How do I use sellercloud-mcp?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@sellercloud-mcp Search for any SKU containing "WIDGET" and show inventory levels." That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

de en es ja ko ru zh

sellercloud-mcp

by alveyautomation

Overview Schema Source Related Servers Discussions Admin

Python

Remote

# sellercloud-mcp

The first Model Context Protocol server for SellerCloud. Plug Claude into your catalog, inventory, orders, and channel listings â€” read-only, in five minutes.

License: MIT Python 3.10+ MCP

Why this exists

SellerCloud has no public SDK. Their REST API is well-documented but unbranded â€” every team that automates against it ends up writing the same auth-and-pagination glue from scratch.

If you use Claude (or any MCP-aware AI assistant) to operate ecommerce day-to-day, that gap is the difference between "summarize today's orders" working out of the box and "summarize today's orders" requiring a custom integration.

sellercloud-mcp closes that gap. It's a tiny, well-tested, MIT-licensed MCP server that exposes seven read-only SellerCloud endpoints to any MCP client. Built from years of running ecommerce automation at scale.

Related MCP server: keycrm-mcp

What you can do with it

Wire this server into Claude Code, Claude Desktop, or any MCP host, then ask things like:

"Search for any SKU containing WIDGET and show me the inventory levels."
"How many orders did we ship yesterday across all marketplaces? Group by channel."
"Pull order 100001 and tell me which line items shipped."
"List the channels configured for company 9001 and show which ones are active."
"For SKU ACME-001, compare the price across every channel listing."

Claude reads your catalog directly. No copy-paste, no spreadsheets, no custom pipelines.

Tools (v0.1, all read-only)

Tool	What it does
`sellercloud_search_products`	Free-text search across catalog (name, SKU, attributes).
`sellercloud_get_product`	Fetch one product by exact SKU.
`sellercloud_search_orders`	List orders in a date window, optionally scoped by company.
`sellercloud_get_order`	Fetch one order by ID, including line items.
`sellercloud_get_inventory`	Current on-hand / reserved / on-order qty for one SKU.
`sellercloud_list_channels`	List configured marketplace/channel feeds.
`sellercloud_get_channel_listing`	Per-channel listing detail for one SKU.

Write endpoints (create order, update inventory, push channel changes) are intentionally not in v0.1. They are planned for v0.2 once read-only ergonomics settle.

Install

pip install sellercloud-mcp

v0.1 ships from this repository. PyPI publication is pending â€” for now, install with pip install git+https://github.com/alveyautomation/sellercloud-mcp or clone and run pip install -e . locally.

Configure credentials

The server reads everything from environment variables. Copy .env.example to .env and fill in your tenant:

SELLERCLOUD_API_URL=https://your-team.api.sellercloud.com/rest/
SELLERCLOUD_USERNAME=your-username
SELLERCLOUD_PASSWORD=your-password
SELLERCLOUD_DEFAULT_COMPANY_ID=        # optional fallback
SELLERCLOUD_HTTP_TIMEOUT=60            # optional, seconds
SELLERCLOUD_MAX_RETRIES=3              # optional

Use a read-only SellerCloud account. v0.1 only calls GET endpoints, but defense in depth means you should hand the server a dedicated user that cannot modify anything. When v0.2 lands with write tools, opt-in by upgrading the credential â€” never the other way around.

Wire into Claude Code

Add to ~/.claude/claude_code_config.json (or your project's MCP config):

{
  "mcpServers": {
    "sellercloud": {
      "command": "sellercloud-mcp",
      "env": {
        "SELLERCLOUD_API_URL": "https://your-team.api.sellercloud.com/rest/",
        "SELLERCLOUD_USERNAME": "your-username",
        "SELLERCLOUD_PASSWORD": "your-password",
        "SELLERCLOUD_DEFAULT_COMPANY_ID": "9001"
      }
    }
  }
}

Restart Claude Code. The seven sellercloud_* tools will appear in any new session.

Wire into Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows) and add the same mcpServers block as above. Restart the desktop app.

Tool reference

Every tool returns a JSON envelope:

{ "ok": true,  "data": { ... } }
{ "ok": false, "error": "human-readable message" }

`sellercloud_search_products`

sellercloud_search_products(
    query: str,                          # required
    company_id: int | None = None,       # falls back to default if unset
    page: int = 1,
    page_size: int = 50,                 # capped at 50 by SellerCloud
)

Example response:

{
  "ok": true,
  "data": {
    "items": [
      { "ID": "ACME-WIDGET-001", "ProductName": "Acme Widget, Standard", "Price": 29.99 }
    ],
    "total": 1,
    "page": 1,
    "page_size": 50
  }
}

`sellercloud_get_product`

sellercloud_get_product(sku: str, company_id: int | None = None)

Returns the catalog record, or data: null if the SKU is not in the company's catalog.

`sellercloud_search_orders`

sellercloud_search_orders(
    date_from: str,                      # ISO date "YYYY-MM-DD"
    date_to: str,                        # ISO date "YYYY-MM-DD"
    company_id: int | None = None,
    query: str | None = None,
    limit: int = 200,                    # max 1000
)

Pagination is handled transparently â€” SellerCloud caps page size at 50, but the tool collects pages up to limit. The response includes limit_reached: true when there were more orders than limit allowed.

`sellercloud_get_order`

sellercloud_get_order(order_id: int)

Returns the full order record (with Items[]), or data: null for a 404.

`sellercloud_get_inventory`

sellercloud_get_inventory(sku: str, company_id: int | None = None)

The returned record includes:

InventoryAvailableQty â€” what the API considers sellable right now
PhysicalQty â€” on-hand
ReservedQty â€” held for open orders
OnOrder â€” incoming PO qty

Use InventoryAvailableQty as the canonical "qty I can sell" number.

`sellercloud_list_channels`

sellercloud_list_channels(company_id: int | None = None)

Returns the list of configured channel feeds for the company. Each record includes ChannelID, Name, and Active.

`sellercloud_get_channel_listing`

sellercloud_get_channel_listing(channel_id: int, sku: str)

Per-channel listing detail. Useful for spot-checking prices across marketplaces.

Local development

git clone https://github.com/alveyautomation/sellercloud-mcp
cd sellercloud-mcp
python -m venv .venv && source .venv/bin/activate    # Windows: .venv\Scripts\activate
pip install -e ".[dev]"
pytest                                                # 44 tests, ~4s

Pre-commit hooks (gitleaks, ruff, formatter, tenant-fingerprint scrubber):

pip install pre-commit
pre-commit install

Integration tests against a real SellerCloud sandbox account are gated behind SELLERCLOUD_INTEGRATION_TESTS=1. They are not required for normal contribution.

Troubleshooting

Failed to obtain SellerCloud token â€” username/password rejected. Most common cause: the account has 2FA enabled or is locked out. SellerCloud's POST /api/token endpoint expects a non-2FA service account.

Missing required environment variables â€” the server tried to start before its .env was loaded. Either export the vars in the parent shell, or ensure your MCP host config includes them in the env block.

Empty results despite known data â€” confirm the company_id is correct. SellerCloud returns only the authenticated user's default company unless you pass companyID explicitly.

Pagination feels slow â€” page size is capped at 50 by SellerCloud, not by us. For large date windows, expect multiple round-trips.

Contributing

Issues and pull requests welcome. Please:

Run pytest before opening a PR (pip install -e ".[dev]").
Run pre-commit run --all-files.
Keep additions to v0.1 scope read-only. Write endpoints land in v0.2.
Synthetic data only in tests â€” no real SKUs, customer names, or order numbers.

License

MIT â€” see LICENSE.

Disclaimer

sellercloud-mcp is an unofficial, third-party integration. It is not endorsed by, affiliated with, or supported by SellerCloud, Inc. "SellerCloud" is a trademark of SellerCloud, Inc. Use at your own risk; verify behavior against your tenant before depending on it for production decisions.

Available Tools

7 tools

sellercloud_get_channel_listingA

Fetch the per-channel listing record for a single SKU.

Args: channel_id: SellerCloud ChannelID (integer). sku: Exact SKU.

Returns: JSON envelope. data is the listing record, or null if the SKU is not listed on the given channel.

ParametersJSON Schema

Name	Required	Description	Default
`channel_id`	Yes
`sku`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.1/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Despite no annotations, the description discloses the return format (JSON envelope with data field) and the null case when SKU is not listed. This provides adequate transparency for a read-only operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise, using three sentences to convey purpose, parameters, and return value. Every sentence is meaningful and front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given an output schema exists, the description sufficiently covers the tool's functionality, input requirements, and output behavior (including null). It is complete for the task of selecting and invoking the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the burden. It reiterates the types (integer, exact SKU) which matches the schema, but does not add additional meaning or constraints beyond what is obvious from names and types.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it fetches the per-channel listing record for a single SKU, using a specific verb and resource. It distinguishes itself from sibling tools like sellercloud_get_inventory or sellercloud_get_product by focusing on channel listings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving a listing by channel and SKU, but does not explicitly state when not to use it or mention alternative tools. No guidance on prerequisites or context is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

sellercloud_get_inventoryA

Fetch the current inventory record for a single SKU.

Args: sku: Exact SKU / InventoryID. company_id: CompanyID scoping the lookup.

Returns: JSON envelope. data is the inventory record (with on-hand, reserved, on-order, available qty fields), or null if absent.

ParametersJSON Schema

Name	Required	Description	Default
`sku`	Yes
`company_id`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.5/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must cover behavioral traits. It states 'Fetch,' implying a read-only operation, and describes the return format including null for absent records. It does not mention authorization or side effects, but the context suggests a safe read.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is highly concise with no wasted words. It front-loads the core action in the first sentence, then efficiently lists parameters and return values in a structured format.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with two parameters and an output schema (though not explicitly shown), the description fully explains the purpose, parameters, and return value. It covers edge cases (null if absent) and key fields in the response.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% meaning no descriptions in the schema. The description adds meaning: 'sku' is described as 'Exact SKU / InventoryID' and 'company_id' as 'CompanyID scoping the lookup,' which clarifies their roles beyond the type-only schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it fetches inventory for a single SKU, using a specific verb ('Fetch') and resource ('inventory record'). This distinguishes it from sibling tools like sellercloud_get_order or sellercloud_get_product, which target different entities.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description specifies it's for a single SKU and lists required parameters. However, it does not explicitly state when to use this tool versus alternatives or provide exclusion criteria. The purpose is clear enough for an agent to infer usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

sellercloud_get_orderA

Fetch full order detail including line items.

Args: order_id: SellerCloud OrderID (integer).

Returns: JSON envelope. data is the order record, or null if the order does not exist.

ParametersJSON Schema

Name	Required	Description	Default
`order_id`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.8/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description bears full burden. It discloses that it returns null if order not found, but does not mention authentication requirements, rate limits, or any side effects. Minimal behavioral info.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Extremely concise: four lines total. Front-loaded with purpose, then structured parameter and return descriptions. No redundant sentences.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with 1 parameter and an output schema, the description covers the core functionality, parameter meaning, and return behavior. Missing usage guidance and behavioral details (rate limits, auth) but acceptable given low complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% (no param descriptions in schema). Description adds 'SellerCloud OrderID (integer)', which gives context beyond the schema's 'Order Id' title and integer type. However, it does not elaborate on format or possible values.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Fetch full order detail including line items.' Identifies specific verb and resource. Distinguishes from siblings like sellercloud_search_orders (search vs fetch) and sellercloud_get_product (different resource).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Does not explicitly state when to use this tool vs alternatives. Usage is implied by requiring an order_id, but no guidance on context (e.g., use when you have an ID, vs search_orders when you don't).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

sellercloud_get_productA

Fetch the full catalog record for a single SKU.

Args: sku: Exact SKU / ProductID to look up. company_id: CompanyID scoping the lookup.

Returns: JSON envelope. data is the product record, or null when the SKU is not present in the company's catalog.

ParametersJSON Schema

Name	Required	Description	Default
`sku`	Yes
`company_id`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It discloses the return format as a JSON envelope and the possibility of null for missing SKU, but lacks details on idempotency, side effects, or rate limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise with a structured Args and Returns section, front-loaded with the main purpose, and no unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity and the presence of an output schema, the description adequately covers purpose, parameters, and return shape. However, it could mention the absence of pagination or limits on the record size.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 0% description coverage, so the description compensates by clarifying 'sku' as 'Exact SKU / ProductID' and 'company_id' as 'CompanyID scoping the lookup', adding meaning beyond the raw types.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the verb 'Fetch' and specifies the resource as 'full catalog record for a single SKU', clearly distinguishing it from sibling tools like 'sellercloud_search_products' which implies search functionality.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description states 'for a single SKU', implying use when exact SKU is known. However, it does not explicitly mention when not to use or compare with alternatives like 'sellercloud_get_channel_listing'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

sellercloud_list_channelsA

List configured channel feeds for the given company.

Args: company_id: CompanyID scoping the lookup.

Returns: JSON envelope. data.channels is the list of channel records.

ParametersJSON Schema

Name	Required	Description	Default
`company_id`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A3.8/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Describes return structure as 'JSON envelope with data.channels'. Given no annotations, it adds some context (scoping lookup by company_id) but lacks details on side effects, rate limits, or behavior with null company_id.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences in a clean Args/Returns format. No superfluous information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list operation, the description covers purpose, parameter role, and return structure. Lacks only minor details like read-only hint or error cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Only parameter 'company_id' is explained as 'CompanyID scoping the lookup'. Adds meaningful context beyond the schema title, compensating for 0% schema description coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'List configured channel feeds for the given company'. Verb (List) and resource (channel feeds) are specific. Differentiates from sibling 'sellercloud_get_channel_listing' by being a list operation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives. No mention of when not to use or when to prefer a sibling like 'sellercloud_get_channel_listing'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

sellercloud_search_ordersA

Search orders created in the inclusive [date_from, date_to] window.

Args: date_from: ISO date (YYYY-MM-DD), start of window. date_to: ISO date (YYYY-MM-DD), end of window. company_id: CompanyID to scope the search to. If omitted, returns orders for the authenticated user's default company. query: Optional free-text filter applied server-side. limit: Cap on yielded orders (default 200, max 1000). The underlying API caps page size at 50; pagination is handled transparently.

Returns: JSON envelope. data.orders is the list of order records.

ParametersJSON Schema

Name	Required	Description	Default
`date_from`	Yes
`date_to`	Yes
`company_id`	No
`query`	No
`limit`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description adequately discloses behavioral traits: pagination is handled transparently, limit caps (default 200, max 1000), default company behavior for company_id. This goes beyond basic parameter names.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a brief purpose, clear args list, and returns section. It is slightly verbose but every sentence adds value. No superfluous content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 5 parameters and an output schema, the description covers date range, optional filters, pagination, limit, and return envelope. It could mention error handling or rate limits, but overall it is sufficiently complete for effective tool use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must fully explain parameters. It does: date_from/date_to with ISO format, company_id with default behavior, query as free-text filter, limit with default and max. This adds significant meaning beyond the schema titles.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Search orders created in the inclusive [date_from, date_to] window.' This specifies the verb (search), resource (orders), and scope (date range), distinguishing it from sibling tools like sellercloud_get_order (single order) and sellercloud_search_products (product search).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for browsing orders within a date window but does not explicitly state when to use this tool over alternatives like sellercloud_get_order or sellercloud_search_products. No when-not guidance or exclusions are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

sellercloud_search_productsA

Search the SellerCloud catalog by name, SKU, or attribute.

Args: query: Free-text search string. Matches against product name, SKU, and indexed attributes. company_id: SellerCloud CompanyID to scope the search to. Falls back to SELLERCLOUD_DEFAULT_COMPANY_ID if omitted. page: 1-indexed page number. page_size: Page size (max 50 enforced server-side).

Returns: JSON envelope: {"ok": true, "data": {"items": [...], "total": N}}.

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes
`company_id`	No
`page`	No
`page_size`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
`result`	Yes

TDQS

A4.4/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It reveals behavioral details like page_size max 50 enforced server-side, pagination behavior, and the response envelope. It does not mention authentication, rate limits, or case sensitivity, but for a search tool the provided info is adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured using bullet points for parameters and a clear Returns section. It is concise but could be slightly more compact (e.g., removing the docstring formatting overhead). Still, every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 4 parameters, no annotations, and an output schema (though not provided), the description covers parameter semantics, pagination, and return format. It lacks cross-referencing to siblings or mention of authorization, but overall it is complete for a search operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage, so the description must compensate. It does so excellently by explaining that query is free-text, company_id has a fallback default, page is 1-indexed, and page_size is capped at 50. This adds substantial meaning beyond the schema's type-only definitions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Search the SellerCloud catalog by name, SKU, or attribute,' providing a specific verb and resource. It distinguishes itself from sibling tools like sellercloud_get_product (single product retrieval) and sellercloud_search_orders (different entity), making the tool's role unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for general product searching but does not explicitly state when to avoid it or compare it to siblings like sellercloud_get_channel_listing or sellercloud_get_inventory. However, the parameter descriptions give clear context on how to use the tool effectively.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

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

7 tool updatesv0.1.0Apr 27, 2026
- First observedsellercloud_get_channel_listing
- First observedsellercloud_get_inventory
- First observedsellercloud_get_order
- First observedsellercloud_get_product
- First observedsellercloud_list_channels
- First observedsellercloud_search_orders
- First observedsellercloud_search_products

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.1/5.0

Scored 2026-04-27 05:10 across 7 tools

Disambiguation5/5

Each tool targets a distinct resource or action: product, inventory, order, channel listing, channels list, and two searches. No overlap in purpose.

Naming Consistency5/5

All tools follow a consistent `sellercloud_verb_noun` pattern (get_, list_, search_), with clear verb choice for the operation type.

Tool Count5/5

7 tools is well-scoped for a seller cloud integration covering core data retrieval: product, inventory, order, and channel information.

Completeness3/5

The tool set is read-only, covering get and search for products, orders, inventory, and channels. Missing update/create operations that agents might need for full workflow support.

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

agentcentral AOAuth
to.agentcentral
Hosted Amazon Seller Central and Amazon Ads MCP server for Claude, ChatGPT, Cursor, and agents.
E-commerce & Retail Customer Support
26
DataDoe MCPOAuth
com.datadoe
Hosted Amazon Seller and Vendor MCP server for Claude, ChatGPT, Cursor, Codex, Gemini, Copilot.
E-commerce & Retail CRM
214
Terra Natural Seller MCPOAuth
uk.co.sellermcp
Connect Amazon Seller Central to Claude or ChatGPT via MCP. Orders, inventory, pricing, fees, FBA.
E-commerce & Retail Finance
1
Furgonetka.pl - Logistics & Shipping MCP ServerOAuth
pl.furgonetka.api
Furgonetka MCP Server is an extension for LLMs (such as Claude) that integrates AI assistants with Poland's most popular courier brokerage platform. The server enables models to interact directly with services from various couriers (including InPost, DPD, DHL, UPS, and Poczta Polska) through a single, unified interface. With this integration, your AI stops just "writing about logistics" and starts actually managing it.
E-commerce & Retail Monitoring Travel & Transportation
2

Related MCP Servers

TripleWhale MCP Serverofficial
E-commerce & Retail Search Databases
Triple-Whale
A
license
Not graded
quality
C
maintenance
An implementation of Model Context Protocol (MCP) that allows users to interact with TripleWhale's e-commerce analytics platform using natural language queries through Claude Desktop.
Updated a year ago (2025-09-30 12:49 UTC)
106 npm
7
MIT
keycrm-mcp
CRM E-commerce & Retail
IvanKlymenko
F
license
Not graded
quality
C
maintenance
A Model Context Protocol server that lets Claude manage keyCRM catalogue, stock, orders, customers, pipelines, and more via natural language.
Updated 6 months ago (2026-03-25 11:17 UTC)
3
-
Amazon Seller MCP Server -
E-commerce & Retail Finance Marketing
Deltologic
A
license
Not graded
quality
B
maintenance
Hosted Amazon Seller Central & Vendor Central MCP server. Connect Claude, ChatGPT, Cursor, Codex, Gemini, and GitHub Copilot to live Amazon SP-API and Amazon Ads API data.
Updated a month ago (2026-08-26 15:09 UTC)
14
MIT
Chatwoot MCP Server
Customer Support Communication
mohnori
A
license
A
quality
D
maintenance
A Model Context Protocol (MCP) server that connects AI assistants like Claude to your Chatwoot instance. Manage customer conversations, read messages, send replies, and filter by date ranges -- all through natural language.
Updated 6 months ago (2026-04-01 08:56 UTC)
5
18 npm
MIT

Why this exists

What you can do with it

Tools (v0.1, all read-only)

Install

Configure credentials

Wire into Claude Code

Wire into Claude Desktop

Tool reference

sellercloud_search_products

sellercloud_get_product

sellercloud_search_orders

sellercloud_get_order

sellercloud_get_inventory

sellercloud_list_channels

sellercloud_get_channel_listing

Local development

Troubleshooting

Contributing

License

Disclaimer

Available Tools

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Output Schema

Tool Schema Changelog

Resources

Related MCP Connectors

Related MCP Servers

TripleWhale MCP Serverofficial

`sellercloud_search_products`

`sellercloud_get_product`

`sellercloud_search_orders`

`sellercloud_get_order`

`sellercloud_get_inventory`

`sellercloud_list_channels`

`sellercloud_get_channel_listing`