Only 419 PASS Rows: Why Low-Risk MCP Candidates Are Narrow by Design
The public Registry has 419 PASS rows. That does not mean low-risk candidates do not exist; it means the evidence bar for calling an MCP server lower-risk is intentionally high.
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
In MCP, a small feature set is not enough to call something low-risk. Source, execution, outbound behavior, and unresolved evidence all need to close.
Key Findings
- The public Registry has 419 PASS rows. That does not mean low-risk candidates do not exist; it means the evidence bar for calling an MCP server lower-risk is intentionally high.
- 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 | 2026-05-20 |
| 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 |
|---|---|---|
| PASS rows | 419 | Public candidate closed as lower-risk |
| Public Registry entries | 20,629 | Public Registry population |
| Detailed PASS profile rows | 382 | Candidate closed as PASS in local profiles |
What We Observed
In MCP, a small feature set is not enough to call something low-risk. Source, execution, outbound behavior, and unresolved evidence all need to close. This lens matters because MCP servers are not just plugins; they are bundles of authority exposed to an AI agent.
Practical Reading
Even PASS candidates should be rechecked against the organization’s data sensitivity, user authority, and connected services. 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
Even PASS candidates should be rechecked against the organization’s data sensitivity, user authority, and connected services. 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.