Seed UGC across many accounts with Mastra

Q: Can I reuse the accounts for the next campaign?

Yes — `list_accounts` then `videos_only` bundles with `account_id`. Accounts remain managed and warm between waves.

Q: How do I handle

Set `disclose_as_ads: true` on paid content; the manager enables the platform's branded-content toggle or adds #ad. Combine with `create_video_ad_code_request` if you plan to boost.

Q: How do I report per creative rather than per account?

Put the creative id in each slot's `external_ref` (or `name`), then join `export_analytics_videos` on it in the agent.

UGC seeding from Mastra means taking a batch of creator-style videos and getting them posted from many ordinary-looking accounts in the target market, so the campaign reads as organic rather than as one brand handle. TokPortal does the account side: create_bundles_bulk opens N accounts in one country, configure_bundle_video places each creative on its slot with disclose_as_ads when required, publish_bundle hands each account to a human manager, and export_analytics_videos gives you a per-account, per-video report. Each account is human-created and human-operated, which is what keeps a seeding wave from being flagged as coordinated automation.

Connect TokPortal to Mastra

Mastra is an agent framework (code): TypeScript agent framework; MCPClient from @mastra/mcp connects HTTP or stdio MCP servers and hands their tools to an Agent.

npm i @mastra/core @mastra/mcp

import { Agent } from '@mastra/core/agent';
import { MCPClient } from '@mastra/mcp';

const mcp = new MCPClient({
  servers: {
    tokportal: {
      url: new URL('https://app.tokportal.com/api/ext/mcp'),
      requestInit: {
        headers: { 'X-API-Key': process.env.TOKPORTAL_API_KEY! },
      },
    },
  },
  timeout: 30000,
});

export const socialOps = new Agent({
  id: 'social-ops',
  name: 'Social ops',
  instructions: 'You operate TikTok and Instagram accounts through TokPortal tools. Quote credit costs before creating bundles.',
  model: 'anthropic/claude-sonnet-4-5',
  tools: await mcp.listTools(),
});

Tools are namespaced tokportal_tokportal_* (server name + tool name). Use mcp.listToolsets() to pass tools per request instead of at construction, and mcp.disconnect() on shutdown.

Snippet status: verified against Mastra's documentation (source).

Once connected, sanity-check the setup with a read-only call: "What is my TokPortal credit balance?" should trigger tokportal_get_credit_balance. GET requests and dry-run writes do not spend credits.

Try the workflow without spending

For this trial, use the remote MCP endpoint https://app.tokportal.com/api/ext/mcp, local tokportal-mcp 1.15.1 or later, or the REST API. Upgrade and restart an older local server first. Version 1.15.0 does not forward the dry-run header; do not use its write tools for a simulation. If you cannot verify the installed local version, use the remote endpoint or REST.

Use the sandbox for the first attempt. MCP write tools accept dry_run: true as a top-level argument, beside body; REST writes accept the X-TokPortal-Dry-Run: true header. Keep your usual authentication and scopes. Each simulated write validates the request and returns credits_would_charge with credits_charged: 0. Nothing is created or published.

Simulated IDs start with 00000000-0000-4000-8000-. Use them only in later dry-run writes. GET requests read real data, so skip publish-readiness checks and polling for synthetic IDs. Simulations have no cross-call memory and upload URLs are placeholders: do not upload files to them.

To run for real, review the returned price and confirm before the first live write. Bundle creation charges credits immediately; publishing hands the order to a manager. Repeat creation without dry-run mode and use the new real IDs for configuration and publishing. A synthetic ID cannot be reused in a live request.

How it works

A seeding plan is a matrix: creatives × accounts × dates. The agent starts with the accounts. create_bundles_bulk with platforms: ["tiktok"] (or ["tiktok","instagram"] to seed both), country, accounts_count (≤100 per call) and videos_per_account returns one bundle id per account. Each account gets its own configure_bundle_account — vary handles, bios and profile pictures (upload with upload_image_from_url) so the accounts look like different people, and consider advanced_warming_terms in the product's niche so the accounts have a history when the seeding starts.

Then the creatives. Upload each once (upload_video → public_url) and reuse the URL across bundles; TokPortal's duplicate-post guard is per account, so the same file on ten different accounts is fine. Fill slots with configure_bundle_video or batch_configure_bundle_videos, staggering target_publish_date across days and accounts (max 3 per day per bundle) so the wave looks natural. Set disclose_as_ads: true where the content is paid promotion — the manager enables branded-content disclosure or adds #ad — and add tiktok_sound_url if the campaign runs on a sound. publish_bundle per bundle (or loop). If a client asks for the Spark/Partner code to boost a post, create_video_ad_code_request returns it after finalization (7 credits).

Reporting is where Mastra shines: export_analytics_videos (CSV, filter by country, platform, from/to) plus get_comment_pulse for what people say, aggregated by the agent into a campaign summary.

Run it from Mastra

With Mastra the sequence is driven by your code: give the agent the tools from the TokPortal MCP server and the prompt below as the user message (or split it into tasks). Log every tokportal_* call and its arguments in development — the tool list is large (91 tools), so consider filtering to the ones this job needs.

Tool sequence

tokportal_get_credit_costs — N accounts × (32 + 2 × videos) — quote before creating.
tokportal_create_bundles_bulk — platforms, country, accounts_count, videos_per_account, optional advanced_warming_terms_count.
tokportal_configure_bundle_account — Different persona per bundle: handle, name, bio, profile_picture_url.
tokportal_upload_video — Upload each creative once; reuse public_url across bundles.
tokportal_configure_bundle_video — Place creative on slot: description, target_publish_date, video_url, disclose_as_ads, tiktok_sound_url.
tokportal_publish_bundle — One call per bundle.
tokportal_create_video_ad_code_request — Spark Code / Partner Code for paid boosting after finalization (7 credits).
tokportal_export_analytics_videos — Per-video CSV across all accounts for the campaign report.
tokportal_get_comment_pulse — Sentiment / themes across the seeded posts.

Prompt to paste

Evaluate this workflow in the TokPortal sandbox only.
Use the remote MCP endpoint https://app.tokportal.com/api/ext/mcp or local tokportal-mcp 1.15.1 or later for write tools.
Verify the installed local version before using its write tools. Version 1.15.0 is unsafe for simulations.
If the local version is older or unknown, use the remote endpoint or authenticated REST
requests with X-TokPortal-Dry-Run: true instead.
For every non-GET MCP tool call, set dry_run: true as a top-level boolean beside body.
For every REST write in a workflow, send the X-TokPortal-Dry-Run: true header.
Use normal read tools for existing real objects. Do not GET or poll synthetic IDs,
and do not upload files to simulated upload URLs. Simulated objects have no cross-call memory.
Show credits_would_charge and verify credits_charged is 0 for each simulated write.
Do not execute any live write. Ask for my explicit GO before the first real write,
including bundle creation, which charges immediately. After GO, repeat creation
without dry_run and use the new real IDs; never reuse synthetic IDs in live requests.

Use the TokPortal MCP tools. Campaign: 12 UGC creatives, seed in Mexico on TikTok across 12 accounts,
one creative per account, dates spread over 2026-09-08 → 2026-09-12, all disclosed as ads.
Quote with get_credit_costs, call create_bundles_bulk (12 accounts, 1 video each, external_ref "mx-wave1"),
then show me the per-bundle configure_bundle_account and configure_bundle_video payloads before running them.

Run with mastra dev and test in the playground, or call agent.generate() from your server code.

REST equivalent (write requests below are simulations; GET requests read existing real data)

# 15 seeding accounts in Brazil, 4 videos each, both platforms
curl -X POST -H "X-TokPortal-Dry-Run: true" https://app.tokportal.com/api/ext/bundles/bulk \
  -H "X-API-Key: sk_..." -H "Content-Type: application/json" -H "Idempotency-Key: $(uuidgen)" \
  -d '{"platforms":["tiktok","instagram"],"country":"BR","accounts_count":15,"videos_per_account":4,"external_ref":"seed-sept-br"}'

# Same creative on bundle A and bundle B, disclosed as ad
for B in BUNDLE_A BUNDLE_B; do
curl -X PUT -H "X-TokPortal-Dry-Run: true" https://app.tokportal.com/api/ext/bundles/$B/videos/1 \
  -H "X-API-Key: sk_..." -H "Content-Type: application/json" \
  -d '{"video_type":"video","description":"testei por 7 dias 👀 #publi","target_publish_date":"2026-09-05","video_url":"https://.../creative-1.mp4","disclose_as_ads":true}'
done

# Campaign export
curl "https://app.tokportal.com/api/ext/analytics/export/videos?country=BR&from=2026-09-01&to=2026-09-30" -H "X-API-Key: sk_..."

Key parameters

Parameter	Values	Notes
`accounts_count`	1–100 per bulk call	One bundle/account each; repeat calls for more.
`platforms`	["tiktok"] · ["instagram"] · both	Bulk creates accounts on each listed platform.
`disclose_as_ads`	boolean (free)	Branded-content disclosure or
`target_publish_date`	YYYY-MM-DD	Stagger across accounts; 3/day/bundle max.
`external_ref`	≤200 chars	Campaign tag copied to every bundle of the bulk call.
`instagram_content_type`	reel · post	For Instagram slots; carousels via carousel_images.

Full schemas: OpenAPI reference · openapi.json.

Example configurations

Bulk seeding fleet

{"platforms":["tiktok"],"country":"MX","accounts_count":25,"videos_per_account":3,
 "wants_advanced_warming":true,"advanced_warming_terms_count":3,"external_ref":"launch-mx-wave1"}

Slot with disclosure and sound

{"video_type":"video","description":"lo probé y… #ad #skincare","target_publish_date":"2026-09-06",
 "video_url":"https://pub-xxx.r2.dev/videos/creative-2.mp4","disclose_as_ads":true,
 "tiktok_sound_url":"https://www.tiktok.com/music/original-sound-7300000000000000000"}

Ad code request (POST /videos/{id}/ad-code-request)

{"note":"Boost for MX wave 1"}

Credits

25 accounts × (32 + 3 × 2) = 950 credits for a 25-account, 3-post wave at standard rates, plus warming targets (5 each) and 7 credits per ad code. Quote live with get_credit_costs; see Credits & Pricing.

Why not the official API

The official APIs are built for a brand posting on its own audited app to accounts users authorized one by one; seeding across dozens of fresh accounts would need dozens of OAuth grants, an audit, and would still be capped per token (6 requests/minute) and per user per day. TokPortal's model — distinct human-operated accounts, dated slots, disclosure flags — is the shape seeding actually needs.

As of August 2026 the first-party routes look like this. TikTok's Content Posting API (Direct Post) requires each account owner to authorize your app with the video.publish scope, limits every user access token to 6 requests per minute, keeps all posts from unaudited apps in private viewing mode until TikTok audits the app, and enforces an unpublished daily post cap per user (spam_risk_too_many_posts) that integrators commonly report at roughly 15–25 posts per account per day. Meta's Instagram Content Publishing API allows 100 API-published posts per professional account in a 24-hour moving window and only for accounts you own and connect via OAuth. Neither creates accounts, warms them, or reports third-party bans. TokPortal is human-operated infrastructure: accounts created and run by managers in the target country, one X-API-Key for all of them, dated slots (max 3 per day per bundle) instead of per-account tokens.

Sources: TikTok Content Posting API – Direct Post, TikTok Content Posting API – Get started, Instagram Platform – Content Publishing.

Seed UGC across many accounts with Mastra

Connect TokPortal to Mastra

Try the workflow without spending

How it works

Run it from Mastra

Key parameters

Example configurations

Credits

Why not the official API

FAQ

Can I reuse the accounts for the next campaign?

How do I handle

How do I report per creative rather than per account?

Also works with

Other jobs with Mastra