50 Essential Mcp Servers

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.

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.

the three rules

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.
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.
3. never enable writes against production from an agent loop. point at a read replica or a snapshot.

install syntax primer

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.

contents

#	category	what it covers
01	core dev — the universal core	github, context7, playwright, filesystem, brave search
02	databases & backend	postgres, supabase, neon, sqlite, redis
03	ops, infra & cloud	cloudflare, vercel, aws, docker hub, sentry, kubernetes
04	corporate / team & productivity	slack, linear, notion, jira/confluence, gdrive, gmail, calendar, asana, airtable
05	payments & fintech	stripe, paypal, plaid, quickbooks
06	blockchain & web3	base, solana agent kit, thirdweb, the graph, dune, etherscan
07	trading & markets	alpaca, ccxt, polygon.io, coingecko, tradingview
08	creator tools — media & design	higgsfield, davinci resolve, figma, elevenlabs, blender, canva, ableton, youtube
09	the reasoning & memory layer	sequential thinking, memory

all 50 servers at a glance

#	server	category	official / community	hosted / local	money or irreversible?
1	github	core-dev	official	hosted	no
2	context7	core-dev	official	hosted / local	no
3	playwright	core-dev	official	local	no
4	filesystem	core-dev	official	local	no
5	brave search	core-dev	official	local	no
6	postgres	data / backend	official (archived)	local	yes
7	supabase	data / backend	official	hosted	yes
8	neon	data / backend	official	hosted	yes
9	sqlite	data / backend	community	local	no
10	redis	data / backend	official	local	no
11	cloudflare	ops / infra	official	hosted	yes
12	vercel	ops / infra	official	hosted	yes
13	aws	ops / infra	official	local	yes
14	docker hub	ops / infra	community	local	no
15	sentry	ops / infra	official	hosted	no
16	kubernetes	ops / infra	community	local	yes
17	slack	productivity	community	local	yes
18	linear	productivity	official	hosted	no
19	notion	productivity	official	hosted	no
20	jira / confluence	productivity	official	hosted	no
21	google drive	productivity	official (archived)	local	no
22	gmail	productivity	community	local	yes
23	google calendar	productivity	community	local	yes
24	asana	productivity	official	hosted	no
25	airtable	productivity	community	local	no
26	stripe	fintech	official	hosted / local	yes
27	paypal	fintech	official	hosted	yes
28	plaid	fintech	official	hosted	yes
29	quickbooks	fintech	community	hosted	yes
30	base	web3	official	hosted	yes
31	solana agent kit	web3	community	local	yes
32	thirdweb	web3	official	local	yes
33	the graph	web3	community	local	no
34	dune	web3	community	local	no
35	etherscan	web3	community	local	no
36	alpaca	trading	official	local	yes
37	ccxt	trading	community	local	yes
38	polygon.io	trading	official	local	no
39	coingecko	trading	official	hosted	no
40	tradingview	trading	community	local	no
41	higgsfield	creator	official	hosted	no
42	davinci resolve	creator	community	local	no
43	figma	creator	official	hosted / local	no
44	elevenlabs	creator	official	local	no
45	blender	creator	community	local	no
46	canva	creator	official	hosted	no
47	ableton live	creator	community	local	no
48	youtube	creator	community	local	no
49	sequential thinking	reasoning	official	local	no
50	memory	reasoning	official	local	no

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.

how to actually choose

if you build software: github, context7, playwright, your database (postgres/supabase/neon), sentry. five servers, 90% of the value.

if you ship content: higgsfield, davinci resolve, elevenlabs, youtube, figma. that's a full creator pipeline.

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.

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.

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.

pick your five. wire them in. ship.

---

source article: @exploraX_ on X

curated by @exploraX_