Machine Learning

Minitap MCP Server

Use Studio chat to drive this server — credentials stay in your workspace.

Minitap is an AI model router and aggregation platform. Access 200+ language models through a unified OpenAI-compatible API. Execute tasks across multiple models, manage LLM profiles, monitor task runs, and track API usage and credits. Perfect for AI applications requiring multi-model support, cost optimization, and centralized AI infrastructure.

14 tools
Agent guide included
API Key
Start Chatting

Opens MCPBundles Studio with this server selected. After sign-in, chat and run tools from the same thread.

Browse all tools

AI Skill
SKILL.md

Domain knowledge for Minitap — workflow patterns, data models, and gotchas for your AI agent.

Minitap

Minitap is an AI model router and aggregation platform. Access 200+ language models through a unified OpenAI-compatible API. Multi-model support, cost optimization, centralized AI infrastructure.

Data Model

  • Models, LLM Profiles — available models and routing configs.
  • Tasks — LLM invocations; IDs use minitap:task:<id> format.
  • Task Runs — execution history; timeline for debugging.
  • Credits — usage and quota.

Gotchas

  • Task ID format: IDs are prefixed (e.g. minitap:task:123); generic fetch uses this format.
  • Rate limits: 60 calls/minute; use limit and pagination.

Tools in this Server (14)

Delete

Delete any Minitap resource by colon-routed ID. Supports api-key, llm-profile, task, and task-run resources. Deletion is permanent.

Fetch

Fetch any Minitap resource by colon-routed ID. Supports api-key, llm-profile, task, and task-run resources.

Minitap Chat Completions

OpenAI-compatible chat completions endpoint. Supports both streaming and non-streaming responses. Core feature for AI chat with mobile device control.

Minitap Get Credits

Get the user's credit balance, total credits, and total usage.

Minitap Get Task Run Timeline

Get consolidated timeline of all observability data (plans, subgoals, traces, agent thoughts) for a task run in chronological order.

Minitap List Llm Profiles

Get a paginated list of LLM profiles for the authenticated user.

Minitap List Models

Get all available AI models from OpenRouter that can be used with Minitap.

Minitap List Task Runs

List task runs for the authenticated user with pagination and filtering by task, status, and orphan status.

Minitap List Tasks

Get a paginated list of tasks with optional fuzzy search and sorting.

Minitap Top Up Credits

Create a Stripe PaymentIntent to top up credits. Returns payment URL.

Minitap Upsert Llm Profile

Create or update an LLM profile. Omit 'id' to create, provide 'id' to update.

Minitap Upsert Task

Create or update a task. Omit 'id' to create, provide 'id' to update.

Minitap Upsert Task Run

Create or update a task run. Omit 'id' to create (normal or orphan run), provide 'id' to update status/output.

Search

Search Minitap resources using natural language. Searches across API keys, LLM profiles, tasks, and task runs.

Frequently Asked Questions

What is the Minitap MCP server?

Minitap is an AI model router and aggregation platform. Access 200+ language models through a unified OpenAI-compatible API. Execute tasks across multiple models, manage LLM profiles, monitor task runs, and track API usage and credits. Perfect for AI applications requiring multi-model support, cost optimization, and centralized AI infrastructure. It provides 14 tools that AI agents can use through the Model Context Protocol (MCP).

How do I connect Minitap to my AI agent?

Add the MCPBundles server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL format is: https://mcp.mcpbundles.com/bundle/minitap. Authentication is handled automatically.

How many tools does Minitap provide?

Minitap provides 14 tools that can be called by AI agents, along with a SKILL.md that gives your AI agent domain knowledge about when and how to use them.

What authentication does Minitap require?

Minitap uses API Key. Minitap requires credentials. Connect via MCPBundles and authentication is handled automatically.

Setup Instructions

Connect Minitap to any MCP client in minutes

https://mcp.mcpbundles.com/bundle/minitap

What is MCP?

Model Context Protocol lets AI tools call external capabilities securely through a single URL. This bundle groups tools behind an MCP endpoint that many clients can use.

Use this bundle in 3 steps

  1. Copy the MCP URL above
  2. Open your AI tool and add a new MCP/connector
  3. Paste the URL and follow any auth prompts

Claude Desktop Users

Skip the manual setup! Use the .mcpb file format for one-click installation. Check the Claude Desktop tab for setup instructions.

Pick your tool tab for exact steps

Select ChatGPT, Cursor, Claude Code, or another tab for copy-paste config.

Ready to chat with Minitap?

Same flow: Studio opens on this server after sign-in. Keep chatting to call tools from the conversation.

Minitap MCP Server & Skill — 14 Tools