pragma.vision Your technology observatory

Verification register Agentic Commerce & Payments

Readiness verdict

Model Context Protocol (MCP)

A dated reading of what is claimed, reported, and independently verified in the current evidence.

As of
2026-06-28
Revision
1
Method
v1.0.0

Current reading

The readiness gap, in one scan

AI-assisted assembly · derived results

Claimed
80

Public ambition and stated capability

Reported
73

Observed practitioner reporting

Verified
66

Independently supported evidence

Gap
+14

Claimed minus verified

Evidence strength Strong

Decision

What the current evidence supports

Human editorial judgment · 2026-06-28

Adopt with guardrails

Why
Massive verified adoption (97M+ monthly SDK downloads, 9,652 registry servers) and we already run MCP servers, but the upcoming breaking RC plus authoritative auth/prompt-injection warnings demand guardrails, not a blind upgrade — and only ~41% of surveyed orgs are in any production stage.
Next
Pin to the 2026-11-25 stable spec now, prototype against the 2026-07-28 RC stateless transport in a branch, and enforce OAuth 2.1 + iss validation (RFC 9207) + explicit user-consent gates and least-privilege per-tool tokens on every server per NSA guidance before exposing any PII tool.

Constraints

Blockers

No named blocker is present in the current public projection.

Evidence summary

Derived counts

AI-assisted assembly

Total
7
Tier 1
0
Tier 2
3
Tier 3
4
Supports
3
Contradicts
2
Context
2
Latest observed
2026-05-24

Counts and dates only. Raw signals, private excerpts, trust records, and internal corpus material are not published here.

Publication record

Revisions

Initial public reading

This is the initial public reading. No earlier readiness change is recorded.

Your opinion

Tell us anything.

What works, what doesn't, what's missing — especially about our watches, lenses, and the register itself. Anonymous is fine; leave an email if you'd like a reply.