1,398 Resource-Intensive Signals Show MCP Needs Cost Review Too
Resource-intensive signals appear in 1,398 profiles. MCP risk includes API quota, database reads, external billing, and local resource consumption, not only data leakage.
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
Repeated MCP calls by an AI agent can surface as a cost incident rather than a classic security incident.
Key Findings
- Resource-intensive signals appear in 1,398 profiles. MCP risk includes API quota, database reads, external billing, and local resource consumption, not only data leakage.
- 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 | 2026-06-04 |
| 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 |
|---|---|---|
| Resource-intensive signal | 1,398 | Observation near resource-intensive behavior |
| External mutation profiles | 2,555 | Candidate that can mutate external state |
| Network write signal | 6,032 | Observation near outbound transmission |
What We Observed
Repeated MCP calls by an AI agent can surface as a cost incident rather than a classic security incident. This lens matters because MCP servers are not just plugins; they are bundles of authority exposed to an AI agent.
Practical Reading
Review rate limits, dry-run behavior, budget alerts, row or request limits, and retry controls. 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
Review rate limits, dry-run behavior, budget alerts, row or request limits, and retry controls. 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.