AI Plugin Index
MCP Evals
Verified · npm:@sbissoliMCP server by SidneyBissoli · updated · ★ 1 · 482 downloads a week
Harness de evals para servidores MCP: seleção de tool em turno único (catálogo, fixtures, scorer, gate, runner via Messages API) e SESSÃO LONGA (loop client-side por stdio, A/B do bloco `retrieval`, métrica de chamadas ruins por tarefa, teto de gasto, NDJ MCP Evals is published by npm:@sbissoli from its verified domain in the official MCP Registry.
Last commit in the past day
MIT: permissive, fine for commercial use
Clear description, published package or server URL, original repository
Not checked yet. What we check
Install MCP Evals
Built from the published package, never by AIclaude mcp add mcp-evals -- npx -y @sbissoli/mcp-evalsRun in your terminal. Add --scope user to use it in every project.
{
"mcpServers": {
"mcp-evals": {
"command": "npx",
"args": [
"-y",
"@sbissoli/mcp-evals"
]
}
}
}Settings, Developer, Edit config. Paste into claude_desktop_config.json and restart.
{
"mcpServers": {
"mcp-evals": {
"command": "npx",
"args": [
"-y",
"@sbissoli/mcp-evals"
]
}
}
}Add to ~/.cursor/mcp.json (all projects) or .cursor/mcp.json (this project).
{
"servers": {
"mcp-evals": {
"command": "npx",
"args": [
"-y",
"@sbissoli/mcp-evals"
]
}
}
}Add to .vscode/mcp.json. VS Code uses "servers", not "mcpServers".
codex mcp add mcp-evals -- npx -y @sbissoli/mcp-evals{
"mcpServers": {
"mcp-evals": {
"command": "npx",
"args": [
"-y",
"@sbissoli/mcp-evals"
]
}
}
}Add to ~/.gemini/config/mcp_config.json (all projects) or .agents/mcp_config.json (this project).
gemini mcp add mcp-evals npx -y @sbissoli/mcp-evalsGemini CLI was replaced by Antigravity CLI in June 2026 and remains only for enterprise licences and paid API keys.
MCP servers run with your permissions and can read what you give them access to. Some need an API key: check the README and add it under env in the mcp-evals block.
Alternatives to MCP Evals
All alternatives →
Meeting bot and transcripts for Google Meet, Teams and Zoom. Live or after, speakers labelled.
Minimal chat-first app with durable threads, actions, and the app-agent loop
Agent-Native Superhuman - email client with keyboard shortcuts and AI triage
Generate QR codes for URLs, PIX, Wi-Fi, vCards, WhatsApp and more. For AI agents.
Host-side Model Context Protocol client for TanStack AI: discover and run MCP server tools, resources, and prompts in any adapter's chat() loop, with generated end-to-end types.
Cited company knowledge from Slack, meetings, transcripts, and decisions
MCP Evals: common questions
How do I install MCP Evals?
In Claude Code run claude mcp add mcp-evals -- npx -y @sbissoli/mcp-evals. For Claude Desktop, Cursor and VS Code, paste the config shown above and restart. See the install guides.
Is MCP Evals the official server?
MCP Evals is published by npm:@sbissoli from its verified domain in the official MCP Registry.
Is MCP Evals free?
The code is published under the MIT licence. The service it connects to may have its own pricing.
Is MCP Evals safe to use?
It scores 79 of 100. Grades: maintenance A, licence A, quality C. The security check has not run for it yet. Review the code before you install. How grades work.
What are alternatives to MCP Evals?
Similar MCP servers: Vexa, Agent-Native Chat, Agent-Native Mail, QR Rápido.
Does MCP Evals work with ChatGPT?
Not directly. It runs locally, and ChatGPT only connects to remote servers with a URL. Use it in Claude Code, Claude Desktop, Cursor, VS Code or Codex.