{"_id":"@arenza/mcp-client","_rev":"2-48d5e41afbf77f43fcfaece15ee62bce","name":"@arenza/mcp-client","dist-tags":{"latest":"0.1.0"},"versions":{"0.1.0":{"name":"@arenza/mcp-client","version":"0.1.0","keywords":["arenza","geo","generative-engine-optimization","ai-visibility","ai-search","llm-seo","brand-mention-tracking","mcp","model-context-protocol","chatgpt","claude","gemini","perplexity","copilot","grok"],"author":{"url":"https://arenza.ai","name":"Arenza","email":"hello@arenza.ai"},"license":"MIT","_id":"@arenza/mcp-client@0.1.0","maintainers":[{"name":"fooly_cooly","email":"naiqiao@hotmail.com"}],"homepage":"https://arenza.ai","bugs":{"url":"https://github.com/arenza-ai/arenza-mcp-client-ts/issues"},"dist":{"shasum":"ca40454e219a37e741e20483d6c96ceea2d74460","tarball":"https://registry.npmjs.org/@arenza/mcp-client/-/mcp-client-0.1.0.tgz","fileCount":18,"integrity":"sha512-GFucZbAMSlfwCK+QSbI4JoEhRvEpkRiQxpXJoGbcJpn5bEAyuDxOMeXseYdvcLvAlXhwjRMW1G8SAGcUMnsVFA==","signatures":[{"sig":"MEUCIHlRgdHbiYMmRwoDCG8/ycrjykszz3IVRNt5Un0vFAKTAiEAv71VKuqQ3ulkrEH1U1kejZ00SDFJk0+ocYC4G8ZtZrI=","keyid":"SHA256:DhQ8wR5APBvFHLF/+Tc+AYvPOdTpcIDqOhxsBHRwC7U"}],"unpackedSize":33033},"main":"dist/index.js","types":"dist/index.d.ts","engines":{"node":">=18"},"gitHead":"70711391f697d6e086a007135c88bc97be9a98b6","scripts":{"build":"tsc","prepublishOnly":"npm run build"},"_npmUser":{"name":"fooly_cooly","email":"naiqiao@hotmail.com"},"repository":{"url":"git+https://github.com/arenza-ai/arenza-mcp-client-ts.git","type":"git"},"_npmVersion":"10.8.2","description":"TypeScript client for the Arenza MCP server — programmatic access to AI visibility metrics, brand mentions, and GEO opportunities across ChatGPT, Claude, Gemini, Perplexity, Copilot, and Grok.","directories":{},"_nodeVersion":"20.19.2","_hasShrinkwrap":false,"devDependencies":{"typescript":"^5.4.0","@types/node":"^20.0.0"},"_npmOperationalInternal":{"tmp":"tmp/mcp-client_0.1.0_1777999047616_0.3927645997778477","host":"s3://npm-registry-packages-npm-production"}}},"time":{"created":"2026-05-05T16:37:27.528Z","modified":"2026-05-07T02:26:03.373Z","0.1.0":"2026-05-05T16:37:27.735Z"},"bugs":{"url":"https://github.com/arenza-ai/arenza-mcp-client-ts/issues"},"author":{"url":"https://arenza.ai","name":"Arenza","email":"hello@arenza.ai"},"license":"MIT","homepage":"https://arenza.ai","keywords":["arenza","geo","generative-engine-optimization","ai-visibility","ai-search","llm-seo","brand-mention-tracking","mcp","model-context-protocol","chatgpt","claude","gemini","perplexity","copilot","grok"],"repository":{"url":"git+https://github.com/arenza-ai/arenza-mcp-client-ts.git","type":"git"},"description":"TypeScript client for the Arenza MCP server — programmatic access to AI visibility metrics, brand mentions, and GEO opportunities across ChatGPT, Claude, Gemini, Perplexity, Copilot, and Grok.","maintainers":[{"email":"naiqiao@hotmail.com","name":"fooly_cooly"},{"email":"quexiaoyu1016@gmail.com","name":"xiaoyuque"}],"readme":"# arenza-mcp-client\n\n> TypeScript client for the **Arenza MCP server** — programmatic access to AI visibility metrics, brand mentions, hallucination findings, and GEO opportunities across ChatGPT, Claude, Gemini, Perplexity, Copilot, and Grok.\n\n[Arenza](https://arenza.ai) is a Generative Engine Optimization (GEO) platform that measures how 6 leading AI assistants describe brands across 4 markets (US, UK, DE, JP). This client wraps the [Model Context Protocol](https://modelcontextprotocol.io) server at `mcp.arenza.ai`, giving you typed access to the same data the Arenza dashboard renders.\n\n## Why an MCP client (not just a REST SDK)\n\nThe Arenza data surface ships as both a REST API (`api.arenza.ai`) and an MCP server (`mcp.arenza.ai`). The MCP variant is what AI agents — Claude Desktop, Claude Code, Cursor, Continue, and any custom agent built on the MCP protocol — connect to natively. This client lets you embed the same connection inside a TypeScript backend, automation, or chatbot.\n\nIf you want to use Arenza from Claude Desktop directly (no code), see [Use Claude with the Arenza MCP server](https://arenza.ai/guides/use-claude-with-arenza-mcp-server) instead.\n\n## Install\n\n```bash\nnpm install @arenza/mcp-client\n# or\npnpm add @arenza/mcp-client\n# or\nyarn add @arenza/mcp-client\n```\n\n## Quick start\n\n```ts\nimport { ArenzaMCPClient } from '@arenza/mcp-client';\n\nconst client = new ArenzaMCPClient({\n  // Get a token at https://app.arenza.ai/settings/api or use OAuth flow.\n  token: process.env.ARENZA_TOKEN!,\n});\n\n// 10 read+write tools available — see tools list below.\nconst brands = await client.listBrands();\nconsole.log(brands);\n\nconst overview = await client.getBrandOverview({ brand_id: brands[0].id });\nconsole.log(overview.share_of_voice, overview.wrong_claims);\n```\n\n## Tools\n\nThe Arenza MCP server exposes 10 tools:\n\n### Read\n\n| Tool | Description |\n|---|---|\n| `list_brands` | List all brands in the authenticated tenant's portfolio. |\n| `get_brand_overview` | Aggregate visibility + accuracy snapshot for one brand. |\n| `list_prompts` | List the AI prompts probed for a brand, with mention rates per LLM. |\n| `list_opportunities` | List measurement-led GEO opportunities (wrong claims to fix, missing canonical pages, listicle gaps). |\n| `suggest_competitors` | LLM-suggested competitors based on the brand description. |\n| `suggest_prompts` | LLM-generated buyer-perspective prompts (70%+ unbranded ratio enforced). |\n\n### Write\n\n| Tool | Description |\n|---|---|\n| `add_competitor` | Add a competitor to a brand's tracking list. |\n| `dismiss_competitor` | Remove a competitor (e.g. wrong suggestion). |\n| `mark_opportunity_done` | Mark a GEO opportunity as completed. |\n| `generate_geo_article` | Draft a canonical-fact article body anchored to a specific finding. |\n\nEach tool is fully typed in this client — TypeScript autocomplete shows parameter shapes and return types.\n\n## Authentication\n\nTwo options:\n\n**API token** (simplest for backend / cron jobs):\n```ts\nconst client = new ArenzaMCPClient({ token: process.env.ARENZA_TOKEN! });\n```\nGet one at [app.arenza.ai/settings/api](https://app.arenza.ai/settings/api).\n\n**OAuth** (for multi-tenant apps, AI agents, end-user authorization):\n```ts\nconst client = await ArenzaMCPClient.fromOAuth({\n  clientId: 'your-client-id',\n  redirectUri: 'https://yourapp.com/oauth/callback',\n});\n```\nThe Arenza MCP server supports OAuth 2.0 with Dynamic Client Registration (DCR) and PKCE — full spec at [`mcp.arenza.ai/.well-known/oauth-authorization-server`](https://mcp.arenza.ai/.well-known/oauth-authorization-server).\n\n## Example: weekly GEO digest cron\n\n```ts\nimport { ArenzaMCPClient } from '@arenza/mcp-client';\n\nasync function weeklyDigest() {\n  const client = new ArenzaMCPClient({ token: process.env.ARENZA_TOKEN! });\n  const brands = await client.listBrands();\n\n  for (const brand of brands) {\n    const ovw = await client.getBrandOverview({ brand_id: brand.id });\n    const opps = await client.listOpportunities({ brand_id: brand.id });\n    console.log(\n      `${brand.name}: SoV ${ovw.share_of_voice}%, ${ovw.wrong_claims} wrong claims, ${opps.length} opportunities`,\n    );\n  }\n}\n\nweeklyDigest();\n```\n\n## Rate limits\n\n- Free tier: 100 MCP calls/hour\n- Pro tier ($299/mo): 1,000 calls/hour\n- Protect tier ($799/mo): 10,000 calls/hour\n- Enterprise: unlimited\n\nCurrent limits are returned in `X-RateLimit-Remaining` headers. The client does not auto-retry on 429 — retry yourself with backoff.\n\n## Related projects\n\n- [`@arenza/cli`](https://github.com/arenza-ai/arenza-cli) — `npx arenza scan brand.com` for one-off scans.\n- [`arenza-mcp-client-python`](https://github.com/arenza-ai/arenza-mcp-client-python) — Python equivalent of this client.\n- [`@arenza/langchain`](https://github.com/arenza-ai/arenza-langchain) — wrap Arenza tools as LangChain tools.\n- [`@arenza/llamaindex`](https://github.com/arenza-ai/arenza-llamaindex) — same for LlamaIndex.\n- [`@arenza/vercel-ai-sdk`](https://github.com/arenza-ai/arenza-vercel-ai-sdk) — Vercel AI SDK provider.\n- [awesome-geo](https://github.com/arenza-ai/awesome-geo) — broader curated GEO resources list.\n\n## Resources\n\n- Arenza homepage: https://arenza.ai\n- API contract: https://app.arenza.ai/methodology\n- Long-form guides: https://arenza.ai/guides\n- Brand reference for AI assistants: https://arenza.ai/llms.txt + https://arenza.ai/llms-full.txt\n- MCP server: https://mcp.arenza.ai\n- OAuth spec: https://mcp.arenza.ai/.well-known/oauth-authorization-server\n\n## License\n\nMIT © Arenza\n","readmeFilename":"README.md"}