MCP Inception MCP Server
The MCP Inception MCP Server allows you to delegate tasks and offload context windows using an agent-based LLM query system. It essentially acts as an agent for agents with three main capabilities:
Execute MCP Client: Offload tasks to another AI for research purposes, fetching data without intermediate steps.
Execute Parallel MCP Client: Run multiple AI tasks in parallel, returning responses as JSON key-value pairs.
Execute Map-Reduce MCP Client: Process multiple items in parallel (map) and then sequentially combine the results (reduce) into a single output.
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., "@MCP Inception MCP Server execute_mcp_client: summarize this research paper on quantum computing"
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.
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
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
mapPromptwith{item}placeholder for individual item processingTakes
reducePromptwith{accumulator}and{result}placeholders for combining resultsTakes list of
itemsto processOptional
initialValuefor the accumulatorProcesses items in parallel, then sequentially reduces results
Example use case: Analyze multiple documents, then synthesize key insights from all documents into a summary
Related MCP server: Orchestration MCP
Development
Dependencies:
Install mcp-client-cli
Also install the config file, and the mcp servers it needs in
~/.llm/config.json
create a bash file somewhere that activates the venv and executes the
llmexecutable
#!/bin/bash
source ./venv/bin/activate
llm --no-confirmationsinstall package
Install dependencies:
npm installBuild the server:
npm run buildFor development with auto-rebuild:
npm run watchInstallation
To use with Claude Desktop, add the server config:
On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json
{
"mcpServers": {
"mcp-inception": {
"command": "node",
"args": ["~/Documents/Cline/MCP/mcp-inception/build/index.js"], // build/index.js from this repo
"disabled": false,
"autoApprove": [],
"env": {
"MCP_INCEPTION_EXECUTABLE": "./run_llm.sh", // bash file from Development->Dependencies
"MCP_INCEPTION_WORKING_DIR": "/mcp-client-cli working dir"
}
}
}
}Debugging
Since MCP servers communicate over stdio, debugging can be challenging. We recommend using the MCP Inspector, which is available as a package script:
npm run inspectorThe Inspector will provide a URL to access debugging tools in your browser.
Available Tools
3 toolsexecute_map_reduce_mcp_clientC
Process multiple items in parallel then sequentially reduce the results to a single output.
Inputs: mapPrompt (required), reducePrompt (required), items (required), initialValue.
execute_mcp_clientB
Offload certain tasks to AI. Used for research purposes, do not use for code editing or anything code related. Only used to fetch data.
Inputs: command (required).
execute_parallel_mcp_clientC
Execute multiple AI tasks in parallel, with responses in JSON key-value pairs.
Inputs: prompt (required), items (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
The three tools have overlapping purposes centered around executing MCP client tasks, with unclear boundaries. execute_map_reduce_mcp_client and execute_parallel_mcp_client both handle parallel execution, while execute_mcp_client is described more broadly for offloading tasks, leading to potential confusion about when to use each.
All tool names follow a consistent snake_case pattern with a 'execute_' prefix, making them predictable and readable. The naming structure is uniform across the set, with no deviations in style or convention.
With only 3 tools, the set feels thin for a server named 'MCP Inception MCP Server', which suggests a broader scope. While the tools cover parallel and sequential execution, the limited count may not fully support complex workflows or diverse use cases implied by the server name.
The tool set is severely incomplete for an MCP server, lacking basic operations like configuration, monitoring, or error handling. It focuses narrowly on execution variants without covering setup, management, or integration aspects, leaving significant gaps for agent-driven tasks.
Maintenance
Related MCP Connectors
Remote MCP server for The Colony — a social network for AI agents (posts, DMs, search, marketplace).
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
MCP Server for an Agent Task Marketplace
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceA TypeScript-based server that connects MCP Clients to Dify applications, dynamically exposing Dify applications as tools that can be used directly within the MCP Client.21 npm5MIT
- FlicenseAqualityDmaintenanceA TypeScript MCP server for launching, tracking, and managing external coding-agent runs across local and remote backends like Codex and Claude Code. It allows top-level agents to orchestrate subagents through tools for spawning tasks, polling events, and handling interactive sessions.72-
- AlicenseNot gradedqualityDmaintenanceA self-hosted MCP server that provides a single execute_code tool, enabling agents to write TypeScript to call multiple REST APIs via fetch() with transparent credential injection, reducing token usage by keeping intermediate results in the sandbox.11BSD 3-Clause
- AlicenseNot gradedqualityCmaintenanceA TypeScript gateway that aggregates multiple MCP servers into a single endpoint, enabling AI agents to access tools from many backends through one connection.53 npm2ISC