After spending the last few weeks trying out different MCP Servers
These are the 10 I have loved using the most:
1. Playwright
Link: github.com/microsoft/play…
2. Github
Link: github.com/github/github-…
3. Parallel AI
Link: docs.parallel.ai/integrations/m…
4. Rams
Link: rams.ai/mcp
5. Chrome Dev Tools
Link: github.com/ChromeDevTools…
6. Firecrawl
Link: github.com/firecrawl/fire…
7. Context7
Link: github.com/upstash/contex…
8. Cloudflare
Link: github.com/cloudflare/mcp…
9. Figma
Link: figma.com/mcp-catalog
10. Postman
Link: github.com/postmanlabs/po…
These are the 10 I have loved using the most:
1. Playwright
Link: github.com/microsoft/play…
2. Github
Link: github.com/github/github-…
3. Parallel AI
Link: docs.parallel.ai/integrations/m…
4. Rams
Link: rams.ai/mcp
5. Chrome Dev Tools
Link: github.com/ChromeDevTools…
6. Firecrawl
Link: github.com/firecrawl/fire…
7. Context7
Link: github.com/upstash/contex…
8. Cloudflare
Link: github.com/cloudflare/mcp…
9. Figma
Link: figma.com/mcp-catalog
10. Postman
Link: github.com/postmanlabs/po…
THE CORE TEAM:
* chief of staff: general day-to-day, cal, slack/email
* eng mgr: breaks down eng work and delegates to...
* eng (× 5): executes, spin off & manage cloud agents
* data analyst: most used*, access to data warehouse
* pm pete: new product ideas, rsch, feedback, docs
here's what e
* chief of staff: general day-to-day, cal, slack/email
* eng mgr: breaks down eng work and delegates to...
* eng (× 5): executes, spin off & manage cloud agents
* data analyst: most used*, access to data warehouse
* pm pete: new product ideas, rsch, feedback, docs
here's what e
10 GitHub repos with ⭐ 450k+ combined stars that stop your agent from wasting tokens
1. caveman 98k⭐ - makes your AI agent talk like a caveman. Same answers, 65% fewer output tokens. github.com/JuliusBrussee/…
2. rtk 76k⭐ - CLI proxy that filters git/test/docker output before it hits your context. Up to 90% less bash noise. github.com/rtk-ai/rtk
3. mem0 63k⭐ - memory layer for AI agents. Stops your agent from re-explaining the same context every session. github.com/mem0ai/mem0
4. context7 60.7k⭐ - pulls exact, up-to-date docs into context instead of your agent guessing and burning tokens on retries. github.com/upstash/contex…
5. aider 48k⭐ - builds a map of your repo instead of loading the whole codebase into context. github.com/Aider-AI/aider
6. code-review-graph 30k⭐ - graphs your codebase so your agent reads 2-3 files instead of the whole repo. Up to 376x fewer tokens per question. github.com/tirth8205/code…
7. serena 28k⭐ - gives agents symbol-level code access instead of reading full files line by line. github.com/oraios/serena
8. repomix 28k⭐ - compresses your entire repo into an AI-friendly format. ~70% token reduction. github.com/yamadashy/repo…
9. ccusage 18k⭐ - shows you exactly where your Claude Code sessions are burning tokens. github.com/ryoppippi/ccus…
10. GPTCache 8k⭐ - semantic cache for LLM calls. Stop paying twice for the same question. github.com/zilliztech/GPT…
Save this before your next agent session burns through your subscription 👇
1. caveman 98k⭐ - makes your AI agent talk like a caveman. Same answers, 65% fewer output tokens. github.com/JuliusBrussee/…
2. rtk 76k⭐ - CLI proxy that filters git/test/docker output before it hits your context. Up to 90% less bash noise. github.com/rtk-ai/rtk
3. mem0 63k⭐ - memory layer for AI agents. Stops your agent from re-explaining the same context every session. github.com/mem0ai/mem0
4. context7 60.7k⭐ - pulls exact, up-to-date docs into context instead of your agent guessing and burning tokens on retries. github.com/upstash/contex…
5. aider 48k⭐ - builds a map of your repo instead of loading the whole codebase into context. github.com/Aider-AI/aider
6. code-review-graph 30k⭐ - graphs your codebase so your agent reads 2-3 files instead of the whole repo. Up to 376x fewer tokens per question. github.com/tirth8205/code…
7. serena 28k⭐ - gives agents symbol-level code access instead of reading full files line by line. github.com/oraios/serena
8. repomix 28k⭐ - compresses your entire repo into an AI-friendly format. ~70% token reduction. github.com/yamadashy/repo…
9. ccusage 18k⭐ - shows you exactly where your Claude Code sessions are burning tokens. github.com/ryoppippi/ccus…
10. GPTCache 8k⭐ - semantic cache for LLM calls. Stop paying twice for the same question. github.com/zilliztech/GPT…
Save this before your next agent session burns through your subscription 👇
GitHub
JuliusBrussee - Overview
caveman. JuliusBrussee has 24 repositories available. Follow their code on GitHub.