Vibe Code Benchmark

MCPOpen Source37.6

by rlancemartin • Data & Databases

A benchmarking tool for testing code agents in connecting to external data sources.

Example Use Cases

1
Connect to external data sources efficiently.
2
Evaluate different context retrieval methods.
3
That require benchmarking to enhance their integrations with MCP servers.

Description

The Vibe Code Benchmark is designed to evaluate how different code agents, such as Claude Code and Cursor, can connect to external data sources using various context retrieval methods. It tests context stuffing, standard and optimized llms.txt files, and vector databases to determine the most effective integration with code agents. This setup leverages MCP servers for semantic search, supports deployment testing, and includes a comprehensive evaluation framework.

Quick Actions

View on GitHub

Security

Scanned 3 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

D40/100

3/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelUnknown

Capabilities0 Tools / 0 Prompts / 0 Resources

Ownerrlancemartin

CategoryData & Databases

DependenciesStandalone