Metraipolis › archive › dc_df6bf9f137c2

ProbeID: Verifying MCP Tool Identity for LLM Agents under Registry Drift — arXiv:2610.33633

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.33633
License (as archived)
CC0-1.0
Archived
2026-10-27T08:00:21.993Z
SHA-256 of the archived text
cb4f8f9bdea9b91b4610d74d5388e2644e7f6de68dfbd65a54831b3f56139eee
Stable URL of this page
https://metraipolis.com/documento/dc_df6bf9f137c2

How to cite

ProbeID: Verifying MCP Tool Identity for LLM Agents under Registry Drift — arXiv:2610.33633 — arXiv (en), https://arxiv.org/abs/2610.33633 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_df6bf9f137c2 (Metraipolis archive dc_df6bf9f137c2, sha256 cb4f8f9bdea9b91b4610d74d5388e2644e7f6de68dfbd65a54831b3f56139eee)
BibTeX
@misc{dcdf6bf9f137c2,
  title = {ProbeID: Verifying MCP Tool Identity for LLM Agents under Registry Drift — arXiv:2610.33633},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33633},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_df6bf9f137c2; sha256 cb4f8f9bdea9b91b4610d74d5388e2644e7f6de68dfbd65a54831b3f56139eee},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33633. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Agents select tools by copyable descriptions, which cannot establish which implementation runs. ProbeID compares canonicalized responses to schema-valid probes with a trusted admission reference and abstains on ambiguity, so a squatter must copy probe-observable behavior. With the gold present, independent probes and a fixed margin, standard concentration arguments give a shared probe budget logarithmic in the candidate count and bound the joint probability of a wrong decision. On cached MCP-IdentityDrift cases, strict choice reaches \(0.956\) hit@1 while description routers fall near chance, but simpler exact comparisons tie it, MMD better tolerates heavy value noise, and a 32B behavioral judge is similarly accurate at higher cost. Random probes from agent banks and a prospective held-out study of 38 tools test theory-set thresholds. On the agent banks, equality refuses every reachable replacement from 64 probes and the bounded distance from 512, and sharper post hoc gates halve both. Two tools whose drift no bank probe reaches always pass. In an MCP-Bench agent, verification cuts tainted tasks from 15 to 9 of 16 at unchanged task success. Over eleven weeks, 7 of 59 real tools changed responses despite version pins. Verification depends on reference integrity, probe coverage, and response noise.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.33633 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-27T07:55:30.837Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).