Skip to main content
Glama
konradbachowski

baselinker-mcp

by konradbachowski
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

baselinker-mcp

Free, open-source MCP server + CLI for the BaseLinker API. There is no free BaseLinker MCP on the market — this is one. MIT licensed.

It is token-lean by design: instead of dumping ~150 tool schemas into the model's context, it exposes two tools — a generic baselinker_call that can invoke any of the ~150 API methods (including future ones), and baselinker_list_methods for on-demand discovery. Full API coverage, minimal context cost.

Install

pipx install baselinker-mcp        # or: pip install baselinker-mcp

From source:

git clone https://github.com/konradbachowski/baselinker-mcp
cd baselinker-mcp
pip install -e .

Related MCP server: clickup-mcp

Get a token

BaseLinker panel → My account → API → copy the token. Then either:

baselinker auth set <YOUR_TOKEN>      # stored in ~/.config/baselinker/config.json (chmod 600)
# or
export BASELINKER_TOKEN=<YOUR_TOKEN>

MCP usage

The server command is baselinker-mcp and reads BASELINKER_TOKEN from the environment.

Claude Desktop / Claude Code (claude_desktop_config.json or .mcp.json):

{
  "mcpServers": {
    "baselinker": {
      "command": "baselinker-mcp",
      "env": { "BASELINKER_TOKEN": "your-token-here" }
    }
  }
}

Cursor (.cursor/mcp.json): same shape.

The two exposed tools:

Tool

Purpose

baselinker_call(method, parameters)

Invoke any BaseLinker API method.

baselinker_list_methods(filter?)

Discover method names, categories and params.

CLI usage

baselinker methods                       # list all ~150 methods
baselinker methods order                 # filter by name/category
baselinker call getOrders --params '{"get_unconfirmed_orders": true}'
baselinker call updateInventoryProductsStock \
    --params '{"inventory_id": 123, "products": {"456": {"bl_001": 10}}}'

Output is the raw JSON response from BaseLinker.

Security

  • Never commit your token. .env and ~/.config/baselinker/ are gitignored.

  • The API token grants full account access — treat it like a password.

  • BaseLinker rate limit is 100 requests/min; the client throttles to stay under it.

Method coverage

All ~150 documented methods across Orders, Invoices, Receipts, Order Returns, Courier Shipments, CRM, Product Catalog (Inventory), Inventory Documents, Purchase Orders, Fulfillment Deliveries, Suppliers, Payers, BaseLinker Connect and External Storages. Run baselinker methods for the full list, or read the API docs.

Need it built for you?

This tool is free — but wiring BaseLinker into your stack (syncing stock and orders across marketplaces, automating fulfillment, connecting your ERP/CRM, custom integrations) is real work. That's what we do at HeyNeuron, an AI-first software house.

If you want BaseLinker automation or an e-commerce integration implemented, get in touch.

License

MIT — see LICENSE.

Available Tools

2 tools
baselinker_callBaselinker CallA

Call any BaseLinker API method and return its JSON response.

method is the exact API method name (e.g. "getOrders", "addOrder", "updateInventoryProductsStock"). parameters is that method's argument object. Use baselinker_list_methods first to discover names and params.

ParametersJSON Schema
NameRequiredDescriptionDefault
methodYes
parametersNo

Output Schema

ParametersJSON Schema
NameRequiredDescription

No output parameters

TDQS

A4.3/5.0
Behavior3/5

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

No annotations are provided, so the description carries the full behavioral burden. It transparently describes a generic passthrough that returns JSON and includes mutating examples like 'addOrder' and 'updateInventoryProductsStock,' which implies side effects. However, it does not explicitly warn about destructive methods, error behavior, authentication, or rate limits, leaving a meaningful gap.

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?

Three short, front-loaded sentences with inline code formatting and concrete examples. No filler; every sentence contributes either the core action, parameter semantics, or discovery guidance.

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 generic API-call passthrough with only two parameters, the description covers the essential invocation contract: exact method name, argument object, JSON response, and discovery path via baselinker_list_methods. With an output schema present, return fields need not be spelled out; the main omission is safety and error context, not call mechanics.

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 coverage is 0%, and the description compensates strongly. It defines `method` as 'the exact API method name' with concrete examples, and `parameters` as 'that method's argument object.' It also points to baselinker_list_methods for discovering names and params, which is exactly the information the bare schema omits.

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?

States a specific verb and resource: 'Call any BaseLinker API method and return its JSON response.' This clearly distinguishes it from sibling baselinker_list_methods, which is for discovery, and the concrete examples reinforce the method-calling purpose.

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 explicitly says 'Use baselinker_list_methods first to discover names and params,' establishing a clear prerequisite and routing the agent to the sibling tool for discovery. It doesn't enumerate exclusions or when-not-to-use conditions, but the sequencing is clear enough for selection.

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

baselinker_list_methodsBaselinker List MethodsA

List available BaseLinker API methods with name, category, description and common params. Pass filter to match a substring of the method name or category (e.g. "order", "inventory", "courier").

ParametersJSON Schema
NameRequiredDescriptionDefault
filterNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A4.3/5.0
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 clearly discloses the filter behavior (substring match on method name or category) and the output contents. It does not explicitly state that the operation is read-only or describe potential limits, but 'List' conveys safety and the output schema covers return structure.

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 exactly two sentences with no redundancy. The primary purpose is front-loaded in the first sentence, and the second sentence adds the only parameter detail needed. Every word earns its place.

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 single-optional-parameter listing tool, the description covers what is returned and how to filter. The only gap is the lack of explicit guidance on how this tool relates to baselinker_call, though the sibling list provides that context. The output schema handles the return structure, so nothing else is missing.

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 provides only a type and default for `filter` with zero description coverage. The tool description fully compensates by explaining that the filter matches a substring of the method name or category and supplies concrete examples ('order', 'inventory', 'courier'). This adds essential meaning beyond the raw 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 uses a specific verb ('List') and resource ('available BaseLinker API methods'), and itemizes the returned fields (name, category, description, common params). This makes it immediately distinguishable from its sibling baselinker_call, which executes a method rather than enumerating them.

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 by explaining how to use the filter, but it never explicitly states when to choose this tool over baselinker_call. The sibling relationship makes the intended discovery-then-call workflow inferable, but no explicit when/when-not guidance is provided.

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.

  1. 2 tool updatesv0.1.0
    • First observedbaselinker_call
    • First observedbaselinker_list_methods
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

A4.4/5.0

Scored across 2 tools

Disambiguation5/5

The two tools have completely distinct purposes: one discovers available API methods and the other invokes them. There is no overlap or ambiguity in selecting between them.

Naming Consistency4/5

Both tools share the baselinker_ prefix and use snake_case, but baselinker_call is a bare verb while baselinker_list_methods follows a verb_noun pattern. This is a minor inconsistency rather than a chaotic naming scheme.

Tool Count4/5

At two tools, this is slightly below the typical 3-15 range, but each tool earns its place for a generic API bridge: one for discovery and one for execution. The count is minimal without feeling incomplete.

Completeness5/5

The generic baselinker_call provides access to every BaseLinker API method, so there are no missing CRUD or lifecycle operations. The baselinker_list_methods tool covers the discovery gap that would otherwise leave agents guessing at method names.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers