iris-eval/mcp-server

Add full-text search to trace queries 18 days ago

enhancement good first issue effort: large dashboard

7

The agent eval standard for MCP — score output quality, catch safety failures, enforce cost budgets

TypeScript

#agent-evaluation#ai-agent#claude#eval#evaluation#llm#mcp#mcp-server#model-context-protocol#observability#security#tracing

Create Python SDK for HTTP transport 18 days ago

enhancement good first issue effort: large

iris-eval/mcp-server

7

The agent eval standard for MCP — score output quality, catch safety failures, enforce cost budgets

TypeScript

#agent-evaluation#ai-agent#claude#eval#evaluation#llm#mcp#mcp-server#model-context-protocol#observability#security#tracing

Add webhook notifications for evaluation failures 18 days ago

enhancement good first issue effort: medium

iris-eval/mcp-server

7

The agent eval standard for MCP — score output quality, catch safety failures, enforce cost budgets

TypeScript

#agent-evaluation#ai-agent#claude#eval#evaluation#llm#mcp#mcp-server#model-context-protocol#observability#security#tracing

Add CSV/JSON export to dashboard 18 days ago

enhancement good first issue effort: medium dashboard

iris-eval/mcp-server

7

The agent eval standard for MCP — score output quality, catch safety failures, enforce cost budgets

TypeScript

#agent-evaluation#ai-agent#claude#eval#evaluation#llm#mcp#mcp-server#model-context-protocol#observability#security#tracing

Add OpenTelemetry trace export support 6 months ago

enhancement good first issue effort: large

iris-eval/mcp-server

7

The agent eval standard for MCP — score output quality, catch safety failures, enforce cost budgets

TypeScript

#agent-evaluation#ai-agent#claude#eval#evaluation#llm#mcp#mcp-server#model-context-protocol#observability#security#tracing

Add evaluation score trend sparkline to dashboard overview 6 months ago

enhancement good first issue effort: small

iris-eval/mcp-server

7

The agent eval standard for MCP — score output quality, catch safety failures, enforce cost budgets

TypeScript

#agent-evaluation#ai-agent#claude#eval#evaluation#llm#mcp#mcp-server#model-context-protocol#observability#security#tracing

Add dark/light theme toggle to dashboard 6 months ago

enhancement good first issue effort: small

iris-eval/mcp-server

7

The agent eval standard for MCP — score output quality, catch safety failures, enforce cost budgets

TypeScript

#agent-evaluation#ai-agent#claude#eval#evaluation#llm#mcp#mcp-server#model-context-protocol#observability#security#tracing

Add copy-to-clipboard for trace IDs in dashboard 6 months ago

enhancement good first issue effort: small

iris-eval/mcp-server

7

The agent eval standard for MCP — score output quality, catch safety failures, enforce cost budgets

TypeScript

#agent-evaluation#ai-agent#claude#eval#evaluation#llm#mcp#mcp-server#model-context-protocol#observability#security#tracing

Open Issues Need Help