Pull analytics across all accounts with any AI agent
Pull TikTok/Instagram analytics across every managed account from any of 25 agents: get_analytics_dashboard, get_analytics_series, list_account_video_an…
From any MCP-capable agent, one call summarizes every managed account: get_analytics_dashboard (filters platform, country, account, from/to), get_analytics_series for daily or weekly curves of views/likes/comments/shares/followers, list_account_video_analytics per account, get_comment_pulse for what people say, and export_analytics_videos / create_analytics_report for the CSV or branded report. TokPortal collects the numbers because it operates the accounts — no per-account OAuth, no Business-account requirement, no scraping on your side.
How it works
Analytics in TokPortal are workspace-wide and account-scoped at once. Start with get_analytics_contract once — it tells the agent which metrics, granularities and freshness guarantees apply to your workspace — then get_analytics_dashboard for the headline numbers over from/to, filtered by repeatable platform, country and account params. get_analytics_series returns time series with metric (views, likes, comments, shares, followers), granularity (day, week) and mode (cumulative, gained, snapshot) — gained per day is what most dashboards want.
Per account, get_analytics_account (or get_account_analytics) gives the profile-level snapshot and list_account_video_analytics the per-video table (paginated, sort_by/sort_order), which the agent can rank to find winning hooks. Comments: get_comment_pulse for the aggregate mood and list_analytics_account_comments for the text. If a number looks stale, can_refresh_account_analytics says whether a refresh is allowed and refresh_account_analytics triggers it — refreshes are rate-limited by design.
For deliverables, export_analytics_videos returns a CSV filtered by account, platform, country, q, from, to; create_analytics_report returns a structured report and export_analytics_report_html a branded HTML page. From any MCP-capable agent the useful pattern is a scheduled digest: every morning, dashboard for yesterday, top 5 videos, accounts with zero posts in 7 days (join with list_accounts), any new entries in list_account_bans — posted to Slack or written to a sheet.
Tool sequence
tokportal_get_analytics_contract— Metrics, granularities and freshness rules for your workspace.tokportal_get_analytics_dashboard— Totals overfrom/towithplatform/country/accountfilters.tokportal_get_analytics_series—metric,granularity,mode, optionalaccount.tokportal_list_accounts— Enumerate accounts (platform,country,banned=false) to iterate.tokportal_list_account_video_analytics— Per-video table per account, sortable.tokportal_get_comment_pulse— Aggregate comment signal across accounts.tokportal_refresh_account_analytics— Force a refresh whencan_refresh_account_analyticsallows.tokportal_export_analytics_videos— CSV for spreadsheets.tokportal_create_analytics_report— Structured report (orexport_analytics_report_html).
Pick your agent
- Pull analytics across all accounts with Claude — Anthropic's assistant on claude.ai, the mobile apps and Claude Desktop, with custom MCP connectors.
- Pull analytics across all accounts with Claude Code — Anthropic's terminal coding agent; MCP servers are added with
claude mcp addand used in any session. - Pull analytics across all accounts with ChatGPT — OpenAI's assistant; plans with developer mode can add remote MCP servers as custom connectors.
- Pull analytics across all accounts with OpenAI Codex — OpenAI's coding agent (Codex CLI and IDE extension); MCP servers live in
~/.codex/config.toml. - Pull analytics across all accounts with Cursor — AI code editor with an agent mode; MCP servers are configured in
.cursor/mcp.jsonor via a one-click deeplink. - Pull analytics across all accounts with Windsurf — Codeium's agentic IDE (Cascade); MCP servers are declared in
~/.codeium/windsurf/mcp_config.json. - Pull analytics across all accounts with Cline — Open-source autonomous coding agent for VS Code with an MCP marketplace and per-tool approval.
- Pull analytics across all accounts with OpenClaw — Open-source autonomous agent runtime with a skills registry (ClawHub); TokPortal ships as a first-party skill.
- Pull analytics across all accounts with Hermes Agent — Nous Research's open-source agent runtime; MCP servers are declared under
mcp_serversin~/.hermes/config.yaml. - Pull analytics across all accounts with Gemini CLI — Google's open-source terminal agent for Gemini; MCP servers via
gemini mcp addor~/.gemini/settings.json, plus extensions. - Pull analytics across all accounts with Goose — Block's open-source local agent; remote MCP servers are added as extensions (Streaming HTTP) or via a
goose://deeplink. - Pull analytics across all accounts with Perplexity — Answer engine with custom MCP connectors on paid plans; good for read-only research over your TokPortal data.
- Pull analytics across all accounts with Microsoft Copilot Studio — Microsoft's low-code agent builder; MCP servers are added as tools through the MCP onboarding wizard (Streamable transport).
- Pull analytics across all accounts with Factory Droid — Factory's software-engineering agent (
droidCLI); HTTP MCP servers are added withdroid mcp add. - Pull analytics across all accounts with n8n — Open-source workflow automation; use the built-in MCP Client Tool node with an AI Agent, or the community node
n8n-nodes-tokportalfor deterministic steps. - Pull analytics across all accounts with Make — Visual automation platform (ex-Integromat); call TokPortal from HTTP modules with
X-API-Key, or from Make's MCP Client module where available. - Pull analytics across all accounts with Zapier — Automation platform; today TokPortal is used via Webhooks by Zapier (REST) — a native TokPortal app is coming.
- Pull analytics across all accounts with Pipedream — Serverless integration platform for developers; call TokPortal from a Node.js/Python code step or the HTTP action, and receive webhooks on an HTTP trigger.
- Pull analytics across all accounts with Dify — Open-source LLM app platform; MCP servers are registered under Tools → MCP and used by Agent nodes and Agent apps.
- Pull analytics across all accounts with Flowise — Open-source visual builder for LLM flows; the Custom MCP node connects any Streamable HTTP server to Agentflow / tool agents.
- Pull analytics across all accounts with Langflow — Open-source visual framework for agents; the MCP Tools component connects to servers registered in Settings → MCP Servers.
- Pull analytics across all accounts with CrewAI — Python multi-agent framework;
MCPServerAdapterfromcrewai-toolsturns any MCP server into agent tools. - Pull analytics across all accounts with LangChain — LangChain / LangGraph agents load MCP tools with
langchain-mcp-adapters(MultiServerMCPClient). - Pull analytics across all accounts with Vercel AI SDK — TypeScript toolkit for AI apps; the MCP client (
@ai-sdk/mcp, formerlyexperimental_createMCPClientinai) turns TokPortal tools intogenerateText/streamTexttools. - Pull analytics across all accounts with Mastra — TypeScript agent framework;
MCPClientfrom@mastra/mcpconnects HTTP or stdio MCP servers and hands their tools to anAgent.