@ai-sdk/mcp
86%
Total Score
healthy
Active releases and strong organization backing outweigh workflow and package-identity cautions.
Health Score Breakdown
The repository name does not match the package and its README does not mention @ai-sdk/mcp, so package ownership is less transparent; the organization monorepo context partly offsets this concern.
All 13 workflows were analyzed and all action references are pinned, while 11 workflows use read-only permissions. One workflow combines workflow_run with an untrusted checkout, and two have top-level write permissions, creating a workflow-hygiene caution without evidence of a directly exploitable sink.
Vulnerabilities
| Title | Versions | Severity |
|---|---|---|
AIKIDO-2026-10997 Pre-CVE Found by Aikido Intel before public disclosure or CVE publication. @ai-sdk/mcp is vulnerable to Cross-Site Request Forgery (CSRF) in versions 1.0.0 - 1.0.27. | 1.0.0 - 1.0.27 | Medium |
Package versions
Maintainers
Direct Dependencies
| Dependency | Last Release | Score |
|---|---|---|
 cross-spawn Version ^7.0.6 | — | — |
pkce-challenge Version ^5.0.1 | — | — |
@ai-sdk/provider Version 4.0.27 | — | — |
@ai-sdk/provider-utils Version 5.0.60 | — | — |
Weekly Downloads
Info
- Last Published
- 13 hours ago
- Created
- 11 months ago
- Unpacked Size
- 0.8 MB
Are You Affected?
Connect your repositories to instantly see whether vulnerable or malicious packages exist in your codebase.
Free. No credit card required.
I consent to receiving marketing communications based on Aikido’s Privacy Policy.
SOC 2Compliant
ISO 27001CompliantISO 42001Compliant
FedRAMPImplementing© All Intel data is openly available and commercially licensed.