This repo adds an MCP server to Blockbench so agents can work with Blockbench through tools and prompts. The plugin exposes a local endpoint, with docs for connecting Claude Code and other MCP clients.
Builders who want an agent to edit or inspect Blockbench projects through MCP.
You can connect an agent to Blockbench instead of copying model steps back and forth by hand.
Runs a Blockbench MCP server at the configurable `:3000/bb-mcp` endpoint.
Shows setup for Claude Code, Claude Desktop, VS Code MCP config, Cline, Ollama, and OpenCode.
Includes prompt files under `prompts/` and a skills-based workflow note for orchestrating tool use.
Adds UI files under `ui/` for settings, status, and prompt preview dialogs.
Implements server tools and resources in `server/tools/` and `server/resources/` for Blockbench actions.
npx mcp-add --type http --url "http://localhost:3000/bb-mcp" --scope project
claude mcp add blockbench --transport http http://localhost:3000/bb-mcp
uvx ollmcp -u http://localhost:3000/bb-mcp
opencode mcp add
https://github.com/user-attachments/assets/ab1b7e63-b6f0-4d5b-85ab-79d328de31db
Open the desktop version of Blockbench, go to File > Plugins and click the "Load Plugin from URL" and paste in this URL:
https://jasonjgardner.github.io/blockbench-mcp-plugin/mcp.js
Configure the MCP server under Blockbench settings: Settings > General > MCP Server Port and MCP Server Endpoint
The following examples use the default values of :3000/bb-mcp
npx mcp-add --type http --url "http://localhost:3000/bb-mcp" --scope project
.vscode/mcp.json
{
"servers": {
"blockbench": {
"url": "http://localhost:3000/bb-mcp",
"type": "http"
}
}
}
claude_desktop_config.json (macOS/Linux)
{
"mcpServers": {
"blockbench": {
"command": "npx",
"args": ["-y", "mcp-remote", "http://localhost:3000/bb-mcp"]
}
}
}
claude_desktop_config.json (Windows)
{
"mcpServers": {
"blockbench": {
"command": "cmd",
"args": ["/c", "npx", "-y", "mcp-remote", "http://localhost:3000/bb-mcp"]
}
}
}
claude mcp add blockbench --transport http http://localhost:3000/bb-mcp
{
"mcpServers": {
"blockbench": {
"serverUrl": "http://localhost:3000/bb-mcp"
}
}
}
cline_mcp_settings.json
{
"mcpServers": {
"blockbench": {
"url": "http://localhost:3000/bb-mcp",
"type": "streamableHttp",
"disabled": false,
"autoApprove": []
}
}
}
uvx ollmcp -u http://localhost:3000/bb-mcp
Recommended: jonigl/mcp-client-for-ollama
opencode mcp add
See sample project for prompt examples.
Use Agent Skills to orchestrate tool usage.
See CONTRIBUTING.md for detailed instructions on setting up the development environment and how to add new tools, resources, and prompts.
Sign in to join the discussion.
No comments yet. Be the first to say what this is good for.
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.
Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Local-first code intelligence graph for MCP and CLI. Builds a persistent map of your codebase so AI coding tools read only what matters, with benchmarked context reductions on reviews and large-repo workflows.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
20 MB lightweight cross-platform database client for 90+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Docker. | 轻量级跨平台数据库管理工具，支持 MySQL、PostgreSQL、SQLite、Redis、MongoDB、达梦等 90+ 数据库，提供桌面端、Docker、CLI、内置 AI 助手和 MCP Server。