@composio/mcp
MCP CLI tool
Supply chain provenance
Status for the latest visible version.
Without SLSA provenance there is no cryptographic link between this tarball and the public source — the axios compromise (March 2026) relied on exactly this gap.
Maintainers
Accepted risks
Findings the reviewer chose to accept rather than block on.
| Source | Rule | Reason | Accepted by | When |
|---|---|---|---|---|
| typosquat | typosquat.levenshtein:yup | AI (typosquat): @composio/mcp is a scoped MCP CLI tool; Levenshtein match to 'yup' is coincidental and not a typosquat. | ai | |
| phantom-deps | phantom-dep:commander | AI (phantom-deps): commander is a CLI framework likely bundled via webpack; phantom detection is a false positive for bundled packages. | ai | |
| phantom-deps | phantom-dep:@types/js-yaml | AI (phantom-deps): Type-only package; not directly imported at runtime by design. | ai | |
| phantom-deps | phantom-dep:event-source-polyfill | AI (phantom-deps): Polyfill loaded via webpack config, not direct import; false positive for bundled packages. | ai | |
| phantom-deps | phantom-dep:rollup-plugin-node-polyfills | AI (phantom-deps): Build plugin referenced in config, not imported in source; false positive. | ai |
Versions (showing 4 of 4)
| Version | Deps | Published |
|---|---|---|
| 1.0.9 | 11 / 28 | |
| 1.0.8 | 9 / 28 | |
| 1.0.7 | 9 / 28 | |
| 1.0.6 | 9 / 28 |
v1.0.9
1 findingPackage was published without Sigstore provenance. Only ~12% of npm packages have provenance, so this is common but not ideal.
v1.0.8
1 findingPackage was published without Sigstore provenance. Only ~12% of npm packages have provenance, so this is common but not ideal.
v1.0.7
1 findingPackage was published without Sigstore provenance. Only ~12% of npm packages have provenance, so this is common but not ideal.
v1.0.6
1 findingPackage was published without Sigstore provenance. Only ~12% of npm packages have provenance, so this is common but not ideal.