mod-dev-mcp
A development tooling MCP server for tModLoader mod projects, enabling building, formatting, and log tailing operations directly from an MCP client.
README
mod-dev-mcp
A small MCP (Model Context Protocol) dev-tooling server for the tModLoader mod projects in this workspace (Ben10Mod, MistbornModOwnBlend). Registered workspace-wide via ../.mcp.json so Claude Code auto-connects.
It does not connect to a running game — it's build/format/log tooling only.
Tools
- build_mod
{ modPath, configuration? }— runsdotnet build, returns structured diagnostics from both build passes (see below), whether a.tmodwas produced, and a tail of raw output. - format_mod
{ modPath, check? }— runs CSharpier. - tail_tmodloader_log
{ lines?, logFile? }— tails tModLoader's client/server log. - check_environment
{}— reports .NET SDK presence, whether the workspacetModLoader.targetsand the officialModSources/tModLoader.targetsexist, and whether theBen10Mod/MistbornModOwnBlendsymlinks inModSourcesresolve correctly.
Why two-pass diagnostic parsing
dotnet build on a tModLoader mod runs an ordinary C# compile, then (if that succeeds) a nested dotnet tModLoader.dll -build ... packaging step that produces the .tmod. Ordinary compile errors come back as standard MSBuild diagnostics (file(line,col): error CSxxxx: ...); packaging-level failures (missing native libraries, mod locked by a running game, bad build.txt/.hjson/textures) come back in tModLoader's own differently-shaped log lines instead (tModLoader : Mod Build error TMLxxx: ...). src/parsers/msbuildDiagnostics.ts handles both and tags each diagnostic's source accordingly. It was built against real captured samples of both failure shapes, not assumed formats — see ../Ben10Mod/CLAUDE.md for the environment quirks that produced them (missing DYLD_LIBRARY_PATH for headless builds, and the "close tModLoader before building via CLI" conflict).
Development
npm install
npm run build # compiles to dist/
npm run dev # run directly via tsx without building
The server communicates over stdio, so it's not meant to be run standalone outside an MCP client — npm run dev/npm start will just sit waiting for a client to connect.
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.