Snapshot of the MCP server ecosystem as of 2026-07-26 · by PulseFeed · see the live report →
128 of 1065 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 97 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.
npm servers get deep signals; remote servers get liveness + HTTPS only.
| Server | Verdict | Flags |
|---|---|---|
| ai.alpic.test/test-mcp-server | avoid | unreachable |
| ai.autorfp/mcp | avoid | unreachable |
| ai.baselight/baselight | avoid | unreachable |
| ai.buyersense/buyersense | avoid | unreachable |
| ai.clarid/compliance | avoid | unreachable |
| ai.com.mcp/hapi-mcp | avoid | unreachable |
| ai.com.mcp/skills-search | avoid | unreachable |
| ai.dynamicfeed/dynamic-feed | avoid | unreachable |
| agentdb | avoid | install_script |
| agentic-flow | avoid | install_script |
| @azure/mcp | avoid | install_script |
| gitnexus | avoid | install_script, unpopular |
| Date | Audited | Install-script | Avoid | Abandoned |
|---|---|---|---|---|
| 2026-07-26 | 1065 | 128 | 136 | 43 |
| 2026-07-25 | 1064 | 128 | 136 | 43 |
| 2026-07-24 | 1054 | 126 | 134 | 44 |
| 2026-07-23 | 1036 | 122 | 129 | 44 |
| 2026-07-22 | 1017 | 119 | 126 | 44 |
| 2026-07-21 | 988 | 112 | 119 | 44 |
| 2026-07-20 | 961 | 106 | 114 | 41 |
| 2026-07-19 | 955 | 105 | 113 | 41 |
| 2026-07-18 | 951 | 105 | 114 | 41 |
| 2026-07-17 | 947 | 105 | 114 | 41 |
| 2026-07-16 | 938 | 104 | 113 | 41 |
| 2026-07-15 | 922 | 101 | 110 | 40 |
| 2026-07-14 | 884 | 97 | 106 | 39 |
| 2026-07-13 | 863 | 90 | 99 | 39 |
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