LogicMCP Server
Enables traceable requirement discovery, technical alignment, and ISO-aligned process checking through deterministic MCP tools and resources, without requiring an embedded LLM.
README
LogicMCP Server
This repository's deployable product is LogicMCP Server, implemented with the FastMCP framework for traceable requirement discovery, technical alignment, and ISO-aligned process checking. It contains no LLM and starts no CLI.
Install and run
.\install.bat
.\run.bat
The service listens on:
http://127.0.0.1:8000/mcp
run.bat performs a first-run installation when necessary. The root
requirements.txt, Dockerfile, and compose.yaml contain only the FastMCP
service boundary.
Optional Factory project
The repository also keeps a replaceable local execution chain for testing the MCP without an IDE:
future APP -> CLI/API adapter -> Python Factory -> LLM adapter -> MCP service
Install and run that optional chain separately, after the MCP service is running:
.\factory\cli\install.bat
.\factory\cli\run.bat
The factory exposes stable contracts and runtime builders from factory/.
Adapters, LLM providers, and the MCP implementation remain separate. A custom
CLI or API adapter only needs to preserve the Factory boundary; it does not
need to duplicate LLM-to-MCP transmission logic.
The code under factory/adapters/app_prototype/ is parked prototype material.
There is no supported APP adapter yet.
Directory boundaries
server/fastmcp_service/ deployable MCP service package
prompts/ LLM prompt contracts exposed by MCP
resources/ schemas, policies, and templates
tools/ deterministic MCP tools
factory/ optional Python workflow factory
contracts.py stable adapter/factory data contracts
controller/ workflow sequencing and MCP client port
llm/ replaceable LLM adapters
composition/ dependency assembly only
adapters/cli/ replaceable terminal adapter
adapters/app_prototype/ parked, unsupported APP prototype
cli/ separate no-IDE CLI project and installer
runtime/ Factory-owned logs, state, input, and output
tools/ MCP inspection/tuning/backup/update utilities
logs/ MCP Server logs only
output/ default MCP-owned file output
tests/ behavior and dependency-boundary tests
Dependency rules:
server/fastmcp_service/never importsfactory/or roottools/.- root
tools/never contains user-facing Factory/CLI entrypoints. - root
logs/is owned exclusively by the MCP Server. factory/llm/never imports MCP service internals.factory/controller/reaches MCP only through its gateway and LLM only throughBaseLLMClient.- adapters consume Factory contracts and builders; they do not own workflow sequencing.
- root installation and startup never install or start CLI, APP, or LLM code.
See INSTALL.MD for deployment and tool configuration, and MAP.MD for the maintenance index.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.