LSP-Claw
About
LSP-Claw is an MCP server that lets an AI agent safely build, run, and debug Lua/LSP web apps inside a controlled Mako/Xedge/BAS lab, including on embedded or RTOS devices.
Details
- Author
- realtimelogic
- Categories
- Developer Tools, Other
Jump to
Setup
Install LSP-Claw in your MCP client (Claude Desktop, Cursor, Windsurf, and others).
Repository: https://github.com/realtimelogic/LSP-Claw
Follow the installation instructions in the repository README, then restart your MCP client.
This quick start is for running LSP-Claw with the Mako Server Developer Edition. See thedetailed instructionsfor other setups, including usingXedge standalone, configuration options, lab management, backups, transfers, and tutorials.
Start Device Interfaces with Light Dashboard
For device-management applications, useLight-Dashboard.
- An AI agent withMCP support, such as Codex, installed on your computer.
- TheMako Server Developer Edition. Running Mako as a service is preferred. Thedownload pageincludes a prompt you can give your AI agent to guide you through downloading, installing, and running it as a service.
-
Install and start Mako using the Developer Edition instructions. You may optionally initialize the MCP authentication token on the first start:
See thecommand-line token instructions.
Add an MCP server namedlsp_clawto your AI agent using this URL:
Restart the agent or open a new session so it discovers LSP-Claw. SeeConfigure Your AI Agentif you need agent-specific configuration details.
The Mako Server Developer Edition is the easiest way to get started because it includes LSP-Claw and the required Mako resources in one ready-to-run package. This avoids manually installing and configuring the application.
Prime the agent before asking it to build anything:
Use LSP-Claw for this session. Check the runtime and lab status, list the available labs, and tell me what you found. Do not change anything yet. Work only through LSP-Claw; if its tools are unavailable, stop and tell me.
Use LSP-Claw to build a device management interface using Light-Dashboard/custom. Check the runtime and lab, then ask what device, pages, live data, commands, and visual style I need. Build and test the interface and give me its URL.
This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.
Policy-gated MCP tools that let coding agents build, flash, stimulate and observe real embedded hardware (OpenOCD, pyOCD, STM32CubeProgrammer, serial, CAN).
A stateful LSP runtime for AI agents: warm language server sessions with 50+ tools for go-to-definition, find-references, diagnostics, rename, and more across 30+ languages.
MCP server for the Brainfuck programming language that allows your favourite LLM to debug Brainfuck programs.
Diagnoses token waste in Claude Code sessions with 6 anomaly types and severity scoring. Fully local.
MCP server that gives coding agents program-analysis primitives — data flow, call graphs, taint analysis — so they reason from ground truth instead of grep-and-guess. (same as the GitHub About — keeps your messaging consistent across the web).
An MCP service that equips your workspace with a complete set of AI-accessible development tools for reading, editing, executing, and managing code.
Fennara MCP connects AI agents like Codex, Cursor, Claude Code, and Claude Desktop to Godot-aware tools for real Godot projects. It focuses on feedback from Godot: GDScript diagnostics, scene validation, runtime errors, scene inspection, node properties, screenshots, SemanticSearch, and patch-and-rerun workflows.
Search verified engineering fixes by error message or technology. Step-by-step solutions with trust scores, built for developers and AI agents.
Integrates with Language Server Protocol (LSP) to provide features like code completion, diagnostics, and hover information.
Visual Studio extension with 20 Roslyn-powered MCP tools for AI assistants. Semantic code navigation, symbol search, inheritance, call graphs, safe rename, build/test.
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
