hive retrieval time, Hive first-observation/original cache time,

cache age, fallback state, runtime status, and a unique receipt for every

material execution instead of silently mixing provider data.

Connect to your AI client

The hosted endpoint is the same everywhere. After OAuth activation,

interactive clients should start with URL-only OAuth discovery. API-key auth

remains the explicit headless fallback.

Claude Code

claude mcp add --transport http --scope user hive https://mcp.hiveintelligence.xyz/mcp

Or install the full plugin bundle (the hosted MCP connection plus 17 crypto

workflow skills) from this repository's plugin marketplace:

claude plugin marketplace add hive-intel/hive-sdk
claude plugin install hive@hive

Cursor

`~/.cursor/mcp.json` (global) or `.cursor/mcp.json` (project):

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

VS Code (GitHub Copilot Chat)

`.vscode/mcp.json` (note the required `type: "http"`):

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

Claude Desktop

Claude Desktop uses the Custom Connectors UI for remote MCP. Open Settings →

Connectors → Add custom connector, set the URL to

`https://mcp.hiveintelligence.xyz/mcp`, then, after OAuth activation, complete

browser authorization. Do not paste a remote `url` block into

`claude_desktop_config.json`; that file is for local stdio servers.

Windsurf / Devin Desktop

Windsurf uses `serverUrl` (not Cursor's `url`) in

`~/.codeium/windsurf/mcp_config.json`:

{
  "mcpServers": {
    "hive": {
      "serverUrl": "https://mcp.hiveintelligence.xyz/mcp"
    }
  }
}

Gemini CLI

Gemini CLI requires `httpUrl` in `~/.gemini/settings.json`:

{
  "mcpServers": {
    "hive": {
      "httpUrl": "https://mcp.hiveintelligence.xyz/mcp"
    }
  }
}

Both configs are URL-only and can use native OAuth after hosted OAuth

activation. Full per-client guides:

hiveintelligence.xyz/install.

Headless API-key fallback

For automation that cannot open a browser, keep a Hive API key in secret

storage and send `Authorization: Bearer $HIVE_API_KEY`. Never embed a real key

in an install link, shared config, screenshot, or repository.

Local stdio (self-host / desktop / your own provider keys)

Prefer a local process or your own upstream keys? Run the published CLI as a stdio MCP server:

{
  "mcpServers": {
    "hive": {
      "command": "npx",
      "args": ["-y", "-p", "hive-intelligence@latest", "hive"],
      "env": {
        "COINGECKO_DEMO_API_KEY": "optional",
        "ALCHEMY_API_KEY": "optional",
        "HELIUS_API_KEY": "optional",
        "MORALIS_API_KEY": "optional"
      }
    }
  }
}

Local stdio does not use a hosted `HIVE_API_KEY`; configure only the upstream

provider keys you want that local process to call. Keyless providers remain

available and providers without credentials stay discoverable with a classified

`missing_key` runtime status. `hive-intelligence` is a stdio transport (a

JSON-RPC channel, not an interactive command). For terminal use, see the

CLI.

Authentication

• No key needed to start: the hosted endpoint's anonymous lane answers 25 material calls per IP per day, and discovery/schema/validation calls are always free.
• Get a key at hiveintelligence.xyz/dashboard/keys when you want your own quota; the Free plan needs no card.
• Authenticate the hosted endpoint with `Authorization: Bearer hive_live_...` (legacy alias `x-api-key` also works).
• One key, least privilege: keys are scoped to your plan's rate limit and credits. Rotate or revoke from the dashboard; never commit a key or paste it into client-side code.

Powered by

Ten upstream provider integrations plus Open Data Fetch, normalized into one tool surface:

Alchemy · CoinGecko · DeFiLlama · Moralis · Codex · GoPlus · Helius · Tenderly · CCXT · Hyperliquid · Open Data Fetch

Tools & discovery

Hive's default contract is a compact eight-tool root: three hero tools for the

dominant intents, plus a five-tool discovery/execution loop over the full

catalog.

Agents start with compact,

paginated `search_tools` results, load one exact `hive://toolsets/{id}` workflow,

inspect `get_api_endpoint_schema`, then call `invoke_api_endpoint` for reads or

`invoke_stateful_endpoint` after explicit approval for a Hive-native state

change. `validate_task_result` checks the final envelope and receipt structure;

it requires claim-to-receipt citations and canonical phase coverage, but cannot

make invented receipt data authentic.

The long-tail catalog remains discoverable behind that workflow surface: 607

callable tools across 10 categories.

Every exact workflow publishes a default and maximum material-call budget,

phases, fallback condition, and stop conditions. Agents stop once the requested

decision is supported and call a fallback only to resolve a material gap,

unavailable source, staleness concern, or disagreement.

Clients that want a smaller, scoped tool surface can connect to a category endpoint directly, e.g. `https://mcp.hiveintelligence.xyz/hive_market_data/mcp` (one per category). Public catalog overview: www.hiveintelligence.xyz/tools/live-catalog. Authenticated REST catalog: `https://mcp.hiveintelligence.xyz/api/v1/tools`.

Security & trust

Crypto answers are only useful if they're trustworthy. Hive is built for that:

• Provenance on every response. Tool results carry a server-minted receipt with provider, Hive retrieval/observation time, cache age, source state, runtime status, server/build version, and SHA-256 input/result self-checks. The digests are not signatures or a retained lookup service. `observed_at` is Hive's first-observation/original cache time, not necessarily the upstream event time; `cache_age_ms: 0` only means newly retrieved by Hive. `source` reports the delivery state, while `origin_source` preserves whether cached data originally came from the live or fallback tier. Use provider timestamps, blocks, slots, transactions, or candle closes for source recency, and mark it unknown when absent. Hive never silently mixes provider data: fallback, cached, or degraded data is labeled as such.
• Point-in-time, not drift. Time-series tools accept `at` / `block_number` so agents answer historical questions without quietly defaulting to "latest."
• Security-first tools. `get_token_security`, `detect_rugpull`, approval-risk, and Tenderly transaction simulation return structured risk flags so an agent can check _before_ a user signs.
• Least privilege & prompt-injection awareness. Use a scoped key per environment and rotate from the dashboard. As with any tool-using agent, treat on-chain text (token names, memos) as untrusted input. Hive returns structured fields rather than free-form instructions to reduce injection surface.
• No client-side keys. Keep your Hive key server-side; browser UIs should call your own backend, which uses the key (see the SDK B2B subject sessions).

Example prompts

Once Hive is connected, ask in plain English. Each prompt maps to a real tool call you don't have to write:

What's the price of BTC, ETH, and SOL right now in USD?
List the top 20 yield pools above 10% APY on Ethereum.
Show me the portfolio of vitalik.eth across all chains.
Is this token a honeypot? 0x...   ·   Run a rugpull check on $PEPE.
What are the current funding rates for BTC perps across exchanges?
What are the most-traded events on Polymarket this week?
Simulate this transaction before I sign it:

More workflow guides: hiveintelligence.xyz/use-cases.

TypeScript SDK: `hive-mcp-client`

Call Hive from your own agent or backend without wiring MCP by hand. The typed client ships on npm and in `client/`:

npm install hive-mcp-client

import { createHiveMcpClient, invokeHiveEndpoint } from "hive-mcp-client";

const hive = await createHiveMcpClient({
  apiKey: process.env.HIVE_API_KEY,
  clientName: "my-app",
});

const result = await invokeHiveEndpoint(hive, "get_price", {
  ids: "bitcoin",
  vs_currencies: "usd",
});
console.log(result.json ?? result.text);
await hive.close();

`invokeHiveEndpoint` is intentionally read-only and already returns a

normalized result. It rejects known Hive state-changing endpoints. After your

application shows the exact effect and receives explicit user approval, call

the separately named `invokeHiveStatefulEndpoint`; never derive approval from

model output or tool arguments:

import { invokeHiveStatefulEndpoint } from "hive-mcp-client";

if (!(await approvalUi.confirm({ endpointName, args }))) {
  throw new Error("User declined the Hive state change");
}

const saved = await invokeHiveStatefulEndpoint(hive, endpointName, args);

Use `normalizeHiveToolResult` only when you call the lower-level

`client.callTool()` method directly.

Includes Vercel AI SDK and LangChain adapters, plus B2B subject sessions for

multi-tenant backends. LangChain stateful tools are disabled unless the app

supplies `approveStatefulCall({ endpointName, args })`; the callback must return

the user's explicit approval, and material stateful invocations are never

adapter-cached. Full API: `client/README.md`.

Agent skills

Installable agent skills teach Claude Code, Cursor, Codex, and other agents the Hive workflow: MCP setup, tool discovery, and live crypto research:

npx skills add hive-intel/hive-skills

Claude Code, OpenAI / Codex, and Cursor plugin bundle

This repository root is also a distribution-ready plugin bundle. It combines

public, reviewable pieces:

• `.claude-plugin/`: Claude Code plugin and marketplace

manifests over the same MCP connection and workflow skills

(`claude plugin marketplace add hive-intel/hive-sdk`).

• `.codex-plugin/plugin.json`: product and

interface metadata, starter prompts, and component declarations.

• `.cursor-plugin/plugin.json`: the

Cursor-native manifest over the same MCP connection and workflow skills.

• `.mcp.json`: the URL-only hosted Hive connection. It contains

no API key, token, header, or credential placeholder.

• `skills/`: bundled setup, discovery, and crypto-research

workflows that teach the agent to inspect schemas, stay within workflow call

budgets, preserve provenance, and require explicit approval before a

Hive-native state change.

• `marketplace-review.json`: release-bound listing

copy, starter prompts, and the exact five positive plus three negative review

cases. It is a public preparation fixture, not a Cursor or OpenAI manifest;

reviewer credentials, domain challenges, availability choices, and legal

attestations remain portal-only.

A Codex catalog or Cursor plugin review can ingest the repository root so the

remote MCP connection and its workflow guidance arrive together. This bundle

does not claim that Hive is already listed in either public marketplace; use the current

Hive install guide until a catalog

listing is live.

CLI

The `hive` CLI is a thin terminal client over the same API. Set `HIVE_API_KEY` (or run `hive auth login` once):

hive market price --ids bitcoin,ethereum,solana --vs usd   # prices
hive defi tvl --protocol aave                              # DeFi TVL
hive security scan --token 0x...                           # token security
hive portfolio balance --address 0x...                     # wallet portfolio
hive tools search "funding rate"                           # search the 607-tool catalog
hive tools call get_price --args '{"ids":"bitcoin","vs_currencies":"usd"}'

Global flags include `--json`, `--pretty`, `--jq `, `--csv`, `--fields`, `--timeout`, `-q/--quiet`. Auth: `hive auth login | whoami | profiles | switch`. Diagnostics: `hive doctor`, `hive status`. Shell completion: `hive completion --install`. Aliases: `hive alias set btc 'market price --ids bitcoin --vs usd'`. Full reference: hiveintelligence.xyz/cli.

Configuration

Pricing

One credit = one material endpoint execution, regardless of provider or response size. `search_tools`, `get_api_endpoint_schema`, `validate_task_result`, MCP `tools/list`, MCP resource reads, and authenticated `GET /api/v1/tools` are free. Full pricing: hiveintelligence.xyz/pricing · machine-readable: hiveintelligence.xyz/pricing.md.

Why Hive over a single-provider MCP?

Single-provider MCPs win on niche depth. Hive wins when the agent needs broad crypto context in one request: prices + DeFi + wallet + security + DEX in a single conversation, without anyone figuring out which tool lives in which provider.

FAQ

What does an API key cost?

Nothing to start: the anonymous lane needs no key at all (25 material calls per IP per day), and the Free plan adds 10,000 monthly credits with no card required. Paid plans start at $49/month (Starter, 100K credits); Pro is $149/month for 500K. Get a key.

Hosted vs local stdio: which should I use?

Hosted (`https://mcp.hiveintelligence.xyz/mcp`) is recommended for most integrations: no local server, Hive runs auth, rate limits, and provider infrastructure. Use local stdio for desktop setups, self-hosting, or your own upstream provider keys.

Which AI clients support MCP?

Claude Desktop, Claude Code, Cursor, Windsurf, VS Code (Copilot Chat), Codex CLI, Gemini CLI, OpenAI Responses API, and clients that support Streamable HTTP MCP. Native OAuth connectors become available after hosted OAuth activation; API-key headers remain the trusted headless fallback.

What chains are supported?

EVM (Ethereum, Arbitrum, Optimism, Base, Polygon, BNB Chain, Avalanche, and 90+ more), Solana with full Helius DAS coverage including compressed NFTs, Bitcoin, and others depending on the provider mix per category.

Is the source code open?

The typed client SDK (`client/`) and the Hive agent skills are MIT-licensed and open source. The Hive MCP server that powers `mcp.hiveintelligence.xyz` is a managed, proprietary service.

How does Hive keep answers trustworthy?

Every material result carries provider attribution, source/cache state, runtime status, and a server-minted receipt. Hive separates its own observation time from provider source recency, never silently mixes provider data, and exposes point-in-time parameters where providers support them. See Security & trust.

Documentation

• Quick Start: hiveintelligence.xyz/quick-start
• API Reference: hiveintelligence.xyz/api-integration
• Install Guides: hiveintelligence.xyz/install
• CLI Reference: hiveintelligence.xyz/cli
• Tool Catalog: hiveintelligence.xyz/tools/live-catalog
• Agent Skills: github.com/hive-intel/hive-skills

Support

• GitHub Issues: github.com/hive-intel/hive-sdk/issues
• Email: support@hiveintelligence.xyz
• Telegram: t.me/HiveIntelligence
• Twitter / X: @Hive_Intel

License

MIT © Hive Intelligence