beret MCP Server
chapeaux/beret
Are you the maintainer of chapeaux/beret? Claim this listing →
MCP server that builds an in-memory RDF knowledge graph of your codebase and exposes it via SPARQL queries
Add AgentRank to Claude Code Discover and compare tools like chapeaux/beret — your AI finds the right one automatically
Get API Access → claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
chapeaux/beret is a Rust MCP server licensed under MIT. MCP server that builds an in-memory RDF knowledge graph of your codebase and exposes it via SPARQL queries
Ranked #31 out of 100 indexed tools.
Actively maintained with commits in the last week.
Ecosystem
Rust MIT
Score Breakdown
Stars 15% 2
2 stars → early stage
Freshness 25% today
Last commit today → actively maintained
Issue Health 25% 50%
No issues filed → no history to score
Contributors 10% 1
1 contributor → solo project
Dependents 25% 0
No dependents → no downstream usage
npm Downloads N/A
PyPI Downloads N/A
Forks 0
Description Good
License MIT
Weights: Freshness 25% · Issue Health 25% · Dependents 25% · Stars 15% · Contributors 10% · How we score →
How to Improve
Description low impact
Contributors medium impact
Dependents medium impact
Matched Queries
From the README
# Beret An MCP server that builds an in-memory RDF knowledge graph of your codebase and exposes it through purpose-built tools and SPARQL queries. It parses 17 programming languages using structural AST analysis, extracts metadata from config files and documents, records binary file information, and lets you explore everything through the Model Context Protocol. ## Installation | Method | Command | Requirements | |--------|---------|--------------| | npx | `npx @chapeaux/beret` | Node.js | | npx (JSR) | `npx jsr:@chapeaux/beret` | Node.js | | Cargo | `cargo install chapeaux-beret` | Rust 1.85+ | | Source | `cargo build --release` | Rust 1.85+ | The release profile enables LTO and single codegen unit for maximum binary performance. ## Usage The server starts with an empty knowledge graph and indexes on demand. Call `refresh_index` with a directory path to populate the graph, then use the other tools to explore. This lets you launch one server and re-target it at different projectsRead full README on GitHub →
Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.