Linear MCP Servers: 17 Implementations Compared

The MCP ecosystem often has several independent packages implementing the same tool — and "Linear" currently has 17. Every one of them was scanned with the same deterministic engine, so the numbers below are directly comparable: the Trust Score (A–F), the capability blast radius, and how much of the package the scan could actually inspect. They are ranked by score; ties break toward unscoped, longer-established packages.

ImplementationPackageTrustCapabilityCoverageFindingsScanned
Linear Source verifiedbest by west10tech @west10tech/linear-mcp npm A 100/100 Minimal Source 0 2026-09-07
Linear by dvcrn mcp-server-linear npm A 99/100 Minimal Source 0 2026-09-07
Linear by dvcrn linear-mcp npm A 99/100 Minimal Source 0 2026-09-07
Linear by sylphx @sylphx/linear-mcp npm A 99/100 Minimal Source 0 2026-09-07
Linear by pipeworx @pipeworx/mcp-linear npm A 99/100 Minimal Source 0 2026-09-07
Linear by universal-mcp-toolkit @universal-mcp-toolkit/server-linear npm A 99/100 Minimal Source 0 2026-09-07
Linear by emmett.deen @emmett.deen/linear-mcp-server npm A 98/100 Minimal Source 1 2026-09-07
Linear Source verified by mkusaka @mkusaka/mcp-server-linear npm A 97/100 Moderate Source 0 2026-09-07
Linear by mseep @mseep/linear-mcp-server npm A 96/100 Moderate Source 1 2026-09-07
Linear by mseep @mseep/linear-mcp npm A 96/100 Moderate Source 0 2026-09-07
Linear (linear-mcp-server) by modelcontextprotocol linear-mcp-server npm A 96/100 Moderate Source 1 2026-08-25
Linear by larryhudson @larryhudson/linear-mcp-server npm A 96/100 Moderate Source 0 2026-09-07
Linear by mcp-wormhole @mcp-wormhole/linear npm A 96/100 Moderate Source 0 2026-09-07
Linear (mcp-linear) by npm mcp-linear npm A 95/100 Moderate Source 1 2026-08-25
Linear by cloud9-labs @cloud9-labs/mcp-linear npm A 95/100 Moderate Source 0 2026-09-07
Linear Source verified by tacticlaunch @tacticlaunch/mcp-linear npm A 93/100 High Source 3 2026-08-30
Linear by gmclend @gmclend/linear-mcp npm A 93/100 High Source 1 2026-09-07

A higher-ranked implementation is not "the official one" — ranking reflects only what the deterministic scan found in each published package. Open an implementation to read its individual findings with evidence, its scan history per version, and to grab an embeddable badge. Scores are automated opinions, recomputed on every rescan.