VS Code and GitHub Copilot
Open GitHub’s MCP Registry and pasang Analitik Web Hitsteps from your VS Code or GitHub Copilot client.
AI assistant integration
Hitsteps exposes a remote Model Context Protocol pelayan for connected AI assistants. Use it to ask about analitik, langsung pelawat, laman, matlamat, masa aktif, amaran, and authorized sembang activity from your Hitsteps akaun while keeping access bounded by OAuth scopes, akaun kebenaran, lesen checks, and privacy-shaped tool results.
Choose your AI client
Start with your client directory when one is available. Every pilihan connects to the same managed Hitsteps MCP pelayan and continues through Hitsteps OAuth.
Open GitHub’s MCP Registry and pasang Analitik Web Hitsteps from your VS Code or GitHub Copilot client.
Open the Analitik Web Hitsteps penyenaraian in Cursor Directory and choose Add to Cursor. Cursor receives only the managed Hitsteps MCP endpoint; your akaun access is granted separately through OAuth.
Add Analitik Web Hitsteps from Claude’s Connector Directory, then sign in to Hitsteps and approve only the scopes you want Claude to use.
The Hitsteps directory penyenaraian for ChatGPT is coming soon. For now, add the endpoint below manually as a custom MCP pelayan, then complete Hitsteps OAuth.
https://www.hitsteps.com/mcp/
Panduan pemasangan
The Hitsteps MCP endpoint is https://www.hitsteps.com/mcp/. If your client asks for a transport, choose Streamable HTTP or HTTP. The official registry name is com.hitsteps/analitik-operations.
Before connecting the pelayan, confirm which Hitsteps user will sign in, which laman web that user can access, and which OAuth scopes the AI client is requesting. Analitik-only use can stay read-only; operational aliran kerja need the specific write scopes described below.
Antigravity custom remote MCP configuration uses serverUrl for remote pelayan.
Save the configuration, start or segar semula the MCP pelayan in your AI client, then follow the sign-in prompt. Hitsteps uses OAuth so you do not need to paste your penjejakan API key into the AI client.
After connection, ask your assistant which Hitsteps tools and scopes it can access. Read-only analitik tools can answer laporan; management tools such as matlamat, Pencetus (called pelawat labels in MCP), masa aktif, amaran, and sembang tindakan require matching OAuth scopes, akaun kebenaran, and explicit confirmation.
Security and access
Use these butiran to connect Hitsteps and understand what the AI assistant can access from your akaun.
https://www.hitsteps.com/mcp/ is the production MCP endpoint. The slashless https://www.hitsteps.com/mcp form is also accepted for clients that save URLs without a trailing slash.
Hitsteps uses remote Streamable HTTP with JSON-RPC. There is no local Node.js package, komputer meja bridge, SSE worker, or separate pelanggan-hosted process to pasang.
The registry/pelayan name is com.hitsteps/analitik-operations and the displayed title is Analitik Hitsteps and Operations.
Public AI clients use Hitsteps OAuth with authorization code flow and S256 PKCE. Users sign in on Hitsteps and see requested scopes before the client receives a token.
The MCP configuration contains only the endpoint URL. Do not paste a Hitsteps password, penjejakan API key, laman web code, or OAuth token into an AI client configuration fail.
Every permintaan is rechecked against the signed-in Hitsteps akaun, sub-user kebenaran, visible laman web, lesen state, feature limits, and the OAuth scopes granted to that client.
Authorization
Hitsteps publishes per-tool OAuth declarations. An AI client can permintaan a narrow read-only grant or a broader operational grant depending on the aliran kerja you want.
analitik:readlaman:writematlamat:writelabels:writemasa aktif:writeamaran:readamaran:writesembang:readsembang:writeTool coverage
The MCP pelayan currently exposes 87 tools: 54 read tools and 33 confirmed write tools, plus authenticated resources, a resource templat, and prompts for common analitik aliran kerja.
Connection information, visible laman web, laman context, metric and dimension catalog, ringkasan laporan, gap-filled time series, breakdowns, anomaly detection, trafik-change explanations, executive digests, and privacy-minimal MCP usage.
Trafik ringkasan, period comparisons, sumber, social rujukan, trafik by hour, top halaman, masuk/keluar halaman, halaman butiran, halaman speed, muat turun, outbound pautan, perujuk, negara, audience technology, carian engines, kata kunci, Rujukan AI, bot trafik, and realtime pelawat.
Matlamat, matlamat penukaran, kempen, funnel performance, interaction peristiwa, agregat paths, retention, Pencetus (pelawat labels), peta haba ringkasan, dijejak-video analitik, sembang ringkasan, masa aktif status/history, and penjejakan health.
Laman web persediaan, allowed laman web tetapan, matlamat/kempen configuration, Pencetus (pelawat-label) configuration, masa aktif contacts and pemantau, maintenance schedules, recovery tindakan, amaran operations, and authorized sembang aliran kerja.
Yes. The Hitsteps papan pemuka calls this feature Pencetus. Internally and in the stable MCP API it is named pelawat labels, with tools such as create_label and the labels:write scope. An unqualified permintaan for a Hitsteps Pencetus should use the label tools unless the user explicitly means a penukaran-matlamat or kempen condition.
No. The MCP pelayan is for connected AI assistants that need to read or operate on Hitsteps data. Laman web penjejakan still uses the Hitsteps JavaScript penjejakan code or a platform-specific Hitsteps pemalam.
Only if the OAuth grant includes the required write scope and the user explicitly confirms the specific write tindakan. Read-only analitik grants cannot create laman web, change tetapan, edit masa aktif pemantau, update amaran, or send sembang replies.
Yes. Claude users can pasang Analitik Web Hitsteps from the Claude Connector Directory. The ChatGPT directory penyenaraian is coming soon; until then, add https://www.hitsteps.com/mcp/ manually as a custom MCP pelayan in ChatGPT and complete Hitsteps OAuth.
The pelayan returns a structured license_action_required response with non-sensitive akaun status and a Hitsteps URL where the user can check, renew, or naik taraf. Connection info, laman penyenaraian, and akaun status remain available so the assistant can explain the issue.
MCP usage telemetry is privacy-minimal. It rekod operational medan such as public OAuth client ID, normalized AI-client channel, tool name, status, duration, credential type, akaun/laman, and timestamp. It does not store prompts, tool arguments, model tokens, raw user ejen, raw result rows, or full ralat-mesej bodies.
Selepas pemasangan