MCP Eval Runner
A standardized testing harness for MCP servers and agent workflows
按你想完成的任务或你使用的应用搜索,再按分类筛选。
按仓库的 GitHub 星标数从高到低排序。星标代表关注度,不代表质量。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
A standardized testing harness for MCP servers and agent workflows
Step-by-step observability for MCP agent workflows
Plaid MCP — wraps Plaid Sandbox API (sandbox.plaid.com)
Pitch Protocol — agent-native venture-capital infrastructure (pitchprotocol.vc).
Go modules MCP — wraps proxy.golang.org
Pennsylvania Consolidated Statutes — state statutes by citation.
Cited cloud best practices and a rules-based review of Terraform, CloudFormation, and Kubernetes.
Scores your code across 12 areas, with findings, fix prompts, and re-assessment in your AI agent
Packagephobia MCP — install-size analysis for npm packages
Oregon Revised Statutes — state statutes by citation.
OpenIBAN MCP — validate an IBAN's checksum + bank code and resolve the bank name / BIC / city.…
MCP server for agent-driven React Native and Expo development and mobile testing
MCP gateway aggregating MCP servers and OpenAPI/Swagger REST APIs behind one MCP endpoint
25 read-only agent utilities: token safety, approvals, tx decode, EIP-712 risk, DNS, time; free tier
39 agent tools: x402 pay gateway, precheck, token safety, tx decode, DNS; credits or 30-day plan
iOS App Store revenue and download estimates with confidence labels, for any app by name or id.
Computer use for coding agents on macOS: JS scripts, accessibility diffs, background input.
Start, stop and read logs of your local dev servers from Claude Code, Cursor and Codex.
Manage pfSense firewalls through AI assistants — rules, DHCP, DNS, and more
Manage pfSense firewalls through AI assistants — rules, DHCP, DNS, and more
Manage Proxmox VE clusters through AI assistants — VMs, containers, and more
Manage Proxmox VE clusters through AI assistants — VMs, containers, and more
DNS, email auth, TLS, BGP/RPKI, WHOIS and subnet tools with plain-English fixes, plus webhook URLs.
MCP server for MikroTik RouterOS and SwOS: typed tools, dry-run, RBAC, audit logs, and rollback.