Skip to content
Back to search

50-essential-mcp-servers

a curated, browsable reference of 50 essential MCP servers for claude, gemini & codex — install commands, official links, and the gotchas that matter

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/moh4696--50-essential-mcp-servers/badge.svg)](/listings/moh4696--50-essential-mcp-servers)

HTML

<a href="/listings/moh4696--50-essential-mcp-servers"><img src="/api/listings/moh4696--50-essential-mcp-servers/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

the three big agents each have their own config path but the underlying json is basically identical:

- **claude code** → `claude mcp add <name> ...` (or `--transport http` for hosted servers) - **codex** → `codex mcp add <name> -- <command>`, or edit `~/.codex/config.toml` - **gemini cli** → edit `~/.gemini/settings.json`, same `mcpServers` block

where a server is hosted (an https url) it usually works in all three with the http transport and a browser oauth flow. where it's local (npx/uvx) you drop the same command block into each agent's config. the entries below give the claude command for each and note when codex/gemini differ.

one honesty note: this space moves weekly. exact install strings are given where they could be confirmed against official docs, and for a few servers — mostly the smaller web3/fintech ones — the entry points you to the vendor's docs instead of a command, because a verified source beats a url that isn't 100% sure. always sanity-check the endpoint against the official repo before you paste in a token.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 116 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. <img src="assets/header.png" alt="50 MCP servers that give claude, codex and gemini superpowers — a curated index across five categories: agentic and core dev, data and ops, corporate and teams, web3 and trading, creator tools" width="100%">
  2. # 50 essential MCP servers for claude, gemini and codex
  3. the model context protocol started life as a niche anthropic spec in late 2024. eighteen months later it's the standard plug every serious AI agent speaks — claude code, gemini cli, codex, cursor, windsurf, all of them. the pitch is boringly simple: instead of every model writing a custom integration for every tool, each model speaks MCP once and every tool that speaks it back becomes available. anthropic calls it a usb-c port for AI. that's the right mental model.
  4. the catalog is now enormous. over 20,000 servers sit on public registries and the sdk was pulling ~97 million downloads a month by march 2026. most of them are junk — abandoned weekend projects, half-finished experiments, or worse. a recent audit found security issues in roughly two-thirds of the popular ones. so before anything else, three rules that matter more than this whole list.
  5. ## the three rules
  6. 1. **don't install 50.** more than 5-7 connected servers and your agent starts choking on tool bloat — it gets slower and dumber. pick the 3-5 that match what you actually do. this is a menu, not a shopping spree.
  7. 2. **treat every server like a cli from a stranger's github.** pin versions. scope tokens to read-only until you've watched how the agent uses them. prefer vendor-official over random forks.
  8. 3. **never enable writes against production from an agent loop.** point at a read replica or a snapshot.
  9. ## install syntax primer
  10. the three big agents each have their own config path but the underlying json is basically identical:
  11. - **claude code** → `claude mcp add <name> ...` (or `--transport http` for hosted servers)
  12. - **codex** → `codex mcp add <name> -- <command>`, or edit `~/.codex/config.toml`
  13. - **gemini cli** → edit `~/.gemini/settings.json`, same `mcpServers` block
  14. where a server is hosted (an https url) it usually works in all three with the http transport and a browser oauth flow. where it's local (npx/uvx) you drop the same command block into each agent's config. the entries below give the claude command for each and note when codex/gemini differ.
  15. one honesty note: this space moves weekly. exact install strings are given where they could be confirmed against official docs, and for a few servers — mostly the smaller web3/fintech ones — the entry points you to the vendor's docs instead of a command, because a verified source beats a url that isn't 100% sure. always sanity-check the endpoint against the official repo before you paste in a token.
  16. ## contents
  17. | # | category | what it covers |
  18. |---|---|---|
  19. | 01 | [core dev — the universal core](servers/01-core-dev.md) | github, context7, playwright, filesystem, brave search |
  20. | 02 | [databases & backend](servers/02-data-backend.md) | postgres, supabase, neon, sqlite, redis |
  21. | 03 | [ops, infra & cloud](servers/03-ops-infra.md) | cloudflare, vercel, aws, docker hub, sentry, kubernetes |
  22. | 04 | [corporate / team & productivity](servers/04-corporate-productivity.md) | slack, linear, notion, jira/confluence, gdrive, gmail, calendar, asana, airtable |
  23. | 05 | [payments & fintech](servers/05-fintech.md) | stripe, paypal, plaid, quickbooks |
  24. | 06 | [blockchain & web3](servers/06-web3.md) | base, solana agent kit, thirdweb, the graph, dune, etherscan |
  25. | 07 | [trading & markets](servers/07-trading.md) | alpaca, ccxt, polygon.io, coingecko, tradingview |
  26. | 08 | [creator tools — media & design](servers/08-creator-tools.md) | higgsfield, davinci resolve, figma, elevenlabs, blender, canva, ableton, youtube |
  27. | 09 | [the reasoning & memory layer](servers/09-reasoning-memory.md) | sequential thinking, memory |
  28. ## all 50 servers at a glance
  29. | # | server | category | official / community | hosted / local | money or irreversible? |
  30. |---|---|---|---|---|---|
  31. | 1 | github | core-dev | official | hosted | no |
  32. | 2 | context7 | core-dev | official | hosted / local | no |
  33. | 3 | playwright | core-dev | official | local | no |
  34. | 4 | filesystem | core-dev | official | local | no |
  35. | 5 | brave search | core-dev | official | local | no |
  36. | 6 | postgres | data / backend | official (archived) | local | yes |
  37. | 7 | supabase | data / backend | official | hosted | yes |
  38. | 8 | neon | data / backend | official | hosted | yes |
  39. | 9 | sqlite | data / backend | community | local | no |
  40. | 10 | redis | data / backend | official | local | no |
  41. | 11 | cloudflare | ops / infra | official | hosted | yes |
  42. | 12 | vercel | ops / infra | official | hosted | yes |
  43. | 13 | aws | ops / infra | official | local | yes |
  44. | 14 | docker hub | ops / infra | community | local | no |
  45. | 15 | sentry | ops / infra | official | hosted | no |
  46. | 16 | kubernetes | ops / infra | community | local | yes |
  47. | 17 | slack | productivity | community | local | yes |
  48. | 18 | linear | productivity | official | hosted | no |
  49. | 19 | notion | productivity | official | hosted | no |
  50. | 20 | jira / confluence | productivity | official | hosted | no |
  51. | 21 | google drive | productivity | official (archived) | local | no |
  52. | 22 | gmail | productivity | community | local | yes |
  53. | 23 | google calendar | productivity | community | local | yes |
  54. | 24 | asana | productivity | official | hosted | no |
  55. | 25 | airtable | productivity | community | local | no |
  56. | 26 | stripe | fintech | official | hosted / local | yes |
  57. | 27 | paypal | fintech | official | hosted | yes |
  58. | 28 | plaid | fintech | official | hosted | yes |
  59. | 29 | quickbooks | fintech | community | hosted | yes |
  60. | 30 | base | web3 | official | hosted | yes |
  61. | 31 | solana agent kit | web3 | community | local | yes |
  62. | 32 | thirdweb | web3 | official | local | yes |
  63. | 33 | the graph | web3 | community | local | no |
  64. | 34 | dune | web3 | community | local | no |
  65. | 35 | etherscan | web3 | community | local | no |
  66. | 36 | alpaca | trading | official | local | yes |
  67. | 37 | ccxt | trading | community | local | yes |
  68. | 38 | polygon.io | trading | official | local | no |
  69. | 39 | coingecko | trading | official | hosted | no |
  70. | 40 | tradingview | trading | community | local | no |
  71. | 41 | higgsfield | creator | official | hosted | no |
  72. | 42 | davinci resolve | creator | community | local | no |
  73. | 43 | figma | creator | official | hosted / local | no |
  74. | 44 | elevenlabs | creator | official | local | no |
  75. | 45 | blender | creator | community | local | no |
  76. | 46 | canva | creator | official | hosted | no |
  77. | 47 | ableton live | creator | community | local | no |
  78. | 48 | youtube | creator | community | local | no |
  79. | 49 | sequential thinking | reasoning | official | local | no |
  80. | 50 | memory | reasoning | official | local | no |
  81. > the **money or irreversible?** column flags servers that — per the source article's warnings — can move real money, handle banking/financial data, place real trades, execute irreversible on-chain transactions, or write to production infrastructure/databases. it is a prompt to slow down and keep a human in the loop, not a claim that the server is unsafe. read each server's gotcha for the specifics.
  82. ## how to actually choose
  83. if you build software: github, context7, playwright, your database (postgres/supabase/neon), sentry. five servers, 90% of the value.
  84. if you ship content: higgsfield, davinci resolve, elevenlabs, youtube, figma. that's a full creator pipeline.
  85. if you trade or work onchain: start read-only — coingecko, polygon, the graph, dune. add base mcp or alpaca only when you understand the confirmation flow cold, and paper-trade first.
  86. if you run a company on docs and tickets: slack, linear/jira, notion, google drive. the agent stops being a chat window and starts being a teammate.
  87. the trap is installing everything because it sounds useful. don't. each connected server eats context and drags performance on the work you actually care about. three to five sharp picks beat twenty dull ones every time. revisit the config quarterly — the ecosystem moves fast, and a server you set up before march 2026 has probably been superseded by something faster and better-authed.
  88. pick your five. wire them in. ship.
  89. ---
  90. source article: [@exploraX_ on X](https://x.com/exploraX_/status/2062448236439155173?s=20)
  91. *curated by [@exploraX_](https://x.com/exploraX_)*

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.