Index · litmus-v17

The MCP Security Index

Every grade we publish — MCP servers tested for behavior and ordered by adoption, Agent Skills scanned for safety. What each one does, not what its README claims.

107 MCP servers graded, ranked by adoption · 13 live endpoints (hosted, egress unverified) · 110 skills scanned · adoption data as of 2026-10-09. A grade is a measurement, not a guarantee; you can re-run the open harness yourself.

Run the harnessHosted grading is discontinued. Grade a server locally with the open harness.

Grade

120 servers

#	Server	Grade	Checks	Adoption
1	npm/@playwright/mcp	A	01✓02✓03✓04✓	100/10030.6M npm/mo
2	npm/@modelcontextprotocol/server-filesystem	A	01✓02✓03✓04✓	87/1002.52M npm/mo
3	npm/@modelcontextprotocol/server-everything	F	01✓02✓03✕04✓	82/1001.12M npm/mo
4	npm/@modelcontextprotocol/server-memory	A	01✓02✓03✓04✓	82/100630K npm/mo
5	npm/@upstash/context7-mcp	A	01✓02✓03✓04✓	81/1003.1M npm/mo
6	npm/firecrawl-mcp	A	01✓02✓03✓04✓	79/100484K npm/mo
7	npm/@modelcontextprotocol/server-sequential-thinking	A	01✓02✓03✓04✓	78/100521K npm/mo
8	npm/@modelcontextprotocol/server-github	A	01✓02✓03✓04✓	76/100506K npm/mo
9	npm/exa-mcp-server	A	01✓02✓03✓04✓	76/100239K npm/mo
10	npm/@notionhq/notion-mcp-server	A	01✓02✓03✓04✓	75/100770K npm/mo
11	npm/n8n-mcp	A	01✓02✓03✓04✓	74/100420K npm/mo
12	npm/@modelcontextprotocol/server-puppeteer	A	01✓02✓03✓04✓	72/100133K npm/mo
13	npm/@netlify/mcp	A	01✓02✓03✓04✓	70/100155K npm/mo
14	npm/tavily-mcp	A	01✓02✓03✓04✓	68/10092.1K npm/mo
15	npm/@21st-dev/magic	A	01✓02✓03✓04✓	67/100121K npm/mo
16	npm/open-websearch	A	01✓02✓03✓04✓	66/10036.1K npm/mo
17	npm/@coding-solo/godot-mcp	A	01✓02✓03✓04✓	64/10023.9K npm/mo
18	npm/mcp-server-kubernetes	A	01✓02✓03✓04✓	63/10041.5K npm/mo
19	npm/@negokaz/excel-mcp-server	A	01✓02✓03✓04✓	62/10040.3K npm/mo
20	npm/@browserbasehq/mcp-server-browserbase	A	01✓02✓03✓04✓	62/10020.2K npm/mo

Page 1 of 6

✓ pass✕ fail– not runC-01 tool-output injection · C-02 egress overreach · C-03 sensitive-data handling · C-04 adversarial-input handling

Ranked by the adoption score (0–100, shown at right above monthly downloads) — a composite of downloads (npm / PyPI), GitHub stars, dependents and release velocity. It measures reach, not safety: the litmus grade is the only safety verdict. Grades come from the open litmus harness; you can run it yourself for a server, or read the methodology.

Grade

110 skills

Skill	Grade	Checks
productclank-campaigns	A	S01✓S03✓S04✓
aeon-autoresearch	A	S01✓S03✓S04✓
zyfai	A	S01✓S03✓S04✓
wake-token-spotter-analysis	A	S01✓S03✓S04✓
zapper	A	S01✓S03✓S04✓
zerion	A	S01✓S03✓S04✓
aeon-deal-flow	A	S01✓S03✓S04✓
0xwork	A	S01✓S03✓S04✓
aeon-deep-research	A	S01✓S03✓S04✓
agenticbets	A	S01✓S03✓S04✓
yoink	A	S01✓S03✓S04✓
aeon-defi-monitor	A	S01✓S03✓S04✓
aeon-defi-overview	A	S01✓S03✓S04✓
aeon-distribute-tokens	A	S01✓S03✓S04✓
aeon-hacker-news-digest	A	S01✓S03✓S04✓
gitlawb	D	S01✓S03✓S04✕
uniswap-hooks	A	S01✓S03✓S04✓
1claw	A	S01✓S03✓S04✓
aeon-huggingface-trending	A	S01✓S03✓S04✓
aeon-last30	A	S01✓S03✓S04✓
aeon-monitor-kalshi	A	S01✓S03✓S04✓
aeon-monitor-polymarket	A	S01✓S03✓S04✓
aeon-monitor-runners	A	S01✓S03✓S04✓
aeon-narrative-tracker	A	S01✓S03✓S04✓
aeon-on-chain-monitor	A	S01✓S03✓S04✓
aeon-paper-pick	A	S01✓S03✓S04✓
aeon-reg-monitor	A	S01✓S03✓S04✓
aeon-rss-digest	A	S01✓S03✓S04✓
aeon-skill-evals	A	S01✓S03✓S04✓
aeon-skill-repair	A	S01✓S03✓S04✓
aeon-skill-security-scan	A	S01✓S03✓S04✓
aeon-token-movers	A	S01✓S03✓S04✓
aeon-token-pick	A	S01✓S03✓S04✓
aeon-unlock-monitor	A	S01✓S03✓S04✓
aeon-vuln-scanner	A	S01✓S03✓S04✓
agent-wormhole	A	S01✓S03✓S04✓
alchemy	A	S01✓S03✓S04✓
azzle	A	S01✓S03✓S04✓
bankr	A	S01✓S03✓S04✓
bankr-shopify	A	S01✓S03✓S04✓
bankr-token-scam-analysis	A	S01✓S03✓S04✓
bankr-twitter-agent	A	S01✓S03✓S04✓
base	A	S01✓S03✓S04✓
base-account	A	S01✓S03✓S04✓
base-deploy	A	S01✓S03✓S04✓
base-minikit	A	S01✓S03✓S04✓
base-network	A	S01✓S03✓S04✓
base-node	A	S01✓S03✓S04✓
berry-juicer	A	S01✓S03✓S04✓
blueagent	A	S01✓S03✓S04✓
botchan	A	S01✓S03✓S04✓
capacitr	A	S01✓S03✓S04✓
cattown	A	S01✓S03✓S04✓
checkr	A	S01✓S03✓S04✓
clanker	A	S01✓S03✓S04✓
codegrid	A	S01✓S03✓S04✓
darksol-random-oracle	A	S01✓S03✓S04✓
endaoment	A	S01✓S03✓S04✓
ens-primary-name	A	S01✓S03✓S04✓
erc-8004	A	S01✓S03✓S04✓
ethskills-addresses	A	S01✓S03✓S04✓
ethskills-audit	A	S01✓S03✓S04✓
ethskills-building-blocks	A	S01✓S03✓S04✓
ethskills-frontend-playbook	A	S01✓S03✓S04✓
ethskills-frontend-ux	A	S01✓S03✓S04✓
ethskills-gas	A	S01✓S03✓S04✓
ethskills-indexing	A	S01✓S03✓S04✓
ethskills-l2s	A	S01✓S03✓S04✓
ethskills-orchestration	A	S01✓S03✓S04✓
ethskills-qa	A	S01✓S03✓S04✓
ethskills-security	A	S01✓S03✓S04✓
ethskills-standards	A	S01✓S03✓S04✓
ethskills-testing	A	S01✓S03✓S04✓
ethskills-tools	A	S01✓S03✓S04✓
ethskills-wallets	A	S01✓S03✓S04✓
ethskills-why	A	S01✓S03✓S04✓
gem-miner	A	S01✓S03✓S04✓
helixa	A	S01✓S03✓S04✓
hermesone	A	S01✓S03✓S04✓
hunch	A	S01✓S03✓S04✓
hydrex	A	S01✓S03✓S04✓
litcoin	A	S01✓S03✓S04✓
megapot	A	S01✓S03✓S04✓
moltycash	A	S01✓S03✓S04✓
nexus-trading-labs	A	S01✓S03✓S04✓
neynar	A	S01✓S03✓S04✓
nookplot	A	S01✓S03✓S04✓
onchainkit	A	S01✓S03✓S04✓
opensea	A	S01✓S03✓S04✓
orlix	A	S01✓S03✓S04✓
pmfi-parbitrage	A	S01✓S03✓S04✓
productclank	A	S01✓S03✓S04✓
qrcoin	A	S01✓S03✓S04✓
quicknode	A	S01✓S03✓S04✓
signa	A	S01✓S03✓S04✓
signals	A	S01✓S03✓S04✓
siwa	A	S01✓S03✓S04✓
stakr	A	S01✓S03✓S04✓
starchild-dao	A	S01✓S03✓S04✓
symbiosis	A	S01✓S03✓S04✓
trails	A	S01✓S03✓S04✓
trustlayer-sybil-scanner	A	S01✓S03✓S04✓
uniswap-cca	A	S01✓S03✓S04✓
uniswap-driver	A	S01✓S03✓S04✓
uniswap-trading	A	S01✓S03✓S04✓
uniswap-viem	A	S01✓S03✓S04✓
veil	A	S01✓S03✓S04✓
versa	A	S01✓S03✓S04✓
productclank-agent-participation	A	S01✓S03✓S04✓
skills/pdf	A	S01✓S03✓S04✓

✓ pass✕ fail– not runS-01 prompt-injection · S-03 data-exfiltration instructions · S-04 dangerous bundled commands

Skills are graded by a static safety scan (litmus-skill-v2) of the SKILL.md and its bundled files — A/B/D/F, no adoption ranking. It reads the skill’s text, not its runtime behavior, so it’s a static read rather than behavioral proof. Read the methodology.

Index data is published under CC BY 4.0: reuse it freely, with attribution to polygraph.so.