Metraipolis › archive › dc_7131f50e2e65

My Credentials, Please: Detecting Filesystem Capability Laundering in MCP Servers at Scale — arXiv:2610.22301

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22301
License (as archived)
CC0-1.0
Archived
2026-10-16T10:19:23.768Z
SHA-256 of the archived text
24d4bf46ba05deb7f9426c89c95f6eed93a500025e38a8d6a5cc8593b9302e8c
Stable URL of this page
https://metraipolis.com/documento/dc_7131f50e2e65

How to cite

My Credentials, Please: Detecting Filesystem Capability Laundering in MCP Servers at Scale — arXiv:2610.22301 — arXiv (en), https://arxiv.org/abs/2610.22301 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7131f50e2e65 (Metraipolis archive dc_7131f50e2e65, sha256 24d4bf46ba05deb7f9426c89c95f6eed93a500025e38a8d6a5cc8593b9302e8c)
BibTeX
@misc{dc7131f50e2e65,
  title = {My Credentials, Please: Detecting Filesystem Capability Laundering in MCP Servers at Scale — arXiv:2610.22301},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22301},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7131f50e2e65; sha256 24d4bf46ba05deb7f9426c89c95f6eed93a500025e38a8d6a5cc8593b9302e8c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22301. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The Model Context Protocol (MCP) standardizes how AI agents invoke external tools. MCP servers expose tools through a declared contract consisting of a name, description, and argument schema. In typical local deployments, client-side approval of a tool call grants the underlying server process broad host filesystem permissions rather than restricting it to the declared operation. We study the resulting vulnerability class, filesystem capability laundering, where attacker-steered arguments cause a tool to access sensitive host files outside its declared contract and deployment scope. We analyze this capability gap across three layers: server-category screening (L1), per-tool contract analysis (L2), and bypassable path-validation checks (L3). We design MCP-FSD to catalog MCP servers, infer least-privilege boundaries per tool, plant credential fixtures outside those boundaries, and evaluate exploitability and sandbox containment via paired dynamic execution. Across 21,097 MCP servers from nine registries, 787 of 4,806 triaged servers (16.4%) exhibit filesystem capabilities despite non-filesystem functional classifications. Dynamic three-case validation confirms 150 vulnerable instances under tested sandbox policies. Coordinated disclosure yielded 13 security advisories, including two CVEs in Anthropic's Git MCP Server.

Tema degli esploratori: fiducia digitale e crittografia (elenco arXiv cs.CR, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR).
Pagina del lavoro: https://arxiv.org/abs/2610.22301 — 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 2026-10-16T08:47:32.618Z dalla pagina https://arxiv.org/list/cs.CR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).