Secure Tool Manifest and Digital Signing Solution for Verifiable MCP and LLM Pipelines

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jamshidi, Saeid, Nafi, Kawser Wazed, Dakhel, Arghavan Moradi, Khomh, Foutse, Nikanjam, Amin, Hamdaqa, Mohammad Adnan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910006273638400
author Jamshidi, Saeid
Nafi, Kawser Wazed
Dakhel, Arghavan Moradi
Khomh, Foutse
Nikanjam, Amin
Hamdaqa, Mohammad Adnan
author_facet Jamshidi, Saeid
Nafi, Kawser Wazed
Dakhel, Arghavan Moradi
Khomh, Foutse
Nikanjam, Amin
Hamdaqa, Mohammad Adnan
contents Large Language Models (LLMs) are increasingly adopted in sensitive domains such as healthcare and financial institutions' data analytics; however, their execution pipelines remain vulnerable to manipulation and unverifiable behavior. Existing control mechanisms, such as the Model Context Protocol (MCP), define compliance policies for tool invocation but lack verifiable enforcement and transparent validation of model actions. To address this gap, we propose a novel Secure Tool Manifest and Digital Signing Framework, a structured and security-aware extension of Model Context Protocols. The framework enforces cryptographically signed manifests, integrates transparent verification logs, and isolates model-internal execution metadata from user-visible components to ensure verifiable execution integrity. Furthermore, the evaluation demonstrates that the framework scales nearly linearly (R-squared = 0.998), achieves near-perfect acceptance of valid executions while consistently rejecting invalid ones, and maintains balanced model utilization across execution pipelines.
format Preprint
id arxiv_https___arxiv_org_abs_2601_23132
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Secure Tool Manifest and Digital Signing Solution for Verifiable MCP and LLM Pipelines
Jamshidi, Saeid
Nafi, Kawser Wazed
Dakhel, Arghavan Moradi
Khomh, Foutse
Nikanjam, Amin
Hamdaqa, Mohammad Adnan
Cryptography and Security
Artificial Intelligence
Large Language Models (LLMs) are increasingly adopted in sensitive domains such as healthcare and financial institutions' data analytics; however, their execution pipelines remain vulnerable to manipulation and unverifiable behavior. Existing control mechanisms, such as the Model Context Protocol (MCP), define compliance policies for tool invocation but lack verifiable enforcement and transparent validation of model actions. To address this gap, we propose a novel Secure Tool Manifest and Digital Signing Framework, a structured and security-aware extension of Model Context Protocols. The framework enforces cryptographically signed manifests, integrates transparent verification logs, and isolates model-internal execution metadata from user-visible components to ensure verifiable execution integrity. Furthermore, the evaluation demonstrates that the framework scales nearly linearly (R-squared = 0.998), achieves near-perfect acceptance of valid executions while consistently rejecting invalid ones, and maintains balanced model utilization across execution pipelines.
title Secure Tool Manifest and Digital Signing Solution for Verifiable MCP and LLM Pipelines
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2601.23132