Skip to content

State of MCP Security · 2026-11-09

Snapshot of the MCP server ecosystem as of 2026-11-09 · by PulseFeed · see the live report →

6101▲349
servers audited
5323▲328
safe verdict (recorded signals)
473▲14
avoid (8%)

Headline: how many run code the moment you install them?

8%▲14

462 of 6101 MCP servers ship an install/postinstall script — arbitrary code runs on your machine at npm i, before you've even used the tool. Some are legitimate native builds, but each is an unreviewed code-execution vector — and 658 of all audited servers publish no repository to inspect at all. A bad MCP server can read your files, env vars and keys the moment it's connected.

Install-script exposure over time

462 80 462 07-0809-0811-09

Verdicts

safe
5323
caution
300
avoid
473
unknown
5

npm servers get deep signals; remote servers get liveness + HTTPS only.

Top safety flags

—

Servers to avoid (sample)

ServerVerdictFlags
ai.agenticshelf/graffeoavoidunreachable
ai.agenticshelf/mcpavoidunreachable
ai.agenticshelf/puroairavoidunreachable
ai.alpic.test/test-mcp-serveravoidunreachable
ai.autorfp/mcpavoidunreachable
ai.baselight/baselightavoidunreachable
ai.buyersense/buyersenseavoidunreachable
ai.clarid/complianceavoidunreachable
ai.com.mcp/hapi-mcpavoidunreachable
ai.com.mcp/skills-searchavoidunreachable
ai.dynamicfeed/dynamic-feedavoidunreachable
agentdbavoidinstall_script, downloads_unknown

Daily archive

DateAuditedInstall-scriptAvoidAbandoned
2026-11-096101462473186
2026-11-086077461472185
2026-11-076046462473185
2026-11-066016460471185
2026-11-055980459470184
2026-11-045908458469181
2026-11-035842452463179
2026-11-025752448459176
2026-11-015741449460175
2026-10-315734448459175
2026-10-305721443454173
2026-10-295684440451170
2026-10-285615434445170
2026-10-275520431442165

Methodology: PulseFeed discovers MCP servers from the official MCP registry and npm, then audits each independently — install/postinstall scripts (code execution on install), abandonment, provenance, license, repository, download volume, and liveness for remote servers. Verdict = safe / caution / avoid. This report is generated automatically from that data and updates daily. Install scripts are not inherently malicious (native builds use them) but every one is an unreviewed code-execution vector worth checking. Same independent-audit approach as our x402 trust oracle.
Check any server free: GET /mcp/verify?package=<npm-name> · Machine-readable: /mcp-report.json · Live observatory: /mcp · /llms.txt