Skip to main content
Glama
tiktok-shop-mcp

tiktok-shop-mcp

by Buer2333

tiktok-shop-mcp

A Model Context Protocol (MCP) server for the TikTok Shop Partner API — query orders, finance, products, analytics, and affiliate performance across multiple shops from Claude, or any other MCP client.

Built for sellers and agencies who operate TikTok Shops and want their AI assistant to answer questions like "what did the US shop sell yesterday?", "which SKUs are trending this week?", or "pull the settlement statements for June" — directly against the official API, with no browser scraping.

Features

  • Multi-shop — configure any number of shops in one JSON file; every tool takes an optional seller_name (partial match) to pick the shop

  • 32 tools covering orders, finance, product catalog and listing lookups, shop/video/SKU analytics, affiliate best-sellers, returns/cancellations, and gated product writes

  • Human-friendly dates — pass start_date=2026-07-01 + an IANA timezone instead of unix timestamps; the server handles conversion

  • Token lifecycle — inspect expiry and refresh access tokens (single shop or all shops) without leaving the conversation

  • Resilient by default — all requests go through mcp-retry (exponential backoff + jitter on 429/5xx/network errors)

  • Read-only by default — product write tools exist (image upload, create, partial edit, activate/deactivate), but every one of them refuses until you list the shop's exact name in TIKTOK_SHOP_WRITE_SHOPS, and each defaults to a dry run. See Product writes. Otherwise the only thing the server writes is your own shops.json, when it refreshes tokens, with owner-only (0600) permissions. If you never need writes, authorize the Partner Center app with read scopes only

Related MCP server: Amazon Seller MCP

Tools

Group

Tools

Shops & auth

list_shops · refresh_token · refresh_all_tokens

Orders

get_shop_orders · get_order_detail · search_returns · search_cancellations

Finance

get_shop_statements · get_shop_transactions

Products

get_shop_products · get_product_detail

Listing lookups

get_categories · get_category_attributes · get_category_rules · get_brands · get_warehouses

Product writes (opt-in, see below)

upload_product_image · create_product · partial_edit_product · activate_products · deactivate_products

Shop analytics

get_shop_performance · get_shop_performance_hourly · get_shop_products_performance · get_product_performance · get_shop_videos_performance · get_sku_performance · get_customer_service_performance

Video & affiliate

get_account_video_gmv · get_videos_bestselling · get_creators_bestselling · get_products_bestselling

Installation

pip install tiktok-shop-mcp

Or from source, into a virtualenv, with the direct dependencies pinned to the versions the tests run against:

git clone https://github.com/Buer2333/tiktok-shop-mcp.git
cd tiktok-shop-mcp
python3 -m venv .venv
.venv/bin/pip install -r requirements.txt
.venv/bin/pip install --no-deps -e .

requirements.txt pins the direct runtime dependencies to exact versions, including mcp-retry, which wraps every API call and so sees your tokens. Transitive dependencies (pydantic, starlette, and so on) are not pinned; for a fully reproducible install, generate a lock file with pip-compile --generate-hashes. Bump a pin only after reading what changed in that release.

Compatibility

Works with both mcp 1.x and 2.x. mcp 2.0 renamed FastMCP to MCPServer (mcp.server.mcpserver) and turned mcp.server.fastmcp into a raising stub; server.py imports via a try-v2-except-v1 shim. Tests pass on 1.28.1 and 2.1.1; requirements.txt pins 2.1.1.

Configuration

Credentials live in a JSON file outside the repo (default ~/.config/tiktok-mcp/shops.json, override with the TIKTOK_SHOP_CONFIG env var). The server never reads a shops.json from the project folder, so a copy there can't be picked up and synced or committed by accident. Keep the file owner-only:

chmod 700 ~/.config/tiktok-mcp && chmod 600 ~/.config/tiktok-mcp/shops.json

The setup scripts leave token backups (shops.json.bak.* and a recovery/ folder) next to it; delete them once your shops are working. A small shops.json.lock file also lives there; it is how the server, the cron refresher, and the setup scripts avoid writing the file at the same time, so leave it be.

[
  {
    "seller_name": "MY SHOP US",
    "seller_base_region": "US",
    "app_key": "...",
    "app_secret": "...",
    "access_token": "TTP_...",
    "refresh_token": "TTP_...",
    "shop_id": "...",
    "shop_cipher": "..."
  }
]

You get app_key / app_secret by creating an app on the TikTok Shop Partner Center, then authorize your shop(s) to obtain tokens. shop_id / shop_cipher are returned by the authorized-shops endpoint; the bundled probe_authorized_shops.py script can fetch them for you.

The three *_bestselling tools need a shop whose app has the Bestsellers scope. The lists are platform-wide, so one such shop is enough: set TIKTOK_SHOP_BESTSELLERS_SHOP to its seller_name (partial match OK) and the tools use it whenever seller_name is omitted. Without it they fall back to the first shop in shops.json.

Adding a shop

TIKTOK_SHOP_APP_SECRET=... .venv/bin/python add_or_update_shop.py "<full_callback_url>" --seller-name "MY SHOP"

TIKTOK_SHOP_APP_SECRET is only needed for the first shop on an app; after that the script reads it from the existing entry. The callback URL carries app_key and code. The code is single-use and starts with TTP_, while an app secret is 40 hex characters, so they are easy to tell apart.

To keep one business's shops apart from another's, point TIKTOK_SHOP_CONFIG at its own file for both this script and the server. Backups and the recovery/ folder follow that path.

Token lifetime

  • Access token: lasts about 7 days. An expired token gets 401 / 105002 Expired credentials; the server then refreshes it and retries once, so MCP use needs no scheduled job.

  • Refresh token: effectively does not expire (observed expiry in 2125).

  • access_token_expire_in / refresh_token_expire_in: despite the names, these are Unix timestamps, not durations.

  • *_expire_at in shops.json and list_shops: real UTC dates. Entries written by older versions can show years like 2083 until their next refresh.

Claude Code

claude mcp add tiktok-shop -- tiktok-shop-mcp

Claude Desktop / other MCP clients

{
  "mcpServers": {
    "tiktok-shop": {
      "command": "tiktok-shop-mcp",
      "env": { "TIKTOK_SHOP_CONFIG": "/path/to/shops.json" }
    }
  }
}

Product writes (opt-in)

Five tools change a shop's listings. They are off unless you turn them on per shop.

Tool

Endpoint (Product API 202309)

Required params

upload_product_image

POST /product/202309/images/upload (multipart)

seller_name, image_path; use_case = MAIN_IMAGE (default), ATTRIBUTE_IMAGE, DESCRIPTION_IMAGE, CERTIFICATION_IMAGE, SIZE_CHART_IMAGE

create_product

POST /product/202309/products

seller_name, product (the Create Product body: title, category_id, main_images, skus, ...)

partial_edit_product

POST /product/202309/products/{id}/partial_edit

seller_name, product_id, changes

activate_products

POST /product/202309/products/activate

seller_name, product_ids (max 20)

deactivate_products

POST /product/202309/products/deactivate

seller_name, product_ids (max 20)

The gate. Every write tool checks, before it builds a request:

  1. seller_name is given and matches a shops.json entry exactly. The read tools' partial, case-insensitive match and first-shop fallback do not apply: "MY SHOP" will not select "MY SHOP US".

  2. That exact name is listed in the TIKTOK_SHOP_WRITE_SHOPS environment variable (comma-separated). Unset or empty means every write tool refuses, dry runs included.

{
  "mcpServers": {
    "tiktok-shop": {
      "command": "tiktok-shop-mcp",
      "env": { "TIKTOK_SHOP_WRITE_SHOPS": "MY SHOP US" }
    }
  }
}

Dry run first. dry_run defaults to true: the tool returns the method, path and JSON body it would send (no token, signature or app key) and makes no HTTP request. Pass dry_run=false to send. A real send then:

  • goes out once. Write requests skip the automatic retry used for reads, because a create that timed out may still have gone through. On a network error the result says the outcome is unknown; read the product before trying again.

  • reads the product back (GET /product/202309/products/{id}) and returns it as read_back. After partial_edit_product the read-back asks for the version under review, since TikTok Shop keeps the old version live until the edit passes audit. After activate_products / deactivate_products it returns each product's status, and errors lists per-product failures that come back with code 0.

What the tools will not do.

  • No full Edit Product (PUT .../products/{id}): it overwrites every field the body leaves out.

  • partial_edit_product refuses skus. The API treats each top-level field as a unit, so a skus list you send stands in for the whole property; the docs do not say what happens to SKUs left out of it (they may be removed), and SKUs carry inventory. It also refuses listing_platforms and anything not on its list (title, description, brand_id, main_images, product_attributes, package_weight, package_dimensions, video, certifications, size_chart, search_terms, key_product_features, external_product_id, save_mode, locale).

  • No stock or price updates, product deletion, or anything touching orders, finance or promotions.

Things to know before sending.

  • Partial Edit leaves omitted top-level fields alone, but an object or list you do send replaces that whole property: leave out one product_attributes entry or one package_dimensions value and it is blanked. Send the full property.

  • Edits other than price and inventory go back to audit. So do activations (status PENDING). New products are audited after creation.

  • create_product sets each SKU's opening inventory (warehouse_id from get_warehouses, quantity). If another system syncs your stock, make the opening numbers match it; after creation, leave stock to that system.

  • US, EU and SEA shops must use category_version v2; the tools default to it.

  • The Partner Center app needs the Product Basic (seller.product.basic) and Product Modify (seller.product.write) scopes; get_warehouses needs Logistics Basic (seller.logistics).

Example prompts

  • "List my shops and when their tokens expire"

  • "Orders for MY SHOP US on 2026-07-18, Eastern time"

  • "Which creators drove the most GMV for us in the last 7 days?"

  • "Compare yesterday's hourly GMV curve with the day before"

  • "Refresh tokens for all shops"

Architecture

tiktok_shop_mcp/
├── server.py     # FastMCP app — tool definitions, date handling, error envelope
├── client.py     # Signed HTTP client (HMAC-SHA256 request signing, via mcp-retry)
├── config.py     # Multi-shop credential loading & resolution
├── write_guard.py # Exact-name + TIKTOK_SHOP_WRITE_SHOPS gate for write tools
└── tools/        # One module per API domain (orders, finance, products, analytics…)

All tools return structured JSON. Errors come back as {"error": true, "message": …, "suggestion": …} so the model can self-correct (e.g. refresh an expired token and retry).

Disclaimer

This is an independent open-source project, not affiliated with or endorsed by TikTok. Use of the TikTok Shop API is subject to TikTok's own terms.

License

MIT

Available Tools

22 tools
get_account_video_gmv_toolB

Auto-paginate all shop videos and aggregate GMV by account username. Pass usernames as comma-separated string (e.g. 'dr.elise,dr.camila') to filter specific accounts. Returns per-account totals: gmv, orders, items_sold, video count.

Inputs: currency, usernames, end_date_lt, seller_name, +2 more. Returns: result

get_creators_bestselling_toolA

Platform-wide TOP 100 bestselling creators (requires Bestsellers scope).

date: reference date YYYY-MM-DD. time_slot: "7D" (default) or "30D". author_type: "ALL" / "AFFILIATE" / "OFFICIAL". Returns bucketed gmv_range per creator. Use for BD outreach discovery.

Inputs: date, currency, time_slot, author_type, +1 more. Returns: result

get_customer_service_performance_toolA

Get shop customer-service performance (after-sales handling time, IM dissatisfaction rate, etc.) over a custom date window.

Dates are YYYY-MM-DD. support_date_ge inclusive, support_date_lt exclusive. Wraps GET /customer_service/202407/performance — replaces SPS-backend's locked 60-day window. Use seller_name to specify shop.

Inputs: seller_name, support_date_ge, support_date_lt. Returns: result

get_order_detail_toolB

Get detailed information for specific TikTok Shop orders (max 50 IDs). Use seller_name to specify which shop.

Inputs: order_ids (required), seller_name. Returns: result

get_product_detail_toolC

Get detailed product info including SKU prices. Use seller_name to specify which shop.

Inputs: product_id (required), seller_name. Returns: result

get_product_performance_toolB

Get single product performance with VIDEO/LIVE/PRODUCT_CARD breakdown. Use seller_name to specify shop.

Inputs: currency, product_id, end_date_lt, granularity, +2 more. Returns: result

get_products_bestselling_toolA

Platform-wide TOP 100 bestselling products (requires Bestsellers scope).

date: reference date YYYY-MM-DD. time_slot: "7D" (default) or "30D". category_id: optional TikTok category filter. Returns bucketed gmv_range per product — use for competitor and category-trend scouting.

Inputs: date, currency, time_slot, category_id, +1 more. Returns: result

get_shop_orders_toolB

Search TikTok Shop orders. Use seller_name to specify which shop (partial match OK, e.g. 'US' matches 'My Brand US').

Date query options (choose one):

  • Raw unix timestamps: create_time_ge / create_time_lt

  • Human-friendly dates: start_date / end_date (YYYY-MM-DD) + timezone

timezone: IANA timezone for date conversion. Use the timezone your reporting day follows, e.g. 'Etc/GMT+8' (fixed UTC-8) or 'America/New_York' (default).

When start_date is provided, it overrides create_time_ge/create_time_lt. start_date = beginning of that day in the given timezone. end_date = end of that day (if omitted, defaults to start_date = single day query).

Inputs: end_date, timezone, page_size, sort_field, +9 more. Returns: result

get_shop_performance_hourly_toolC

Get shop performance by hour for a specific date (YYYY-MM-DD). Use seller_name to specify shop.

Inputs: date, currency, seller_name. Returns: result

get_shop_performance_toolB

Get shop-level sales performance (GMV, orders, customers) with VIDEO/LIVE/PRODUCT_CARD breakdown. Dates are YYYY-MM-DD. granularity: 'ALL' (aggregate) or '1D' (daily). Use seller_name to specify shop.

Inputs: currency, end_date_lt, granularity, seller_name, +1 more. Returns: result

get_shop_products_performance_toolC

Get performance ranking for all products (GMV, orders, items_sold). Sort by gmv/items_sold/orders. Use seller_name to specify shop.

Inputs: currency, page_size, page_token, sort_field, +5 more. Returns: result

get_shop_products_toolC

Get TikTok Shop product listings. Use seller_name to specify which shop (partial match OK).

Inputs: status, page_size, seller_name, next_page_token. Returns: result

get_shop_statements_toolC

Get TikTok Shop financial statements (daily settlement records). Use seller_name to specify which shop.

Inputs: page_size, seller_name, create_time_ge, create_time_lt, +2 more. Returns: result

get_shop_transactions_toolA

Get transaction details for a specific order or statement. Provide exactly one of order_id or statement_id. Use seller_name to specify which shop.

Inputs: order_id, seller_name, statement_id. Returns: result

get_shop_videos_performance_toolB

Get performance ranking for all videos driving shop sales (GMV, views, click-through). account_type: ALL/SELF/AFFILIATE. Use seller_name to specify shop.

Inputs: currency, page_size, page_token, sort_field, +5 more. Returns: result

get_sku_performance_toolC

Get single SKU performance. Use seller_name to specify shop.

Inputs: sku_id, currency, end_date_lt, granularity, +2 more. Returns: result

get_videos_bestselling_toolA

Platform-wide TOP 100 bestselling videos (requires Bestsellers scope).

date: reference date YYYY-MM-DD. time_slot: "7D" (default) or "30D". Returns bucketed gmv_range per video — no exact GMV. Useful for trend-scouting and creator discovery.

Inputs: date, currency, time_slot, seller_name. Returns: result

list_shops_toolB

List all configured TikTok Shop accounts with their names and token expiry dates.

Inputs: random_string. Returns: result

refresh_all_tokens_toolC

Refresh access tokens for ALL configured shops. Useful for batch renewal before expiry.

Inputs: random_string. Returns: result

refresh_token_toolA

Refresh the TikTok Shop access token for a specific shop. Call when you get a 401/token expired error. New tokens are auto-saved to shops.json.

Inputs: seller_name. Returns: result

search_cancellations_toolC

Search cancelled orders with refund amounts and cancel reasons. Use start_date/end_date (YYYY-MM-DD) or raw timestamps.

Inputs: end_date, timezone, page_size, start_date, +4 more. Returns: result

search_returns_toolB

Search return/refund orders with refund amounts. Use start_date/end_date (YYYY-MM-DD) or raw timestamps.

Inputs: end_date, timezone, page_size, start_date, +4 more. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3.4/5.0

    Scored across 22 tools

    Disambiguation4/5

    The 22 tools mostly target distinct resources and actions, and clusters like the five performance tools (shop, hourly, product, SKU, videos) are differentiated by entity and granularity in their descriptions. Minor potential confusion exists between get_shop_videos_performance_tool and get_account_video_gmv_tool (both sound like shop-video GMV), but descriptions clarify the difference.

    Naming Consistency5/5

    Every tool uses a uniform verb_noun pattern with a consistent '_tool' suffix (list_shops_tool, get_shop_orders_tool, search_returns_tool, refresh_token_tool). Verbs are consistently recognizable (get/list/search/refresh) and the naming is fully predictable.

    Tool Count4/5

    22 tools sits at the heavy end, but the domain is broad (orders, products, finance, performance analytics, creator/video discovery, token management) and each tool appears to fill a distinct niche. It is well-scoped for a comprehensive TikTok Shop reporting surface rather than bloated.

    Completeness4/5

    Coverage spans orders, order detail, products, returns, cancellations, statements, transactions, multi-level performance, bestsellers, customer service, and token refresh — a thorough read/analytics surface. It is largely read-only, so write operations like order fulfillment, inventory, or product editing are absent, but these are minor gaps for the apparent analytics purpose.

    Maintenance

    ActivityMaintained
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      MCP server for the Shopline Open API. Exposes 140+ tools for querying and managing orders, products, customers, promotions, analytics, and store settings from your Shopline store via Claude.
      100
      MIT
    • F
      license
      A
      quality
      C
      maintenance
      Connects Claude to your Amazon Seller Central account via the Selling Partner API, enabling queries for recent orders, sales summaries, FBA inventory, and financial events.
      4
      -
    • A
      license
      Not graded
      quality
      C
      maintenance
      Enables sellers to interact with Amazon Selling Partner API and Advertising API data—orders, inventory, pricing, ads, reports, and more—through MCP clients like Claude and Cursor.
      MIT