What breaks in MCP servers: results from launching 750 registry entries

A weekly testing project called MCP Verified ran 750 entries from the official Model Context Protocol registry through a clean-sandbox install, initialize handshake and tools/list call, finding only 431 (57%) working. npm packages performed best at 73% working, while remote SSE endpoints were worst at 10%, with dead remote endpoints (88) and servers crashing on start (47) among the leading failure causes. The operator notes the sample is not the full registry and that servers requiring configuration or credentials were left untested.

Disclosure: I run MCP Verified, a weekly test of servers in the official Model Context Protocol registry. This post is the data. The newsletter link is at the end. Each week we take a sample of 750 entries from the official MCP registry 300 npm, 150 PyPI, 200 remote streamable-HTTP, 100 remote SSE . We install or connect to each one in a clean sandbox, run the MCP initialize handshake, and call tools/list . Where possible we also make one harmless tool call. We supply no API keys. | Type | Tested | Working | Median handshake | Median tools | |---|---|---|---|---| | npm | 300 | 218 73% | 563 ms | 14 | | PyPI | 150 | 73 49% | 1,581 ms | 16 | | HTTP | 200 | 130 65% | 436 ms | 8.5 | | SSE | 100 | 10 10% | 1,152 ms | 9 | | All | 750 | 431 57% | | | | Reason | Count | |---|---| | Needs config/env vars untested | 92 | | Remote endpoint dead | 88 | | Needs credentials untested | 54 | | Crashed on start | 47 | | Install failed | 12 | | Handshake failed | 10 | | tools/list failed after handshake | 6 | | URL isn't an MCP server | 6 | | Timeout 45 s | 4 | Working count in our runs: 422 Oct 13 , then 427, then 431 both Oct 19 . This is a sample, not the whole registry. "Needs config" doesn't mean broken. Results are from one sandbox environment. Weekly results free newsletter : https://buttondown.com/mcpverified https://buttondown.com/mcpverified · Site: https://mcpverified.netlify.app https://mcpverified.netlify.app