278 Remote-Service and 10,335 Local-Process Profiles Require Different Adoption Models
Remote public service profiles total 278, while local subprocess profiles total 10,335. MCP adoption should not use the same checklist for both models.
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
Local servers require review of endpoint authority, dependencies, files, and environment variables. Remote servers require review of transmitted data, authentication, operator trust, and retention.
Key Findings
- Remote public service profiles total 278, while local subprocess profiles total 10,335. MCP adoption should not use the same checklist for both models.
- 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 | 2026-06-16 |
| 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 |
|---|---|---|
| Local subprocess | 10,335 | Candidate launched on the endpoint |
| Remote public service | 278 | Candidate running as a remote service |
| Remote MCP targets | 1,213 | Candidate targeting a remote endpoint |
What We Observed
Local servers require review of endpoint authority, dependencies, files, and environment variables. Remote servers require review of transmitted data, authentication, operator trust, and retention. This lens matters because MCP servers are not just plugins; they are bundles of authority exposed to an AI agent.
Practical Reading
The first review question should be whether the server is a local process or a remote service. The checklist should branch from there. 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
The first review question should be whether the server is a local process or a remote service. The checklist should branch from there. 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.