1,832 npm-Package MCP Profiles and the Supply Chain Behind npx Installs
detailed profile rows include 1,832 npm-package targets and 8,376 git-repository targets. Easy npx installation makes package source, version pinning, and install behavior important.
Terminology
| Term | Meaning |
|---|---|
| Public Registry | Inspected MCP candidates searchable in the public Registry |
| Profile evidence | Inspection-profile aggregates used to interpret public candidates in more depth |
| Review/action rows | Entries in WARN, NEED_REVIEW, RESTRICT, or BLOCK that require reasoned adoption review |
Lead
MCP examples are often copied as one-line npx or uvx commands. That is convenient, but it hides version resolution, publisher trust, and dependency behavior.
Key Findings
- detailed profile rows include 1,832 npm-package targets and 8,376 git-repository targets. Easy npx installation makes package source, version pinning, and install behavior important.
- The 20,629 public Registry entries and 11,627 profile-evidence rows answer different questions and should not be mixed casually.
- The observation is an adoption input, not a final approval for a specific environment.
- Counts are snapshot evidence, so adoption review should check the observation date before treating the number as current state.
Dataset
| Item | Value |
|---|---|
| Article date | 2026-06-13 |
| Public Registry snapshot | 20,629 entries, synced 2026-06-06T01:17:38.963Z |
| Detailed profile evidence | 11,627 rows, generated 2026-05-20/21 |
| Public disclosure level | Aggregates, distributions, anonymized observations, and operational interpretation |
Observed Metrics
| Metric | Value | Meaning |
|---|---|---|
| npm package targets | 1,832 | Candidate distributed as an npm package |
| Git repository targets | 7,686 | Candidate whose primary target is a GitHub repository |
| Python package targets | 264 | Candidate distributed as a Python package |
What We Observed
MCP examples are often copied as one-line npx or uvx commands. That is convenient, but it hides version resolution, publisher trust, and dependency behavior. This lens matters because MCP servers are not just plugins; they are bundles of authority exposed to an AI agent.
Practical Reading
For production use, consider version pinning, publisher review, lockfiles, verified mirrors, and sandboxed execution. Review should record execution location, destinations, data touched, and unresolved evidence, not only the server name or README.
Limits
- The evidence uses public aggregate data and anonymized observations, not internal detection mechanics.
- Counts are snapshot values and will change as the Registry updates.
- This is not a claim that any named MCP server is safe or unsafe.
Conclusion
For production use, consider version pinning, publisher review, lockfiles, verified mirrors, and sandboxed execution. Keeping this evidence in the intake record makes the review repeatable across teams and deployments.
MCP Guard continuously turns public Registry and profile evidence into adoption-review signals for MCP security teams.