{
"markdown": "\n\n# Hive Intelligence\n\n**One connection for evidence-backed crypto due diligence.**\n\nEvery Hive-backed answer carries sources, freshness, and a runtime receipt. The\nhosted MCP normalizes market, wallet, DeFi, security, DEX, NFT, network, and\nprediction-market evidence behind one agent-ready connection.\n\n[](https://modelcontextprotocol.io)\n[](LICENSE)\n[](https://hiveintelligence.xyz)\n[](https://www.hiveintelligence.xyz/install/cursor)\n[](https://www.hiveintelligence.xyz/install/vs-code)\n\n[**Connect**](#connect) · [**Tools**](#tools--discovery) · [**Security**](#security--trust) · [**SDK**](#typescript-sdk--hive-mcp-client) · [**CLI**](#cli) · [**Pricing**](#pricing) · [**FAQ**](#faq) · [**Get an API key**](https://hiveintelligence.xyz/dashboard/keys)\n\n
\n\n> **Try it now, with no account and no key.** The hosted endpoint's anonymous lane\n> answers 25 material calls per IP per day; discovery, schema lookup, and\n> validation are always free:\n>\n> ```text\n> https://mcp.hiveintelligence.xyz/mcp\n> ```\n>\n> [Guided setup](https://www.hiveintelligence.xyz/setup) · [Install guides](https://www.hiveintelligence.xyz/install) · [Example prompts](#example-prompts)\n\n---\n\n## Connect\n\nHive is a **hosted MCP server** for clients that support remote Streamable HTTP.\nOnce the hosted OAuth deployment is enabled, interactive clients discover it\nfrom the public endpoint and open browser authorization. Headless agents can\nuse an API key from secret storage:\n\n```text\nhttps://mcp.hiveintelligence.xyz/mcp\n```\n\nOne-click config prefills, URL-only with no key or secret embedded:\n\n[](https://cursor.com/en/install-mcp?name=hive&config=eyJ1cmwiOiJodHRwczovL21jcC5oaXZlaW50ZWxsaWdlbmNlLnh5ei9tY3AifQ==)\n[](vscode:mcp/install?%7B%22name%22%3A%22hive%22%2C%22type%22%3A%22http%22%2C%22url%22%3A%22https%3A%2F%2Fmcp.hiveintelligence.xyz%2Fmcp%22%7D)\n[](https://www.hiveintelligence.xyz/install/cursor)\n[](https://www.hiveintelligence.xyz/install/vs-code)\n\nThe prefills carry only the public endpoint URL. The setup pages check the live\nprotected-resource metadata, server card, release version, and required client\nredirect profiles before showing a native install action. Until that gate\npasses, use the API-key fallback from a trusted backend/client; never put a key\nin an install link. Per-client config blocks are below.\n\n## What is Hive Intelligence?\n\nA managed MCP server, REST API, and CLI that give AI agents one evidence-backed\nworkflow surface over live crypto market data, DeFi, wallets, token security,\nDEX flows, NFTs, prediction markets, and on-chain network data. Agents receive\nthe provider, Hive retrieval time, Hive first-observation/original cache time,\ncache age, fallback state, runtime status, and a unique receipt for every\nmaterial execution instead of silently mixing provider data.\n\n## Connect to your AI client\n\nThe hosted endpoint is the same everywhere. After OAuth activation,\ninteractive clients should start with URL-only OAuth discovery. API-key auth\nremains the explicit headless fallback.\n\n### Claude Code\n\n```bash\nclaude mcp add --transport http --scope user hive https://mcp.hiveintelligence.xyz/mcp\n```\n\nOr install the full plugin bundle (the hosted MCP connection plus 17 crypto\nworkflow skills) from this repository's plugin marketplace:\n\n```bash\nclaude plugin marketplace add hive-intel/hive-sdk\nclaude plugin install hive@hive\n```\n\n### Cursor\n\n`~/.cursor/mcp.json` (global) or `.cursor/mcp.json` (project):\n\n```json\n{\n \"mcpServers\": {\n \"hive\": {\n \"url\": \"https://mcp.hiveintelligence.xyz/mcp\"\n }\n }\n}\n```\n\n### VS Code (GitHub Copilot Chat)\n\n`.vscode/mcp.json` (note the required `type: \"http\"`):\n\n```json\n{\n \"servers\": {\n \"hive\": {\n \"type\": \"http\",\n \"url\": \"https://mcp.hiveintelligence.xyz/mcp\"\n }\n }\n}\n```\n\n### Claude Desktop\n\nClaude Desktop uses the Custom Connectors UI for remote MCP. Open Settings →\nConnectors → Add custom connector, set the URL to\n`https://mcp.hiveintelligence.xyz/mcp`, then, after OAuth activation, complete\nbrowser authorization. Do not paste a remote `url` block into\n`claude_desktop_config.json`; that file is for local stdio servers.\n\n### Windsurf / Devin Desktop\n\nWindsurf uses `serverUrl` (not Cursor's `url`) in\n`~/.codeium/windsurf/mcp_config.json`:\n\n```json\n{\n \"mcpServers\": {\n \"hive\": {\n \"serverUrl\": \"https://mcp.hiveintelligence.xyz/mcp\"\n }\n }\n}\n```\n\n### Gemini CLI\n\nGemini CLI requires `httpUrl` in `~/.gemini/settings.json`:\n\n```json\n{\n \"mcpServers\": {\n \"hive\": {\n \"httpUrl\": \"https://mcp.hiveintelligence.xyz/mcp\"\n }\n }\n}\n```\n\nBoth configs are URL-only and can use native OAuth after hosted OAuth\nactivation. Full per-client guides:\n[hiveintelligence.xyz/install](https://hiveintelligence.xyz/install).\n\n### Headless API-key fallback\n\nFor automation that cannot open a browser, keep a Hive API key in secret\nstorage and send `Authorization: Bearer $HIVE_API_KEY`. Never embed a real key\nin an install link, shared config, screenshot, or repository.\n\n### Local stdio (self-host / desktop / your own provider keys)\n\nPrefer a local process or your own upstream keys? Run the published CLI as a stdio MCP server:\n\n```json\n{\n \"mcpServers\": {\n \"hive\": {\n \"command\": \"npx\",\n \"args\": [\"-y\", \"-p\", \"hive-intelligence@latest\", \"hive\"],\n \"env\": {\n \"COINGECKO_DEMO_API_KEY\": \"optional\",\n \"ALCHEMY_API_KEY\": \"optional\",\n \"HELIUS_API_KEY\": \"optional\",\n \"MORALIS_API_KEY\": \"optional\"\n }\n }\n }\n}\n```\n\nLocal stdio does not use a hosted `HIVE_API_KEY`; configure only the upstream\nprovider keys you want that local process to call. Keyless providers remain\navailable and providers without credentials stay discoverable with a classified\n`missing_key` runtime status. `hive-intelligence` is a stdio transport (a\nJSON-RPC channel, not an interactive command). For terminal use, see the\n[CLI](#cli).\n\n## Authentication\n\n- 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.\n- Get a key at [hiveintelligence.xyz/dashboard/keys](https://hiveintelligence.xyz/dashboard/keys) when you want your own quota; the Free plan needs no card.\n- Authenticate the hosted endpoint with `Authorization: Bearer hive_live_...` (legacy alias `x-api-key` also works).\n- 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.\n\n## Powered by\n\nTen upstream provider integrations plus Open Data Fetch, normalized into one tool surface:\n\n```\nAlchemy · CoinGecko · DeFiLlama · Moralis · Codex · GoPlus · Helius · Tenderly · CCXT · Hyperliquid · Open Data Fetch\n```\n\n| Provider | Coverage |\n| ---------------------- | ------------------------------------------------------------------------------------------------------------ |\n| **Alchemy** | EVM portfolio, token, NFT, transfer, simulation, gas, network data, and Solana DAS |\n| **CoinGecko** | Market data, prices, OHLCV, exchanges, NFT collections |\n| **DeFiLlama** | TVL, yield pools, protocol metrics, bridges, treasuries |\n| **Moralis** | EVM and Solana wallet, token, NFT, DeFi, transfer, and market analytics |\n| **Codex** (Defined.fi) | DEX pair OHLCV, prediction markets (Polymarket) |\n| **GoPlus** | Token security, honeypot detection, contract risk, malicious-address reputation |\n| **Helius** | Solana RPC, DAS, compressed NFTs, priority fees |\n| **Tenderly** | EVM simulation, gas estimation, traces, contract decode, signatures, storage changes, and transaction ranges |\n| **CCXT** | Centralized exchange data, order books, derivatives, funding, leverage, and borrow rates |\n| **Hyperliquid** | Native perpetual DEX volume, funding, candles, open-interest caps, and builder DEXs |\n| **Open Data Fetch** | Allowlisted, size-capped access to long-tail public crypto APIs when no typed tool covers the source |\n\n## Tools & discovery\n\nHive's default contract is a compact eight-tool root: three hero tools for the\ndominant intents, plus a five-tool discovery/execution loop over the full\ncatalog.\n\n| Root tool | What it does |\n| --- | --- |\n| `get_token_price` | Hero: live price for any token (`response_format`: concise or detailed) |\n| `check_token_safety` | Hero: honeypot, rugpull, and contract-risk verdict before anyone signs |\n| `get_wallet_portfolio` | Hero: multi-chain wallet balances and portfolio value |\n| `search_tools` | Find the right task toolset and route across the full catalog (free) |\n| `get_api_endpoint_schema` | Inspect exact parameters before executing (free) |\n| `invoke_api_endpoint` | Execute any read endpoint in the catalog |\n| `invoke_stateful_endpoint` | Hive-native state changes; requires explicit user approval |\n| `validate_task_result` | Check the final envelope and receipt structure (free) |\n\nAgents start with compact,\npaginated `search_tools` results, load one exact `hive://toolsets/{id}` workflow,\ninspect `get_api_endpoint_schema`, then call `invoke_api_endpoint` for reads or\n`invoke_stateful_endpoint` after explicit approval for a Hive-native state\nchange. `validate_task_result` checks the final envelope and receipt structure;\nit requires claim-to-receipt citations and canonical phase coverage, but cannot\nmake invented receipt data authentic.\n\nThe long-tail catalog remains discoverable behind that workflow surface: 607\ncallable tools across 10 categories.\n\nEvery exact workflow publishes a default and maximum material-call budget,\nphases, fallback condition, and stop conditions. Agents stop once the requested\ndecision is supported and call a fallback only to resolve a material gap,\nunavailable source, staleness concern, or disagreement.\n\n| # | Category | Tools | What's inside |\n| --- | ---------------------------- | ----- | ----------------------------------------------------------------------------------------------------- |\n| 1 | **Market Data & Price** | 106 | Prices, OHLCV, market caps, derivatives, funding rates, stablecoins, gainers/losers, exchange tickers |\n| 2 | **On-Chain DEX & Pool** | 64 | DEX pools, liquidity, trending pairs, swap history, bridges, aggregator volumes |\n| 3 | **Portfolio & Wallet** | 77 | Balances, PnL, DeFi positions, swap history, NFT holdings, multi-chain history |\n| 4 | **Token & Contract** | 50 | Token metadata, holders, top traders, ENS resolution, treasury tracking, transfers |\n| 5 | **DeFi Protocol** | 18 | TVL, fees, yield farming, chain metrics, treasuries, emissions |\n| 6 | **NFT Analytics** | 67 | Collection data, floors, market charts, NFT pools, trait metadata, sales |\n| 7 | **Security & Risk** | 51 | Honeypot detection, rugpull checks, approval risk, Tenderly simulation, gas estimation |\n| 8 | **Network & Infrastructure** | 40 | Chain health, blocks, gas prices, supported networks, Solana infrastructure |\n| 9 | **Search & Discovery** | 25 | Cross-provider search, trending coins, categories, token discovery |\n| 10 | **Prediction Markets** | 21 | Events, markets, prices, trades, traders, holdings, order books, and category filters |\n\nClients 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](https://www.hiveintelligence.xyz/tools/live-catalog). Authenticated REST catalog: `https://mcp.hiveintelligence.xyz/api/v1/tools`.\n\n## Security & trust\n\nCrypto answers are only useful if they're trustworthy. Hive is built for that:\n\n- **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.\n- **Point-in-time, not drift.** Time-series tools accept `at` / `block_number` so agents answer historical questions without quietly defaulting to \"latest.\"\n- **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.\n- **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.\n- **No client-side keys.** Keep your Hive key server-side; browser UIs should call your own backend, which uses the key (see the [SDK](#typescript-sdk--hive-mcp-client) B2B subject sessions).\n\n## Example prompts\n\nOnce Hive is connected, ask in plain English. Each prompt maps to a real tool call you don't have to write:\n\n```\nWhat's the price of BTC, ETH, and SOL right now in USD?\nList the top 20 yield pools above 10% APY on Ethereum.\nShow me the portfolio of vitalik.eth across all chains.\nIs this token a honeypot? 0x... · Run a rugpull check on $PEPE.\nWhat are the current funding rates for BTC perps across exchanges?\nWhat are the most-traded events on Polymarket this week?\nSimulate this transaction before I sign it: \n```\n\nMore workflow guides: [hiveintelligence.xyz/use-cases](https://hiveintelligence.xyz/use-cases).\n\n## TypeScript SDK: `hive-mcp-client`\n\nCall Hive from your own agent or backend without wiring MCP by hand. The typed client ships on npm and in [`client/`](./client):\n\n```bash\nnpm install hive-mcp-client\n```\n\n```ts\nimport { createHiveMcpClient, invokeHiveEndpoint } from \"hive-mcp-client\";\n\nconst hive = await createHiveMcpClient({\n apiKey: process.env.HIVE_API_KEY,\n clientName: \"my-app\",\n});\n\nconst result = await invokeHiveEndpoint(hive, \"get_price\", {\n ids: \"bitcoin\",\n vs_currencies: \"usd\",\n});\nconsole.log(result.json ?? result.text);\nawait hive.close();\n```\n\n`invokeHiveEndpoint` is intentionally read-only and already returns a\nnormalized result. It rejects known Hive state-changing endpoints. After your\napplication shows the exact effect and receives explicit user approval, call\nthe separately named `invokeHiveStatefulEndpoint`; never derive approval from\nmodel output or tool arguments:\n\n```ts\nimport { invokeHiveStatefulEndpoint } from \"hive-mcp-client\";\n\nif (!(await approvalUi.confirm({ endpointName, args }))) {\n throw new Error(\"User declined the Hive state change\");\n}\n\nconst saved = await invokeHiveStatefulEndpoint(hive, endpointName, args);\n```\n\nUse `normalizeHiveToolResult` only when you call the lower-level\n`client.callTool()` method directly.\n\nIncludes Vercel AI SDK and LangChain adapters, plus B2B subject sessions for\nmulti-tenant backends. LangChain stateful tools are disabled unless the app\nsupplies `approveStatefulCall({ endpointName, args })`; the callback must return\nthe user's explicit approval, and material stateful invocations are never\nadapter-cached. Full API: [`client/README.md`](./client/README.md).\n\n## Agent skills\n\nInstallable [agent skills](https://github.com/hive-intel/hive-skills) teach Claude Code, Cursor, Codex, and other agents the Hive workflow: MCP setup, tool discovery, and live crypto research:\n\n```bash\nnpx skills add hive-intel/hive-skills\n```\n\n### Claude Code, OpenAI / Codex, and Cursor plugin bundle\n\nThis repository root is also a distribution-ready plugin bundle. It combines\npublic, reviewable pieces:\n\n- [`.claude-plugin/`](./.claude-plugin): Claude Code plugin and marketplace\n manifests over the same MCP connection and workflow skills\n (`claude plugin marketplace add hive-intel/hive-sdk`).\n- [`.codex-plugin/plugin.json`](./.codex-plugin/plugin.json): product and\n interface metadata, starter prompts, and component declarations.\n- [`.cursor-plugin/plugin.json`](./.cursor-plugin/plugin.json): the\n Cursor-native manifest over the same MCP connection and workflow skills.\n- [`.mcp.json`](./.mcp.json): the URL-only hosted Hive connection. It contains\n no API key, token, header, or credential placeholder.\n- [`skills/`](./skills): bundled setup, discovery, and crypto-research\n workflows that teach the agent to inspect schemas, stay within workflow call\n budgets, preserve provenance, and require explicit approval before a\n Hive-native state change.\n- [`marketplace-review.json`](./marketplace-review.json): release-bound listing\n copy, starter prompts, and the exact five positive plus three negative review\n cases. It is a public preparation fixture, not a Cursor or OpenAI manifest;\n reviewer credentials, domain challenges, availability choices, and legal\n attestations remain portal-only.\n\nA Codex catalog or Cursor plugin review can ingest the repository root so the\nremote MCP connection and its workflow guidance arrive together. This bundle\ndoes not claim that Hive is already listed in either public marketplace; use the current\n[Hive install guide](https://www.hiveintelligence.xyz/install) until a catalog\nlisting is live.\n\n## CLI\n\nThe `hive` CLI is a thin terminal client over the same API. Set `HIVE_API_KEY` (or run `hive auth login` once):\n\n```bash\nhive market price --ids bitcoin,ethereum,solana --vs usd # prices\nhive defi tvl --protocol aave # DeFi TVL\nhive security scan --token 0x... # token security\nhive portfolio balance --address 0x... # wallet portfolio\nhive tools search \"funding rate\" # search the 607-tool catalog\nhive tools call get_price --args '{\"ids\":\"bitcoin\",\"vs_currencies\":\"usd\"}'\n```\n\nGlobal 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](https://hiveintelligence.xyz/cli).\n\n## Configuration\n\n| Variable | Description |\n| ---------------------- | ------------------------------------------------------------- |\n| `HIVE_API_KEY` | **Required.** API key, or run `hive auth login` |\n| `HIVE_API_URL` | Custom base URL (default: `https://mcp.hiveintelligence.xyz`) |\n| `API_EXECUTE_ENDPOINT` | Override execute endpoint (advanced) |\n\n## Pricing\n\n| Plan | Monthly credits | Rate limit | API keys | Price |\n| -------------- | --------------- | -------------- | -------- | ------- |\n| **Free** | 10,000 | 100 req/min | 5 | Free |\n| **Starter** | 100,000 | 300 req/min | 5 | $49/mo |\n| **Pro** | 500,000 | 500 req/min | 10 | $149/mo |\n| **Enterprise** | Custom | Custom req/min | Custom | Custom |\n\nOne 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](https://hiveintelligence.xyz/pricing) · machine-readable: [hiveintelligence.xyz/pricing.md](https://hiveintelligence.xyz/pricing.md).\n\n## Why Hive over a single-provider MCP?\n\n| | Hive | CoinGecko MCP | Moralis MCP | DeFiLlama MCP | GoPlus only |\n| -------------------- | ------- | ------------- | ----------- | ------------- | ----------- |\n| Provider groups | **13** | 1 | 1 | 1 | 1 |\n| Categories | **10** | 2 | 3 | 1 | 1 |\n| Total tools | **607** | ~50 | ~60 | ~15 | ~20 |\n| Market data | ✓ | ✓ | partial | – | – |\n| DeFi TVL + yields | ✓ | – | – | ✓ | – |\n| Wallet portfolio | ✓ | – | ✓ | – | – |\n| Pre-signing security | **✓** | – | – | – | ✓ |\n| DEX pool analytics | ✓ | – | partial | – | – |\n| Prediction markets | **✓** | – | – | – | – |\n| Solana depth (DAS) | ✓ | – | – | – | – |\n| Managed (no ops) | ✓ | ✓ | partial | varies | varies |\n\nSingle-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.\n\n## FAQ\n\n**What does an API key cost?**\nNothing 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](https://hiveintelligence.xyz/dashboard/keys).\n\n**Hosted vs local stdio: which should I use?**\nHosted (`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.\n\n**Which AI clients support MCP?**\nClaude 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.\n\n**What chains are supported?**\nEVM (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.\n\n**Is the source code open?**\nThe typed client SDK (`client/`) and the [Hive agent skills](https://github.com/hive-intel/hive-skills) are MIT-licensed and open source. The Hive MCP server that powers `mcp.hiveintelligence.xyz` is a managed, proprietary service.\n\n**How does Hive keep answers trustworthy?**\nEvery 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](#security--trust).\n\n## Documentation\n\n- **Quick Start:** [hiveintelligence.xyz/quick-start](https://hiveintelligence.xyz/quick-start)\n- **API Reference:** [hiveintelligence.xyz/api-integration](https://hiveintelligence.xyz/api-integration)\n- **Install Guides:** [hiveintelligence.xyz/install](https://hiveintelligence.xyz/install)\n- **CLI Reference:** [hiveintelligence.xyz/cli](https://hiveintelligence.xyz/cli)\n- **Tool Catalog:** [hiveintelligence.xyz/tools/live-catalog](https://hiveintelligence.xyz/tools/live-catalog)\n- **Agent Skills:** [github.com/hive-intel/hive-skills](https://github.com/hive-intel/hive-skills)\n\n## Support\n\n- **GitHub Issues:** [github.com/hive-intel/hive-sdk/issues](https://github.com/hive-intel/hive-sdk/issues)\n- **Email:** [support@hiveintelligence.xyz](mailto:support@hiveintelligence.xyz)\n- **Telegram:** [t.me/HiveIntelligence](https://t.me/HiveIntelligence)\n- **Twitter / X:** [@Hive_Intel](https://x.com/Hive_Intel)\n\n## License\n\nMIT © Hive Intelligence\n",
"bytes": 26044,
"sha": "df05fcfce1b1b37ffda820b41a913fce927e4c11d3ed96a3bf3a585632e2a4cb",
"repo_slug": "hive-intel/hive-sdk",
"fonte": "repo",
"truncated": false,
"api": "https://agentalog.com/api/listings/plg_hive_intel_hive_sdk_bc2bf603/readme"
}