MCPBox
MCPBox is a Go-based control plane for MCP servers. It lets you group local and remote MCP backends by project, inspect what they expose, monitor traffic, and publish a single project URL for AI clients such as Claude, Cursor, Codex, LM Studio, and local Ollama-based workflows.
Why MCPBox
Managing several MCP servers quickly turns into a mix of JSON snippets, terminal tabs, and half-documented local setup. MCPBox gives you one embedded UI and one local binary for the operational side of that work.
Key capabilities:
- Project-based organization for local
stdioand remoteHTTP streamingMCP servers - One project MCP endpoint at
/mcp/{project_token}that aggregates all enabled servers in the project - Built-in Knowledge Base / RAG collections with local indexing for code, text, CSV, XLSX, DOCX, PPTX, and text-based PDF
- Live inspection of
tools,resources,prompts, and nearby README files for localstdioservers - Health checks on create, update, manual check, and local server start
- Audit log for MCP traffic and control actions
- Project pause/resume and per-server enable/disable controls
- Embedded Market / Catalog flow for syncing, installing, verifying, and uninstalling integrations
- One-click Ollama and llama.cpp launchers for local MCP testing
- Single-binary deployment with embedded React UI and local SQLite storage
Quick Start
- Download the binary for your OS from the latest release, or build from source.
- Run
MCPBox. - Open
http://127.0.0.1:38180/if the browser does not open automatically. - Create a project.
- Add local
stdioservers or remoteHTTP streamingservers. - Copy the project endpoint from the UI and connect your AI client to
/mcp/{project_token}.
For local Ollama testing:
- Make sure
ollamais installed. - Open a project that has at least one enabled MCP server.
- Choose a local Ollama model in the UI.
- Click
Launch Ollama.
For LM Studio:
- Open a project that has at least one enabled MCP server or connected knowledge base.
- Click
Launch Project. - Choose
Add to LM Studio. - Confirm the deeplink in LM Studio when your OS opens it.
For local llama.cpp Web UI testing:
- Make sure
llama-serveris installed and available inPATH. - Set
MCPBOX_LLAMACPP_MODELor choose a local.ggufmodel in the launch dialog. - Open a project with an enabled MCP server or connected knowledge base.
- Click
Launch Projectand choose the llama.cpp action. - MCPBox starts
llama-server, applies the project prompt as a system prompt, and opens the Web UI.
Build From Source
Requirements:
- Go
1.26+ - Node.js and npm
Build steps:
npm --prefix html install
npm --prefix html run build
go build -o MCPBox .
Run from source:
go run .
Default port: 38180
Documentation
- README-ru.md - Russian user guide
- DEVELOPER.md - developer guide, API notes, and architecture
- DEVELOPER-ru.md - Russian developer guide
Notes
- MCPBox uses a local SQLite database by default.
- The current Knowledge Base / RAG implementation uses local full-text indexing with Bleve. It does not build or require embedding indexes at this stage.
- The Docker runtime support in
1.2.1is intentionally an MVP. Advanced container features such as compose-style orchestration, custom networks, and volume presets are not fully implemented yet. - The
go_installpackage flow in1.2.2assumes the target integration can be installed throughgo install module/path@versionand exposed through a concrete binary entry point. - Secret masking is applied in the UI and catalog install flow. Existing manually configured servers that still pass secrets directly in command arguments should be migrated to environment variables for full process-list safety.
- The Ollama launcher is shown only when
ollamais installed on the machine. - The llama.cpp launcher requires
llama-server; project prompts are passed through--system-prompt-fileand are also exposed through MCPprompts/listasproject_prompt. - Local server inspection is available for
stdioservers only.
No comments yet
Be the first to share your take.