An MCP Tool Description Is Also an Authority Description
detailed profile rows include 3,213 tool-authority observations. In MCP, tool names and descriptions are part of the authority boundary exposed to an AI agent.
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
An MCP tool description is not just documentation. The AI agent uses it to decide when and how to invoke the tool.
Key Findings
- detailed profile rows include 3,213 tool-authority observations. In MCP, tool names and descriptions are part of the authority boundary exposed to an AI agent.
- 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 | 2026-05-26 |
| 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 |
|---|---|---|
| Visible authority observations | 3,213 | Candidate where authority is visible from tool description |
| Static registration evidence | 8,406 | Candidate with static tool-registration evidence |
| Declared/static tool profiles | 8,406 | Candidate whose tool definition became review evidence |
What We Observed
An MCP tool description is not just documentation. The AI agent uses it to decide when and how to invoke the tool. This lens matters because MCP servers are not just plugins; they are bundles of authority exposed to an AI agent.
Practical Reading
Review tool names, descriptions, inputs, outputs, and failure behavior for over-broad authority or ambiguous instructions. 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 tool names, descriptions, inputs, outputs, and failure behavior for over-broad authority or ambiguous instructions. 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.