Evidence over Narrative: Governing AI Agent Tool Calls under Shared Credentials

AI agents increasingly call real APIs through the Model Context Protocol (MCP), often with credentials shared between many agents, routers and orchestrators. The protocol gives no way to ask why a call is made, who approved it, or which agent behind a shared credential made it. I present a governance gateway that sits between agents and OpenAPI-described backends. It separates a deterministic core (permissions, four risk ratings, hard impact limits, and execution only from a stored, approved call) from advisory components: a reviewer model that questions the agent, and a human approval step run by external applications. Because a shared credential identifies only the principal, I define assurance levels A0 to A3 under which attribution is a claim until it is signed or verified, and a call whose assurance falls short has its risk rating raised, never lowered. Key claims in an agent's justification are checked against systems the agent cannot write to. I give a threat model, argue that, under the assumptions in Section 3.4, the main safety properties follow from the design, and discuss limitations, including that intent cannot be proven and that the gateway protects only the backend it fronts.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-14
DOI
https://doi.org/10.5281/zenodo.24212059
Primary Topic
Access Control and Trust
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Evidence over Narrative: Governing AI Agent Tool Calls under Shared Credentials

Arka Prava Ghosh
Zenodo (CERN European Organization for Nuclear Research)
Access Control and Trust
article

Evidence over Narrative: Governing AI Agent Tool Calls under Shared Credentials

Arka Prava Ghosh
article en

Abstract

AI agents increasingly call real APIs through the Model Context Protocol (MCP), often with credentials shared between many agents, routers and orchestrators. The protocol gives no way to ask why a call is made, who approved it, or which agent behind a shared credential made it. I present a governance gateway that sits between agents and OpenAPI-described backends. It separates a deterministic core (permissions, four risk ratings, hard impact limits, and execution only from a stored, approved call) from advisory components: a reviewer model that questions the agent, and a human approval step run by external applications. Because a shared credential identifies only the principal, I define assurance levels A0 to A3 under which attribution is a claim until it is signed or verified, and a call whose assurance falls short has its risk rating raised, never lowered. Key claims in an agent's justification are checked against systems the agent cannot write to. I give a threat model, argue that, under the assumptions in Section 3.4, the main safety properties follow from the design, and discuss limitations, including that intent cannot be proven and that the gateway protects only the backend it fronts.

Zenodo (CERN European Organization for Nuclear Research)
Access Control and Trust
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon