Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Apitaco MCP Server How much have I spent on Apitaco in the last 30 days?"
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.
MCP server for Apitaco. Query your balance, usage, and pricing from any MCP-compatible client.
Exposes 3 MCP tools to Claude Desktop / Cursor / Claude Code / Cline:
apitaco_get_balance — current account balance in USD
apitaco_get_usage — token + cost stats for last N days
apitaco_list_models — supported models with per-1M pricing
Ask Claude: "How much do I have left on Apitaco?" → it calls the tool and answers.
Related MCP server: patch-usage-mcp
npm install -g @apitaco/mcp-serverOr run from source:
git clone https://github.com/myapitaco/apitaco-mcp-server
cd apitaco-mcp-server
npm install
npm run buildEdit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS)
or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"apitaco": {
"command": "npx",
"args": ["-y", "@apitaco/mcp-server"],
"env": {
"APITACO_API_KEY": "sk-..."
}
}
}
}Restart Claude Desktop. The apitaco_* tools appear in the tool list.
In Cursor settings → Features → MCP, add:
{
"mcpServers": {
"apitaco": {
"command": "npx",
"args": ["-y", "@apitaco/mcp-server"],
"env": { "APITACO_API_KEY": "sk-..." }
}
}
}claude mcp add apitaco npx -y @apitaco/mcp-server
# then set the env var in your shell
export APITACO_API_KEY=sk-...After configuring, just ask Claude in any MCP client:
"Check my Apitaco balance."
"How much have I spent on Apitaco in the last 30 days?"
"Which Apitaco models are cheapest for output?"
Var | Default | Description |
| required | Get one at my.apitaco.com/register |
|
| Override for self-hosted / staging |
MIT.
Get the current Apitaco account balance in USD. Use this when the user asks 'how much do I have left' or 'what's my balance'.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. 'Get' reasonably implies a non-mutating read and the USD unit is disclosed, but there is no mention of auth requirements, rate limits, whether the balance reflects real-time or cached data, or the response shape. Adequate but thin for a zero-annotation tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, zero filler, and the capability statement is front-loaded before the usage trigger. Every clause earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description usefully states that the result is a balance denominated in USD, covering the essential return semantics. It omits any detail on precision, currency formatting, or error cases, which is a minor gap for a tool this simple.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a parameterless tool applies. The description correctly avoids inventing parameter-like options such as currency selection.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Get the current Apitaco account balance') and pins the unit ('in USD'), so the agent knows exactly what comes back. It does not explicitly contrast itself with the siblings apitaco_get_usage and apitaco_list_models, though the resource name distinguishes it well enough in practice.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives concrete trigger phrasing ('how much do I have left', 'what's my balance'), which maps user intent to this tool directly. It stops short of naming alternatives or exclusions, so the agent must infer that balance questions differ from usage questions rather than being told.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get Apitaco usage stats for the last N days (default 7). Returns total tokens and cost.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | Window size in days (default 7, max 90) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It does disclose the return content (total tokens and cost) and the default window, but says nothing about permission/auth requirements, whether stats are account-wide or per-key, data freshness, 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tight sentences with the resource and scope front-loaded and the return payload stated second; every clause earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a one-optional-param read tool with no output schema, the description covers the essentials by naming the returned metrics and the default window. It falls just short on the aggregation scope and auth assumptions an agent might need.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% and the single parameter already documents its default (7) and maximum (90). The description only restates the default, adding no format, timezone, or unit detail beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Specific verb (Get) plus resource (Apitaco usage stats), with the window scope and the returned metrics named. It is distinguishable from apitaco_get_balance and apitaco_list_models by subject matter, but it never names or contrasts those siblings explicitly.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The window parameter implies a usage-reporting scenario, but there is no statement of when to prefer this over apitaco_get_balance (remaining credits vs consumed tokens/cost is a real ambiguity here) and no exclusions or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List models available on Apitaco with their per-million-token pricing.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of disclosure. It does reveal the nature of the returned data (model list plus per-million-token pricing), which implies a read-only operation, but it says nothing about pagination, scope, authentication, 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single front-loaded sentence with no filler, restated name, or redundant phrasing. Every clause (models, availability, pricing) carries information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no parameters and no output schema, the description must set expectations for what comes back, and it does name the two key payload elements (models and per-million-token pricing). It could note whether results are paginated or filtered server-side, but for a simple parameterless listing it is close to sufficient.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a parameterless tool is 4. The description does not need to explain any argument syntax.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states a clear verb ("List") and resource ("models available on Apitaco") and adds a payload detail (per-million-token pricing). It is distinguishable from the sibling tools apitaco_get_balance and apitaco_get_usage, though it never explicitly contrasts itself with them.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives no when-to-use, when-not-to-use, or alternative guidance. A caller must infer from the name and siblings that this is the catalog/enumeration tool as opposed to the account-centric balance and usage tools.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0apitaco_get_balanceapitaco_get_usageapitaco_list_modelsScored across 3 tools
Each tool targets a distinct resource and action: balance, usage stats, and available models. There is no overlap in purpose, and an agent can easily select the correct tool based on the user's request.
All tools follow a consistent pattern: apitaco_ prefix plus a clear verb_noun structure (get_balance, get_usage, list_models). The convention is predictable and readable.
Three tools is appropriate for a focused account-information server. Each tool earns its place by covering a distinct read-only query without unnecessary surface area.
The surface covers the core account queries: balance, usage, and model pricing. Minor gaps like detailed historical usage breakdowns or account settings exist, but agents can work around them for the stated purpose.
Account, billing, team, API key and model discovery tools for agents that use ModelsLab.
Analytics for MCP servers. Query your tool calls, first-call success, retries and schema cost.
Manage a ScaledThought account: API keys, budgets, usage and prepaid top-ups. Needs an API key.
Personal finance, bank account, and shared memory connector for Claude, ChatGPT, Gemini Spark & more
