SaSame
FactoryPlansEvidenceOperationsFor AI Agents
Contact
FactoryPlansEvidenceOperationsFor AI Agents
Contact
SaSameSince 2019

One MCP Factory lifecycle for production, distribution, inspection and continuous observation across 21 stations.

Factory

  • Factory
  • Plans
  • Evidence
  • For AI Agents

Company

  • Operations
  • Contact
  • Privacy

For Machines

  • Public MCP
  • Factory start
  • Protocol Observatory
  • Factory public contract
  • Agent Card
  • llms.txt
  • llms-full.txt

Contact

  • consulting@srl-sasame.com
  • X / @SRLsasame
  • Operator
    SaSame SRL · Romania (EU) · CUI 50731520
Operations

© 2026 SaSame SRL. All rights reserved.

Factory Evidence Program

Paper 0: publication record with an open correction.

This is a public evidence and reproducibility record from the Factory's Layer-1 Evidence capability. It is not a separate product, endorsement, certification, ranking, safety verdict or North Star claim.

Open DOIZenodo v1.0.0Author ORCID

Cite this record

Fukui, K. (2026). The Registry-Runtime Gap in Agentic AI: A 35-Day Measurement of 31,407 Public Model Context Protocol Endpoint Records (Version 1.0.0) [Preprint]. Zenodo. https://doi.org/10.5281/zenodo.21513720

Correction status: open

The published and retained denominators are not reconciled.

The v1.0 publication title reports 31,407 discovered endpoint records. The retained latest-normalized-URL reproduction yields 31,408. Neither is presented here as a corrected denominator until the original frozen discovery or deduplication snapshot is recovered.

The exact state-changing classifier version and intermediate classified-tool table are also unrecovered, so the published 30,641 and 7,618 classifier-derived values remain publication claims rather than currently reproduced Factory facts.

What the retained ledger does reproduce

152,781

Repeated observations

Matches the frozen Paper 0 observation window.

4,162

Enumerable tool surfaces

Matches the frozen Paper 0 observation window.

78,041

Declared tools

Matches the frozen Paper 0 observation window.

78.2%

Overall annotation coverage

Matches the frozen Paper 0 observation window.

Publication boundary

Public aggregate evidence; private operational data.

The publication exposes aggregate methodology, integrity and correction status. It does not expose raw operational ledgers, credentials, owner-control material, suppression data or private topology.

What the study does not claim

  • Missing metadata does not establish unsafe behavior.
  • Observed metadata does not establish safety or trustworthiness.
  • Non-response can reflect authentication, policy, transport or measurement conditions.
  • Research visibility and downloads are not revenue.

A follow-on Paper 1 draft exists only on an unmerged research branch; it is prospective and non-authoritative pending provenance and owner-authority reconciliation tracked in issue #2026.