Happy slice of mcp pizzaMCP.pizza

mcp-inception

MCP.Pizza Chef: tanevanwifferen

mcp-inception is an MCP client designed to call and delegate tasks to other MCP clients, enabling offloading of context windows and parallel or map-reduce execution of tasks. It acts as an agent for your agent, facilitating complex workflows by splitting tasks between models and managing multi-step reasoning across clients. Built with TypeScript and leveraging mcp-client-cli, it simplifies scaling LLM interactions and task delegation within MCP ecosystems.

Unmaintained · No commits in 18 months.

Use This MCP client To

Delegate complex queries to specialized MCP clients Offload large context windows to separate clients Execute parallel or map-reduce style task workflows Chain multiple MCP clients for multi-step reasoning Split tasks between different LLM models efficiently Manage and orchestrate multi-client LLM interactions

README

Disclaimer

Ok this is a difficult one. Will take some setting up unfortunately. However, if you manage to make this more straightforward, please send me PR's.

mcp-inception MCP Server

Call another mcp client from your mcp client. Delegate tasks, offload context windows. An agent for your agent!

This is a TypeScript-based MCP server that implements a simple LLM query system.

  • MCP Server and Client in one
  • Made with use of mcp-client-cli
  • Offload context windows
  • Delegate tasks
  • Parallel and map-reduce execution of tasks

Inception Server MCP server

Features

Tools

  • execute_mcp_client - Ask a question to a separate LLM, ignore all the intermediate steps it takes when querying it's tools, and return the output.
    • Takes question as required parameters
    • Returns answer, ignoring all the intermediate context
  • execute_parallel_mcp_client - Takes a list of inputs and a main prompt, and executes the prompt in parallel for each string in the input. E.G. get the time of 6 major cities right now - London, Paris, Tokyo, Rio, New York, Sidney.
    • takes main prompt "What is the time in this city?"
    • takes list of inputs, London Paris etc
    • runs the prompt in parallel for each input
    • note: wait for this before using this feature
  • execute_map_reduce_mcp_client - Process multiple items in parallel and then sequentially reduce the results to a single output.
    • Takes mapPrompt with {item} placeholder for individual item processing
    • Takes reducePrompt with {accumulator} and {result} placeholders for combining results
    • Takes list of items to process
    • Optional initialValue for the accumulator
    • Processes items in parallel, then sequentially reduces results
    • Example use case: Analyze multiple documents, then synthesize key insights from all documents into a summary

Development

Dependencies:

mcp-inception FAQ

How does mcp-inception handle task delegation?
It calls other MCP clients to process tasks, returning only final answers.
Can mcp-inception run tasks in parallel?
Yes, it supports parallel and map-reduce execution of tasks across clients.
Is mcp-inception both a client and a server?
Yes, it functions as both to facilitate communication between MCP clients.
What programming language is mcp-inception built with?
It is built using TypeScript and uses the mcp-client-cli framework.
How does mcp-inception help with context window limits?
It offloads large context windows to other MCP clients to avoid hitting limits.
Can mcp-inception integrate with multiple LLM providers?
Yes, it can delegate tasks to clients using OpenAI, Claude, Gemini, and others.
Is setting up mcp-inception complex?
It requires some configuration but enables powerful multi-client orchestration once set up.
Does mcp-inception return intermediate tool steps from delegated clients?
No, it returns only the final output, ignoring intermediate steps.