mirror of
https://github.com/affaan-m/everything-claude-code.git
synced 2026-04-01 14:43:28 +08:00
* feat(skills): add evalview-agent-testing skill and MCP server Add EvalView as a regression testing skill for AI agents. EvalView snapshots agent behavior (tool calls, parameters, output), then diffs against baselines after every change — catching regressions before they ship. Skill covers: - CLI workflow (init → snapshot → check → monitor) - Python API (gate() / gate_async() for autonomous loops) - Quick mode (no LLM judge, $0, sub-second) - CI/CD integration (GitHub Actions with PR comments) - MCP integration (8 tools for Claude Code) - Multi-turn test cases - OpenClaw integration for autonomous agents Also adds evalview MCP server to mcp-servers.json. * fix(skills): pin action SHA and remove unvetted external links - Pin hidai25/eval-view action to commit SHA instead of @main - Replace external GitHub links with PyPI package link (vetted registry) Addresses cubic-dev-ai review feedback. * fix(skills): replace third-party action with pip install + CLI Use plain pip install + evalview CLI instead of a third-party GitHub Action. No external actions, no secrets passed to unvetted code. Addresses cubic-dev-ai supply-chain review feedback. * fix(skills): add destructive revert warning for gate_or_revert Add prominent warning that gate_or_revert runs git checkout, discarding uncommitted changes. Documents the revert_cmd override for safer alternatives like git stash. Addresses cubic-dev-ai review feedback. * fix(skills): pin pip version range and document fail-on tradeoffs - Pin evalview to >=0.5,<1 to prevent breaking CI on major upgrades - Document --fail-on REGRESSION vs --strict tradeoff so users understand what gates and what passes through Addresses greptile-apps review feedback. * fix: use python3 -m evalview for venv compatibility in MCP config Follows the same pattern as insaits entry. Resolves correctly even when evalview is installed in a virtual environment that isn't on the system PATH. * fix: align MCP install command with mcp-servers.json pattern Use python3 -m evalview mcp serve consistently across both the skill docs and the MCP config catalog. * fix: use evalview CLI entry point for MCP command pip install evalview installs the evalview binary to PATH, so using it directly is consistent with the install docs and avoids python3 version mismatch issues. * fix: pin install version to match CI section * fix: pin all pip install references consistently * fix: add API key placeholder and pin install version in MCP config Add OPENAI_API_KEY env placeholder matching other entries. Note that the key is optional — deterministic checks work without it. Pin install version to match skill docs. * fix: guard score_delta format for non-scored statuses --------- Co-authored-by: Affaan Mustafa <me@affaanmustafa.com>
172 lines
6.5 KiB
JSON
172 lines
6.5 KiB
JSON
{
|
|
"mcpServers": {
|
|
"github": {
|
|
"command": "npx",
|
|
"args": ["-y", "@modelcontextprotocol/server-github"],
|
|
"env": {
|
|
"GITHUB_PERSONAL_ACCESS_TOKEN": "YOUR_GITHUB_PAT_HERE"
|
|
},
|
|
"description": "GitHub operations - PRs, issues, repos"
|
|
},
|
|
"firecrawl": {
|
|
"command": "npx",
|
|
"args": ["-y", "firecrawl-mcp"],
|
|
"env": {
|
|
"FIRECRAWL_API_KEY": "YOUR_FIRECRAWL_KEY_HERE"
|
|
},
|
|
"description": "Web scraping and crawling"
|
|
},
|
|
"supabase": {
|
|
"command": "npx",
|
|
"args": ["-y", "@supabase/mcp-server-supabase@latest", "--project-ref=YOUR_PROJECT_REF"],
|
|
"description": "Supabase database operations"
|
|
},
|
|
"memory": {
|
|
"command": "npx",
|
|
"args": ["-y", "@modelcontextprotocol/server-memory"],
|
|
"description": "Persistent memory across sessions"
|
|
},
|
|
"omega-memory": {
|
|
"command": "uvx",
|
|
"args": ["omega-memory", "serve"],
|
|
"description": "Persistent agent memory with semantic search, multi-agent coordination, and knowledge graphs — run via uvx (richer than the basic memory store)"
|
|
},
|
|
"sequential-thinking": {
|
|
"command": "npx",
|
|
"args": ["-y", "@modelcontextprotocol/server-sequential-thinking"],
|
|
"description": "Chain-of-thought reasoning"
|
|
},
|
|
"vercel": {
|
|
"type": "http",
|
|
"url": "https://mcp.vercel.com",
|
|
"description": "Vercel deployments and projects"
|
|
},
|
|
"railway": {
|
|
"command": "npx",
|
|
"args": ["-y", "@railway/mcp-server"],
|
|
"description": "Railway deployments"
|
|
},
|
|
"cloudflare-docs": {
|
|
"type": "http",
|
|
"url": "https://docs.mcp.cloudflare.com/mcp",
|
|
"description": "Cloudflare documentation search"
|
|
},
|
|
"cloudflare-workers-builds": {
|
|
"type": "http",
|
|
"url": "https://builds.mcp.cloudflare.com/mcp",
|
|
"description": "Cloudflare Workers builds"
|
|
},
|
|
"cloudflare-workers-bindings": {
|
|
"type": "http",
|
|
"url": "https://bindings.mcp.cloudflare.com/mcp",
|
|
"description": "Cloudflare Workers bindings"
|
|
},
|
|
"cloudflare-observability": {
|
|
"type": "http",
|
|
"url": "https://observability.mcp.cloudflare.com/mcp",
|
|
"description": "Cloudflare observability/logs"
|
|
},
|
|
"clickhouse": {
|
|
"type": "http",
|
|
"url": "https://mcp.clickhouse.cloud/mcp",
|
|
"description": "ClickHouse analytics queries"
|
|
},
|
|
"exa-web-search": {
|
|
"command": "npx",
|
|
"args": ["-y", "exa-mcp-server"],
|
|
"env": {
|
|
"EXA_API_KEY": "YOUR_EXA_API_KEY_HERE"
|
|
},
|
|
"description": "Web search, research, and data ingestion via Exa API — prefer task-scoped use for broader research after GitHub search and primary docs"
|
|
},
|
|
"context7": {
|
|
"command": "npx",
|
|
"args": ["-y", "@upstash/context7-mcp@latest"],
|
|
"description": "Live documentation lookup — use with /docs command and documentation-lookup skill (resolve-library-id, query-docs)."
|
|
},
|
|
"magic": {
|
|
"command": "npx",
|
|
"args": ["-y", "@magicuidesign/mcp@latest"],
|
|
"description": "Magic UI components"
|
|
},
|
|
"filesystem": {
|
|
"command": "npx",
|
|
"args": ["-y", "@modelcontextprotocol/server-filesystem", "/path/to/your/projects"],
|
|
"description": "Filesystem operations (set your path)"
|
|
},
|
|
"insaits": {
|
|
"command": "python3",
|
|
"args": ["-m", "insa_its.mcp_server"],
|
|
"description": "AI-to-AI security monitoring — anomaly detection, credential exposure, hallucination checks, forensic tracing. 23 anomaly types, OWASP MCP Top 10 coverage. 100% local. Install: pip install insa-its"
|
|
},
|
|
"playwright": {
|
|
"command": "npx",
|
|
"args": ["-y", "@playwright/mcp", "--browser", "chrome"],
|
|
"description": "Browser automation and testing via Playwright"
|
|
},
|
|
"fal-ai": {
|
|
"command": "npx",
|
|
"args": ["-y", "fal-ai-mcp-server"],
|
|
"env": {
|
|
"FAL_KEY": "YOUR_FAL_KEY_HERE"
|
|
},
|
|
"description": "AI image/video/audio generation via fal.ai models"
|
|
},
|
|
"browserbase": {
|
|
"command": "npx",
|
|
"args": ["-y", "@browserbasehq/mcp-server-browserbase"],
|
|
"env": {
|
|
"BROWSERBASE_API_KEY": "YOUR_BROWSERBASE_KEY_HERE"
|
|
},
|
|
"description": "Cloud browser sessions via Browserbase"
|
|
},
|
|
"browser-use": {
|
|
"type": "http",
|
|
"url": "https://api.browser-use.com/mcp",
|
|
"headers": {
|
|
"x-browser-use-api-key": "YOUR_BROWSER_USE_KEY_HERE"
|
|
},
|
|
"description": "AI browser agent for web tasks"
|
|
},
|
|
"devfleet": {
|
|
"type": "http",
|
|
"url": "http://localhost:18801/mcp",
|
|
"description": "Multi-agent orchestration — dispatch parallel Claude Code agents in isolated worktrees. Plan projects, auto-chain missions, read structured reports. Repo: https://github.com/LEC-AI/claude-devfleet"
|
|
},
|
|
"token-optimizer": {
|
|
"command": "npx",
|
|
"args": ["-y", "token-optimizer-mcp"],
|
|
"description": "Token optimization for 95%+ context reduction via content deduplication and compression"
|
|
},
|
|
"laraplugins": {
|
|
"type": "http",
|
|
"url": "https://laraplugins.io/mcp/plugins",
|
|
"description": "Laravel plugin discovery — search packages by keyword, health score, Laravel/PHP version compatibility. Use with laravel-plugin-discovery skill."
|
|
},
|
|
"confluence": {
|
|
"command": "npx",
|
|
"args": ["-y", "confluence-mcp-server"],
|
|
"env": {
|
|
"CONFLUENCE_BASE_URL": "YOUR_CONFLUENCE_URL_HERE",
|
|
"CONFLUENCE_EMAIL": "YOUR_EMAIL_HERE",
|
|
"CONFLUENCE_API_TOKEN": "YOUR_CONFLUENCE_TOKEN_HERE"
|
|
},
|
|
"description": "Confluence Cloud integration — search pages, retrieve content, explore spaces"
|
|
},
|
|
"evalview": {
|
|
"command": "python3",
|
|
"args": ["-m", "evalview", "mcp", "serve"],
|
|
"env": {
|
|
"OPENAI_API_KEY": "YOUR_OPENAI_API_KEY_HERE"
|
|
},
|
|
"description": "AI agent regression testing — snapshot behavior, detect regressions in tool calls and output quality. 8 tools: create_test, run_snapshot, run_check, list_tests, validate_skill, generate_skill_tests, run_skill_test, generate_visual_report. API key optional — deterministic checks (tool diff, output hash) work without it. Install: pip install \"evalview>=0.5,<1\""
|
|
}
|
|
},
|
|
"_comments": {
|
|
"usage": "Copy the servers you need to your ~/.claude.json mcpServers section",
|
|
"env_vars": "Replace YOUR_*_HERE placeholders with actual values",
|
|
"disabling": "Use disabledMcpServers array in project config to disable per-project",
|
|
"context_warning": "Keep under 10 MCPs enabled to preserve context window"
|
|
}
|
|
}
|