About BRICO feature memory
BRICO is a feature-memory MCP server for coding agents. It indexes features from other projects, assesses their fit for the current project, and helps agents integrate them.
Key features
- 01Index features from existing projects
- 02Assess fit for the current project
- 03Help coding agents reuse features
Use cases
- 01Find reusable features across past projects
- 02Identify features suited to a current project
MCP support
BRICO runs as an MCP server for coding agents, including Claude Code and Cursor. It exposes indexed project features and their relevance for reuse.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
npx -y bricowerxBRICO_TOKENSecretYour BRICO Builder invite token (bt_…). Optional if you ran `brico login`.Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEBRICO releases
Release binaries for BRICO: your feature memory. BRICO finds the features you've built in your other projects, tells you how well each fits the project you're in, and lets your coding agent wire it in.
This repository holds release downloads only. Docs: https://www.bricowerx.com
Install
npm i -g bricowerx
# or
curl -fsSL https://github.com/ScienceWerx-Inc/brico_release/releases/latest/download/install.sh | sh
Use it in your coding agent (MCP)
brico login bt_… # your BRICO Builder invite token
brico index ~/code/an-old-project # remember its features
claude mcp add brico -- npx -y bricowerx mcp # Claude Code
Cursor, in ~/.cursor/mcp.json:
{ "mcpServers": { "brico": { "command": "npx", "args": ["-y", "bricowerx", "mcp"] } } }
Every release includes SHA256SUMS.txt; the installers verify downloads against it.
MCP registry
server.json is the server's MCP registry entry, io.github.ScienceWerx-Inc/brico. After each npm release, copy it from the source repository and run Actions → MCP registry → Run workflow.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.