Loading the registry…
Production-ready OAuth 2.1 server implementation for Model Context Protocol (MCP) with PKCE support
We found this by crawling public sources and nobody has attested to it. That is how most of the registry gets here, and it is not a mark against the artifact — it only means no authenticated act of publication is on record. An artifact can be the vendor's own and still appear here.
This artifact ships from 2 sources and their verdicts differ. The worst is github (Flagged). Installing from a cleaner source does not mean the others are safe — check the source you actually install from.
github: https://github.com/granular-software/mcpresso-oauth-server, 96 findings
Choose your runtime: the CLI writes the mcpServers config entry for that target.
nerlo install --target claude-code -- mcpresso-oauth-server
Install respects the composite badge: Clean proceeds, Caution prompts for confirmation, and Flagged is refused. Write operations require an API token.
6 of 11 scanners examined this package. The rest do not apply to it — language, ecosystem and packaging decide which analyzers can say anything, and a scanner that cannot examine an artifact reports nothing rather than passing it.
v1.4.0
0 findings · 0.6s
v2.0.11
3 findings · 8.5s
v0.3.74
21 findings · 1.1s
v0.1.0
2 findings · 4.3s
v0.1.0
0 findings · 4.3s
v0.1.0
0 findings · 8.6s
vv0.3.2
No Go packages were found in this artifact. What each scanner covers
0 findings · 0.1s
No report in this scan: govulncheck, osv-scanner, trivy, trivy_image.
1 scan on record. Every scan's full results are retained immutably for 24 months.
| Completed | Composite | Change | Scanners | Status |
|---|---|---|---|---|
| Aug 20, 2026 | Scan Halted | — | agentshield: completecisco-skill-scanner: completeagent-audit-kit: completenerlo-behavioral: completenerlo-install-instruction: completecapslock ·n/a: not applicablenerlo-multi-source: complete | rejected |
Findings in files this artifact installs stand as reported; a model re-read the rest and said which ones it believes are false positives. This is a second opinion published beside the evidence, not a correction to it: the per-scanner reports above are unchanged, every dismissed finding is still listed there at its original severity, and the score and the Flagged badge are computed from those raw severities alone. Nothing below moved them.
Out of 26 findings across every scanner that examined this package.
Not reviewed is not the same as clean. Those 26 findings stand exactly as their scanners reported them, at full severity, as they would have without this review.
26 The model's answer could not be read.
Rules: AAK-OAUTH-004, AAK-SECRET-004, opt.nerlo-rules.nerlo-js-secret-to-network-egress and 9 more · Files: test/mcp-oauth-flow.test.ts, test/oauth-server.test.ts, examples/mcpresso-integration.ts and 10 more · reported by agent-audit-kit, nerlo-behavioral, cisco-skill-scanner
Artifact handles secrets and performs network egress.
The artifact contains critical findings related to sensitive data handling in `/repo/src/index.ts`. High severity findings indicate potential credential exposure and network egress in `src/oauth-server.ts`, `src/server.ts`, and `examples/mcpresso-integration.ts`. These findings suggest the artifact can access and transmit sensitive information.
Concern level assessed by the review: Critical. This is the review's scale, not the registry badge.
Reviewed by gemini-2.5-flash. The model sees the findings, not your code, and cannot change a score.