MCP Security

MCP: Model Context Protocol

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, down 50% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 23

Sep 22, 2026cs.CR

A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem

Agents using the Model Context Protocol (MCP) rely on semantic matching to select tools from third-party servers, exposing a semantic supply-chain risk through attacker-controlled metadata and outputs. We introduce A2M (Attraction-to-Manipulation), a two-stage black-box framework for hijacking MCP agents. The Attraction phase optimizes tool metadata to increase invocation probability; the Manipulation phase uses execution traces to refine adversarial tool returns that steer agents toward attacker-desired outcomes. On LiveMCPBench, direct attacks optimized and evaluated on GLM-4.6 achieve a macro-average malicious tool invocation rate of 93.6% across four scenarios, increase weighted token costs to 32.4

\times

the benign baseline under Cognitive Denial of Service, and attain a mean attack success rate of 74.4% across Information Exfiltration, Environment Integrity Compromise, and Reasoning Derailment. Transfer to four other models without re-optimization yields corresponding macro-averages of 63.6%, 2.7

\times

, and 24.5%. These findings motivate stronger tool vetting and runtime isolation in MCP ecosystems. Code is publicly available at https://github.com/Lilaizhen/A2M.

Laizhen Li, Xuan Wang, Peicheng Zhao +4

Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Nanyang Technological University +3

MCP Security AI Agent Security Black-Box Adversarial Attacks

Sep 9, 2026cs.CR

No-Box Vulnerability Analysis: Description-only Detection of Indirect Prompt Injection Vulnerabilities in MCP Servers

Conventional vulnerability analysis relies on either system access or dynamic interaction, all of which may be unavailable to third-party analysts auditing closed-source, remotely hosted, critical in situ systems, or commercially gated software. Therefore, we propose a new paradigm of no-box vulnerability analysis in which neither access nor runtime interaction is available, and only functionality metadata is available. Such metadata defines the intended behavior of the system, including its inputs, outputs, and side effects, while constraining the space of implementations consistent with that behavior. We propose hypothesizing about vulnerabilities that exist across all possible implementations of a given system metadata, without observing or interacting with the target system. An analyst can later validate these hypotheses when additional access is available. We showcase the feasibility of no-box vulnerability analysis through implementing a prototype called MCPSEC, which audits Model Context Protocol (MCP) servers for indirect prompt injection vulnerabilities using only the tool metadata exposed at server registration time. We evaluate MCPSEC on 20 widely deployed MCP servers comprising 177 tools, among which human evaluators confirm 95 vulnerable tools. MCPSEC identified 143 tools as vulnerable, and for each vulnerable tool, it produced a hypothesized vulnerability along with exploitation technique. Using metadata alone, MCPSEC predicted 94 (98.9% recall) real verified vulnerabilities, compared against an LLM baseline with 80 (84.2% recall). Overall, our results introduce no-box vulnerability analysis as a new analysis paradigm and demonstrate its practical feasibility in realistic systems.

Zehua Zhang, Jie Hu, Pratham Hegde +13

School of Computing and Augmented Intelligence, Arizona State University

MCP Security Software Vulnerability Detection Indirect Prompt Injection Prompt Injection Detection

Sep 1, 2026cs.CR

Public-Sharing Labels and Verbatim Field Egress in an MCP-to-A2A Agent Configuration: A Controlled Multi-Model Study

Safety properties assessed separately for Model Context Protocol (MCP) tool use and Agent2Agent (A2A) delegation need not describe behavior when one agent uses both. We measure one such behavior in a single controlled MCP-to-A2A configuration: a testbed drives a real-model host across a local MCP and a local A2A leg into an ordered event trace scored by exact deterministic rules (no LLM judge), one restricted decision per trial. In a pre-specified, frozen three-arm design, each of 10 record scenarios appears with a CONFIDENTIAL header, with no header, and with PUBLIC - OK TO SHARE; the six substantive record values are byte-identical across arms, and the outcome is verbatim occurrence of any of them in the outbound message. Four models x 3 arms x 4 repeats give 480 trials; the scenario is the unit of generalization, and we report the 10 scenario-level values (mean, median, sign counts), with no p-values or intervals. The confidential-minus-unlabeled contrast is inconclusive and floor-limited in every model (both arms at or near zero), so it does not show that confidential labels lack a protective effect. Adding PUBLIC - OK TO SHARE is descriptively associated with higher verbatim egress relative to the unlabeled baseline, with strong model dependence: strong and consistent for Claude Sonnet 5 (public-minus-unlabeled mean +0.800, all 10 scenarios; mostly an association with whether Claude relays at all), moderate but floor-limited for one GPT-5.6 tier, small (median 0) for another, and a complete floor for the third. This is an association in one configuration, not a causal or general effect. Code, byte-pinned traces, and the offline analysis pipeline are released as a public artifact.

Arpan Kumar Mahapatra

MCP Security LLM Agent Security Privacy Leakage in Language Models Multi-Agent System Security

Aug 30, 2026cs.CR

Zero-Knowledge Predicate Proofs Between AI Agents: A Measured, Cross-Protocol Gateway and the Source-Integrity Gap

Multi-agent AI platforms move quickly from staging to production, but the way agents establish trust remains rudimentary: an agent either transmits raw data to a peer or accepts that peer's natural-language self-report that a value complies with policy. The first over-shares; the second is unverifiable and is exactly the channel prompt injection attacks. Prevailing responses emphasise identity, visibility, and post-hoc detection, and recent proposals for cryptographically enforced agent policy have been evaluated in simulation rather than execution. We take provable data minimisation between agents from proposal to running system. In our Zero-Knowledge Proof Gateway, agents exchange proofs of governance-defined predicates over private data rather than the data itself, so exposure is prevented by design rather than detected afterwards; because no interoperability protocol can carry such a proof, we propose a slot and implement it on both MCP and Agent2Agent from one endpoint. A 32-bit threshold predicate proves in 6.2 ms and verifies in 1.0 ms with a 608-byte Bulletproofs proof on one commodity vCPU; eleven adversarial experiments and nineteen protocol checks pass; and the system is deployed to Kubernetes with empirically verified network isolation. Our case study proves a retail client order is within its limit without revealing the amount, instantiating the GDPR data-minimisation principle as an enforced technical measure of the kind EU law now names explicitly. We then address the limitation no comparable work resolves: a predicate proof binds a statement to a committed value, never to the system of record. We give a construction fusing an enclave attestation with the proof in both directions, so verifying one artifact certifies jointly that the predicate holds and that the value was read by a specific measured binary, and test it against a mock authority.

Ashok Subbabhatta Gopalakrishna

independent researcher

Agent Communication Protocols MCP Security Remote Attestation AI Agent Security Zero-Knowledge Proofs

Aug 13, 2026cs.CR

Labels Are Not Endpoints: Treatment Leakage and Construct Validity in MCP Agent Security Evaluation

Security evaluations of tool-using agents often equate stored labels with behavioral facts. We audit a preserved campaign by tracing 10,200 execution rows to 180 model-bound requests, 45 semantic requests, and 15 observable stimuli. Two schema treatments were delivered, but the planned external payload-family corpus was not. The historical grader exhibited direct treatment leakage: treatment metadata gated the ATTACK_SUCCESS class, so fixed behavior could change class under treatment relabeling. A treatment-blind reconstruction corrects 58 historical ATTACK_SUCCESS or HIJACK_ATTEMPT labels to authorized benign completions while preserving three verified protected-data transfers and one separate unauthorized-forwarding case. The locked v2 census contains exactly zero ATTACK_SUCCESS records, while the forwarding case remains a HIJACK_ATTEMPT at a semantic boundary concerning objective completion. A dual-reviewer blinded concordance review of all 96 requests deemed structurally interpretable by locked v2 produced identical reviewer-consensus classes but differed from the locked codebook on four construct-boundary cases. We contribute a seven-link Integrity Chain and an executable, scope-bounded endpoint-integrity linter. The result is a campaign-bounded measurement audit, not a population attack-rate, model-ranking, defense-efficacy, or causal estimate.

Rana Muhammad Ahmed, Sabahat Abbas

Department of Computer Science, Bahria University, Islamabad, Pakistan

MCP Security LLM Agent Security AI Agent Security Benchmarks Benchmark Validity

Aug 11, 2026cs.CR

A Gateway Architecture for Enterprise MCP Authentication: Unifying Heterogeneous Auth, Identity Delegation, and the User / Non-User Persona Problem

The Model Context Protocol (MCP) has become the de-facto interface for connecting LLM agents to enterprise tools, and adoption has been explosive: within a year, large organizations went from zero to dozens of internally built MCP servers. That speed created a governance crisis. Each team implemented authentication independently -- some with no auth, some with API keys, some with full OAuth -- producing a fragmented landscape with no consistent way to authorize callers, track who did what, or offboard a departing employee across the fleet. This paper reports an industry deployment that resolves the crisis with a centralized MCP gateway: a single aggregation, governance, and authentication layer that fronts every downstream MCP server. We make four contributions grounded in production experience. First, a two-axis authentication model crossing persona (interactive user vs. automated non-user) with credential type (no-auth, static/dynamic API key, PKCE, client credentials, platform app-context). Second, a gateway authentication layer supporting three enterprise SSO grants and three token-provisioning models: Bring-Your-Own-Token, Generate-Your-Own-Token, and delegated OAuth via RFC 8693 token exchange. Third, three end-to-end identity flows -- User-to-OAuth2, Non-user-to-Service-Account, and User-to-Service-Account -- composing client, gateway, and server. Fourth, the deployment evolution from CDN/WAF/edge perimeter to private MCP tunnels and enterprise-wide connectors. The architecture is in production, fronting dozens of MCP servers across web, desktop, custom-SDK, and low-code clients.

Suraj Kumar, Amy Wang, Srinivasan Manoharan

Enterprise AI Platform Engineering

MCP Security Tool-Use Authorization Access Control

Aug 6, 2026cs.CR

Hardware Keystores for AI Agent Signing Workflows: A Zero-Trust MCP Enforcement Architecture

AI agents increasingly sign Git commits, certify documents, and attest release artifacts on behalf of their operators, using private keys that live in software-accessible locations (plaintext files, environment variables, container memory) readable by any process the agent can reach. A widely deployed agent framework recently leaked its keys this way to a single email injection. Hardware keystores (HSM, TPM, smart card) keep the key on-device, but exposing the keystore as a tool an LLM agent can call moves the problem rather than removing it: once a signing session exists, the hardware cannot tell a request reflecting the operator's intent from one injected into content the agent read. We characterize this confused-deputy problem and build the five-layer Zero-Trust enforcement stack it requires, so that only requests consistent with the operator's committed intent reach the hardware. We evaluate on two attack planes. Prompt injection in content the agent reads (AgentDojo, three injection-following models, n=144) falls from an 18.1% baseline attack success rate to 0% under the full stack. Tool poisoning by a compromised MCP server (MCPTox) is contained identically: a hash comparison protects a pre-committed payload, and human-in-the-loop escalation contains autonomous requests with nothing pre-committed. A further probe delineates how far the semantic filter's protection extends: it detects a substitute document under an unrelated name, but an adversarially plausible substitute name defeats it in every trial we ran. We report this as a central finding: the architecture's guarantee never rests on the filter being right, only on a human being asked whenever nothing was committed in advance. The trade-off we characterize across both planes is that the less an operator can commit to in advance, the less deterministic the resulting guarantee, down to asking a human.

Leo Sambrook, Sampo Sovio

Hardware Systems Security Lab (HSSL) Huawei Technologies & EPITA Helsinki, Finland

MCP Security AI Agent Security LLM Agent Security Prompt Injection Attacks on AI Agents Tool Access Control for LLM Agents Zero-Trust Security

Jul 31, 2026cs.CR

Exposed by Design: A Dynamic Security Assessment of Internet-Facing MCP Servers at Scale

The Model Context Protocol (MCP) has seen rapid adoption since its November 2024 launch, with over 21,000 server instances detectable on the public internet. We present the first dynamic behavioral security assessment of internet-facing MCP servers, combining passive discovery across eleven data sources (crt.sh, HuggingFace, GitHub, npm, Smithery, PyPI, Censys, FOFA, Shodan, glama.ai, and pulsemcp.com) with active dynamic testing using Corvus, a purpose-built framework implementing 34 test modules covering 10 MCP-specific vulnerability classes. Across four measurement runs spanning July 2026, we confirm 640 production MCP servers and dynamically audit 414, uncovering 68 reportable vulnerabilities including SQL injection, SSRF targeting cloud metadata services, prompt template injection, and path traversal via cursor manipulation. We find that 91.8% of dynamically audited servers lack OAuth authentication, 687 tool instances across confirmed servers expose shell execution capabilities without access controls, and 41.6% of confirmed servers disappear within three days between consecutive measurement runs---indicating rapid deployment cycles without security review. We report on our responsible disclosure pipeline and release Corvus as an open-source framework for MCP security evaluation.

Nicolás Padilla

CobaltoSec

MCP Security Software Vulnerability Detection Software Security

Jul 28, 2026cs.CR

Hybrid Analysis for Secure MCP Tool Use in LLM Agents

The rapid development of large language model (LLM) agents has enabled their broad adoption across diverse real-world tasks. To standardize interactions between LLM agents and external environments, Model Context Protocol (MCP) tools have emerged as a de facto standard and have been widely integrated into these systems. However, the use of MCP tools also introduces new safety risks, as LLM agents can be induced to perform malicious or unauthorized actions. Although prior work has proposed defenses for securing tool use in LLM agents, most methods rely on static analysis, i.e., inspecting prompts and generated outputs, which limits the defense effectiveness and robustness. To address these limitations, we propose MTGuard, a hybrid analysis-based defense framework designed to safeguard the use of MCP tools in LLM agents by leveraging lifecycle-aware static-dynamic co-analysis. Extensive evaluation demonstrates that MTGuard effectively mitigates multiple categories of harmful tool use across different LLM agents while maintaining performance on benign user tasks.

Ping He, Yuexiang Xie, Yaliang Li +1

Zhejiang University · Alibaba Group

MCP Security LLM Agent Security Tool Access Control for LLM Agents

Jul 20, 2026cs.CR

ChainWatch: A Kill Chain-Aligned Sequential Detection Framework for Multi-Step Attacks in MCP-Based AI Agent Systems

The Model Context Protocol (MCP) is an open-source standard that allows AI agents to connect to external tools, databases, and services. While this connectivity enables powerful agent capabilities, it also introduces multi-step attacks that existing per-call defenses cannot reliably detect. Attackers can compose individually benign tool invocations into malicious sequences that evade isolated inspection. This paper presents ChainWatch, a sequential detection framework for identifying multi-step attacks in MCP-based AI agent systems. ChainWatch models attack progression using a six-stage kill chain and applies a Hidden Markov Model (HMM) to classify tool-call sequences. Detection rules are triggered when a session exhibits suspicious progression across multiple stages. The framework is supported by a structured threat model covering direct sequential attacks, indirect prompt injection chains, and hybrid multi-stage attacks. A 20-dimensional feature extraction schema captures behavioral signals from tool interactions. We demonstrate the approach using five representative attack scenarios from the security literature, showing how ChainWatch detects attack chains that evade traditional per-call security mechanisms.

Om Narayan, Rashmi Jyoti, Ramkinker Singh

Computer Science New York University New York, USA · Cybersecurity University of Maryland, College Park MD, USA · Carnegie Mellon University Pittsburgh, USA

MCP Security AI Agent Security AI Agent Monitoring

Jul 7, 2026cs.CR

Unicode TAG-Block Concealment of Tool-Metadata Payloads in the Model Context Protocol: An Approval-View Fidelity Gap Across Three Independent Server Implementations

The Model Context Protocol (MCP) is the dominant way coding agents discover and invoke external tools. A server advertises each tool through a tools/list handshake that returns a name, a natural-language description, and a JSON input schema. The client renders this metadata once, in a one-time approval dialog, and then injects it verbatim into the model's context on every subsequent turn. Nothing in the protocol requires the rendered approval view and the bytes delivered to the model to match. We isolate that gap as a single structural mechanism, concealment encoding, and show with a model-free, protocol-free analysis that Unicode's TAG block (U+E0000 to U+E007F) has no assigned glyph in any mainstream terminal, chat, or IDE renderer, so a payload written in it is absent from what a human reviewer sees while surviving byte-for-byte into the model's tokenizer. We then measure whether this mechanism actually defeats today's client-side defenses, building a proof-of-concept that speaks the real MCP JSON-RPC/stdio protocol against a genuine client and server. Across 5 distinct MCP metadata surfaces we implement 8 concrete techniques with a deterministic, protocol-level harness. All 8/8 techniques deliver an attacker-controlled payload into the model's context, 4/8 evade a representative string-matching sanitizer, and exactly as the mechanism analysis predicts, only the TAG-block encoding (1/8) is invisible in the human approval view while still reaching the model verbatim. MCP forces re-approval for 0/8 techniques even under a time-of-check to time-of-use rug-pull. To test whether these outcomes are a property of the protocol or an artifact of one server codebase, we re-implement the catalogue against 3 independently developed Python MCP server libraries and find total agreement across all 32 cross-library outcome cells. The baseline sanitizer flags 0 of 25 benign descriptions.

Mohammadreza Rashidi

Department of Computer Science AI and Media Analysis Lab Berlin, Germany

Adversarial Attacks MCP Security Indirect Prompt Injection Model Context Protocol

Jun 27, 2026cs.CR

From Tool Connection to Execution Control: Benchmarking Security Invariants in MCP-Style Agent Runtimes

Model Context Protocol (MCP)-style ecosystems give language-model applications a practical connection layer for tools, resources, prompts, and transports. As agents move from connection to execution, security decisions often remain split across clients, servers, prompts, approval dialogs, OAuth deployments, and logs. This paper asks whether a runtime can make execution-layer invariants explicit and testable while preserving MCP-like workflows. We define eight invariants: metadata non-authority, grant-backed approval, canonical resources, principal binding, scoped capability invocation, source-and-target data-flow authorization, deny-path audit, and explicit protocol state. We implement these invariants in HCP, a Handle-Capability Protocol reference runtime for MCP-style agent execution that represents calls through principals, resources, grants, capabilities, handles, policy decisions, data-pipe checks, and audit entries. We evaluate HCP against two MCP-like baselines: a naive connection-layer runtime and a practice-informed connection-layer mitigation baseline with metadata linting, session checks, and per-call approvals. Across 10 benchmark cases, the naive baseline permits all modeled attacks, the mitigation baseline permits 6 of 10, and HCP blocks all 10 while preserving audit evidence. Ablations identify which runtime components block attacks and preserve forensic evidence. A local in-memory microbenchmark reports sub-millisecond mean latencies for measured policy, invocation, peek, and pipe operations. A bounded GitHub README-screening sample provides ecosystem signals, not vulnerability findings. The results support a narrow claim: MCP-style agent systems need an execution-control layer in addition to connection-layer conventions.

Ting Liu

SymbolicLight Research Foshan, Guangdong, China

MCP Security LLM Agent Security AI Agent Security Benchmarks Capability-Based Security Tool Access Control for LLM Agents Runtime Verification

Jun 25, 2026cs.CR

ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP

With the rapid evolution of LLM-driven agents, Model Context Protocol (MCP), an open protocol bridging LLMs with external tools, has quickly become foundational to modern agent ecosystems. However, the expanding adoption of MCP has also introduced novel security concerns such as Tool Poisoning Attack (TPA), which exploit LLM-server interactions to inject malicious prompts. Existing poisoning schemes typically adopt a monolithic plaintext embedding paradigm, which fails to withstand manual inspection or automated detectors. Current research still lacks a systematic analysis on multi-tool poisoning, where multiple tools can be exploited cooperatively to disperse detection risk. In this paper, we introduce ShareLock, a multi-tool threshold poisoning framework that utilizes Shamir's threshold scheme to ensure exceptional stealth and fault tolerance. ShareLock distributes the malicious instruction as benign-looking secret shares across multiple tool descriptions, achieving both information-theoretic secrecy and attack robustness against moderate auditing. After a covert reconstruction trigger is planted during server update, the aggregated shares reconstruct the hidden instruction, resulting in critical breaches of system assets or private data. To evaluate the realistic threat of ShareLock, we constructed a comprehensive benchmark encompassing four multi-tool scenarios and conducted extensive experiments across mainstream LLMs on two distinct MCP clients. Our results demonstrate that ShareLock significantly outperforms existing single-tool poisoning strategies in tool description-based detection while maintaining an average attack success rate exceeding 90%.

Liwei Liu, Tianzhu Han, Zijian Liu +2

Shanghai Jiao Tong University · Shanghai, China

Adversarial Attacks MCP Security LLM Security Data Poisoning Attacks

Jun 3, 2026cs.CR

Description-Code Inconsistency in Real-world MCP Servers: Measurement, Detection, and Security Implications

The Model Context Protocol (MCP) has emerged as a critical standard empowering Large Language Models (LLMs) to utilize external tools. In this ecosystem, LLMs rely on natural language descriptions provided by MCP servers to select and execute functions. This interaction implicitly assumes that tool descriptions faithfully reflect their underlying implementations, while this assumption is not mandatorily verified in practice. As a result, MCP deployments may suffer from a problem named Description-Code Inconsistency (DCI), where a tool's description of its capabilities and security boundaries is not consistent with what the code actually does. In this paper, we present a comprehensive study of DCI in real-world MCP servers. We formally define the problem and propose a comprehensive taxonomy spanning functionality inconsistencies and undeclared side effects. Guided by this taxonomy, we develop DCIChecker, an automated framework that combines structure-aware static analysis with the Direct-Reverse-Arbitration prompting method to cross-validate tool descriptions against actual code implementations. We apply this framework to a large-scale dataset comprising 19,200 description-code pairs extracted from 2,214 real-world MCP servers. Our measurement reveals that DCI is widespread, with 9.93% of these pairs exhibiting inconsistencies. We further demonstrate that DCI creates a critical defense blind spot, facilitating varied risks from operational failures to stealthy malicious behaviors. Finally, we propose mitigation strategies to enforce semantic consistency and enhance the reliability of the emerging agentic ecosystem.

Yutao Shi, Xiaohan Zhang, Xiangjing Zhang +5

Fudan University, China

MCP Security AI Agent Security

May 24, 2026cs.NI

Device Context Protocol: A Compact, Safety-First Architecture for LLM-Driven Control of Constrained Devices

Large language models are increasingly used as orchestrators of external tools via the Model Context Protocol (MCP), but MCP is built for software services with megabytes of memory and does not descend to the microcontrollers that dominate the long tail of physical devices. Recent work (IoT-MCP) ports MCP to edge gateways at 74 KB peak memory; this still excludes the smallest commodity MCUs and, critically, does not address the safety problem of giving an unreliable caller (an LLM that may hallucinate or be prompt-injected) direct control of physical hardware. We present the Device Context Protocol (DCP): a sub-50-byte typical frame (6-byte header + CBOR payload + optional 16-byte HMAC), a manifest schema in which capability scoping, range and type checks, dry-run evaluation, and units-as-types are protocol-layer primitives, and a host-side Bridge that rejects malformed or hallucinated calls before any byte reaches the device. Reference firmware measures 27.6 KB flash / 0.6 KB RAM on ESP32; the Python Bridge, ESP32 firmware, and a language-neutral conformance suite are MIT-licensed and public. An empirical study -- 675 tool calls produced by five LLMs across four vendors (DeepSeek, Alibaba, Zhipu, MiniMax) against six categories of adversarial prompts, with the injection category instantiating AgentDojo's attack templates -- shows DCP rejects 100% of capability-escalation attempts and 78% of prompt-injection attempts, versus 0--1% for Raw MCP and IoT-MCP, matching the expressiveness of a well-formed OpenAPI 3 schema at three orders of magnitude less firmware footprint. We position DCP as the missing layer between MCP (which is moving toward enterprise SaaS connectivity) and the physical devices it does not reach.

Dongxu Yang

1DeepLethe

Language Model-Based Control MCP Security LLM Agent Safety

May 22, 2026cs.CR

Attested Tool-Server Admission: A Security Extension to the Model Context Protocol

The Model Context Protocol (MCP) standardizes how a large-language-model (LLM) agent and an external tool server exchange messages, but not trust: a host reads a server's self-declared tool list and dispatches calls, with no notion of which servers it may use, at what sensitivity, or which of a server's tools are in bounds. This work grew out of a concrete need -- letting the Enclawed agent use Google's externally-operated MCP servers (Gmail, Calendar, Drive) safely, admitting the server and bounding the tools it may drive, without changing MCP or Enclawed's own tool application-programming interface (API). The mechanism we built, mcp-attested (shipped in both the open enclawed-oss distribution and the enclaved flavor), generalizes: the gap that makes an unmediated third-party connection unsafe for one user makes a regulated deployment impossible to accredit. We close it with three additive mechanisms: (1) a small, offline-signed clearance assertion a server publishes at a well-known Uniform Resource Identifier (URI) and a host verifies against a pinned trust root before any tool dispatch; (2) a deny-by-default per-server tool allowlist, so admitting a server is not trusting its every tool; and (3) a flavor-gated enforcement mode that turns the checks from warnings into hard denials, with every decision written to a tamper-evident audit log. We give the wire format, the verification algorithm, a security analysis, and an LLM-driven adversarial evaluation; we then state the design in normative Request-for-Comments (RFC 2119) form -- schema, verification rules, error registry, well-known registration, and machine-checkable conformance vectors -- so it can be adopted as an MCP addendum rather than reinvented. An unextended host ignores the well-known document and behaves exactly as today.

Alfredo Metere

Enclawed LLC

MCP Security AI Agent Security Model Context Protocol Tool-Use Authorization Tamper-Evident Logging

May 22, 2026cs.CR

When the Manual Lies: A Realistic Benchmark to Evaluate MCP Poisoning Attacks for LLM Agents

The rise of tool-using Large Language Model (LLM) agents, standardized by protocols like the Model Context Protocol (MCP), has unlocked unprecedented autonomous execution capabilities for LLM Agents by integrating external open-domain knowledge and tools. However, this interoperability introduces a covert attack surface targeting the agent's cognitive planning layer. This paper systematically investigates Tool Description Poisoning (TDP), a novel semantic attack. In TDP, malicious instructions are not embedded in a tool's executable code, but rather covertly injected into its descriptive metadata, the very "manual" an agent relies on for secure planning and decision-making. To rigorously and systematically evaluate this emerging threat, we introduce the MCP-TDP Security Benchmark. This high-fidelity sandbox environment comprises 32 realistic, real-world test cases spanning 6 distinct risk categories. Our evaluation of 8 mainstream LLMs reveals severe vulnerabilities, with leading models like GPT-4o exhibiting a nearly 100% Attack Success Rate (ASR) in six high-risk scenarios. Furthermore, our findings demonstrate that common prompt-guardrail defenses are largely ineffective and can, counterintuitively, even be counterproductive (a phenomenon which we term the "Firewall Fallacy"). Crucially, we also propose a defense mechanism: "Reactive Self-Correction," where an agent autonomously detects and reverts its own malicious actions post-execution. This work provides the first specialized security benchmark tailored for TDP, offering essential insights for securing the cognitive and planning layers of advanced agentic systems.

Shi Liu, Xuehai Tang, Xikang Yang +4

Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China

MCP Security LLM Agent Security AI Agent Security Benchmarks

May 17, 2026cs.AI

ADR: An Agentic Detection System for Enterprise Agentic AI Security

We present the Agentic AI Detection and Response (ADR) system, the first large-scale, production-proven enterprise framework for securing AI agents operating through the Model Context Protocol (MCP). We identify three persistent challenges in this domain: (1) limited observability -- existing Endpoint Detection and Response (EDR) tools see file writes but not the agent reasoning, prompts, or causal chains linking intent to execution; (2) insufficient robustness -- static defenses constrained by pre-defined rules fail to generalize across diverse attack techniques and enterprise contexts; and (3) high detection costs -- LLM-based inference is prohibitively expensive at scale. ADR addresses these challenges via three components: the ADR Sensor for high-fidelity agentic telemetry, the ADR Explorer for systematic pre-deployment red teaming and hard-example generation, and the ADR Detector for scalable, two-tier online detection combining fast triage with context-aware reasoning. Deployed at Uber for over ten months, ADR has sustained reliable detection in production with growing adoption reaching over 7,200 unique hosts and processing over 10,000 agent sessions daily, uncovering hundreds of credential exposures across 26 categories and enabling a shift-left prevention layer (97.2% precision, 206 detected credentials). To validate the approach and enable community adoption, we introduce ADR-Bench (302 tasks, 17 techniques, 133 MCP servers), where ADR achieves zero false positives while detecting 67% of attacks -- outperforming three state-of-the-art baselines (ALRPHFS, GuardAgent, LlamaFirewall) by 2--4x in F1-score. On AgentDojo (public prompt injection benchmark), ADR detects all attacks with only three false alarms out of 93 tasks.

Chenning Li, Pan Hu, Justin Xu +9

Uber Technologies, Inc., USA · Massachusetts Institute of Technology, USA · University of Oxford, United Kingdom

MCP Security AI Agent Security AI Agent Security Benchmarks

May 12, 2026cs.CR

Options, Not Clicks: Lattice Refinement for Consent-Driven MCP Authorization

As Model Context Protocol adoption grows, securing tool invocations via meaningful user consent has become a critical challenge, as existing methods, broad always allow toggles or opaque LLM-based decisions, fail to account for dangerous call arguments and often lead to consent fatigue. In this work, we present Conleash, a client-side middleware that enforces boundary-scoped authorization by utilizing a risk lattice to auto-permit safe calls within known boundaries while escalating risks, a policy engine for user-defined invariants, and a refinement loop that converts user decisions into reusable rules. Evaluated on 984 real-world traces, Conleash achieved 98.2% accuracy, caught 99.4% of escalations, and added only 8.2 ms of overhead for policy verification; furthermore, in a user study where N=16, participants significantly preferred Conleash scoped permissions over traditional methods, citing higher trust and reduced prompting.

Ying Li, Yanju Chen, Peiran Wang +4

University of California, Los Angeles USA · University of California, San Diego USA · University of Texas at Arlington USA +1

MCP Security Tool-Use Authorization Access Control Tool Access Control for LLM Agents

Apr 30, 2026cs.AI

MCPHunt: An Evaluation Framework for Cross-Boundary Data Propagation in Multi-Server MCP Agents

Multi-server MCP agents create an information-flow control problem: faithful tool composition can turn individually benign read/write permissions into cross-boundary credential propagation -- a structural side effect of workflow topology, not necessarily malicious model behavior. We present MCPHunt, to our knowledge the first controlled benchmark that isolates non-adversarial, verbatim credential propagation across multi-server MCP trust boundaries, with three methodological contributions: (1) canary-based taint tracking that reduces propagation detection to objective string matching; (2) an environment-controlled coverage design with risky, benign, and hard-negative conditions that validates pipeline soundness and controls for credential-format confounds; (3) CRS stratification that disentangles task-mandated propagation (faithful execution of verbatim-transfer instructions) from policy-violating propagation (credentials included despite the option to redact). Across 3,615 main-benchmark traces from 5 models spanning 147 tasks and 9 mechanism families, policy-violating propagation rates reach 11.5--41.3% across all models. This propagation is pathway-specific (25x cross-mechanism range) and concentrated in browser-mediated data flows; hard-negative controls provide evidence that production-format credentials are not necessary -- prompt-directed cross-boundary data flow is sufficient. A prompt-mitigation study across 3 models reduces policy-violating propagation by up to 97% while preserving 80.5% utility, but effectiveness varies with instruction-following capability -- suggesting that prompt-level defenses alone may not suffice. Code, traces, and labeling pipeline are released under MIT and CC BY 4.0.

Haonan Li, Tianjun Sun, Yongqing Wang +1

Key Laboratory of Intraplate Volcanoes and Earthquakes (China University of Geosciences, Beijing), Ministry of Education, Beijing 100083, China · School of Geophysics and Information Technology, China University of Geosciences, Beijing 100083, China

MCP Security Privacy Leakage in Language Models AI Agent Security Benchmarks

Apr 18, 2026cs.CR

CASCADE: A Component Ablation and Corpus Audit of a Layered Local Defense for MCP-Based Systems

The Model Context Protocol (MCP) widens the prompt injection attack surface of large language model applications to tool descriptions, parameter schemas, and tool outputs. Defenses for it are appearing quickly, but their reported figures are not comparable: each is evaluated on a corpus of its authors' construction, under a decision convention that is rarely stated. This paper asks how much those choices decide, taking CASCADE, a fully local layered defense, as the case: three configurations on a frozen 5,000-sample corpus under a pinned revision and a fixed protocol, with that corpus audited in full. Four results follow. First, the aggregation convention dominates the headline metric: counting review referrals as positives reports an 11.70% false-positive rate where 1.51% of benign traffic would be denied without a human, and conceals that 68.5% of all traffic reaches a reviewer. Second, detection is not provenance-invariant: recall ranges from 86.20% on original material to 99.88% on template-generated material, and added false positives fall on original benign records at ten times the rate they fall on transformed ones. Third, the operating point that ran is not readable from the released configuration, which names four candidate thresholds, its deployment files selecting one that did not govern; it is recoverable from point masses the policy layer leaves in the score distribution, so record-level output is a stronger reproducibility guarantee than a parameter table. Fourth, a local review model invoked for 32.56% of requests at 2.51 s each changes no classification outcome: it returned 90 not-malicious verdicts and the policy stage admitted none, making that null a guard setting rather than a model property. The ablation is unsurprising -- the rule-based layer reaches 61.05% recall, the semantic stage 94.77% -- and that is what makes the other results the substance of the paper.

İpek Abasıkeleş Turgut, Edip Gümüş

Department of Computer Engineering, Faculty of Engineering and Natural Sciences, Iskenderun Technical University, Hatay, Türkiye · Department of Computer Engineering, Institute of Graduate Studies, Iskenderun Technical University, Hatay, Türkiye

MCP Security LLM Security Prompt Injection Defense Prompt Injection Detection

Apr 18, 2026cs.CR

Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety Primitives

AI agents increasingly call external tools (file system, network, APIs) through the Model Context Protocol (MCP). These tool calls are the agent's syscalls: privileged operations with side effects on shared state, yet today's safety enforcement lives entirely in userspace, where a 10-line script can bypass it. I propose Governed MCP, a kernel-resident tool governance gateway built on a logit-based safety primitive (ProbeLogits). The gateway interposes on every MCP tool call in a 6-layer pipeline: schema validation, trust tier, rate limit, adversarial pre-filter, a ProbeLogits semantic gate (the load-bearing check), and constitutional policy match, with a Blake3-hashed audit chain. I implement Governed MCP in Anima OS, a bare-metal x86-64 kernel in ~286,000 lines of Rust. The five non-inference layers plus the audit append cost a measured 11.3 us per call; the ProbeLogits gate (one probe-prompt prefill plus a single logit read) costs 332-556 ms per classification across Qwen2.5-7B, Llama-3-8B, and Mistral-7B, 2.4-3.4x faster than a Llama Guard 3 pass on the same hardware. A silicon-measured ablation shows that removing the ProbeLogits layer collapses F1 from 0.789 to 0.357 (delta-F1 = -0.432): hand-rule firewalling alone is insufficient. Every WASM-to-system host function and every registered MCP tool is mediated by the kernel gateway, so the 10-line userspace bypass that defeats existing guardrail libraries is structurally impossible; a disclosed set of ring-3 syscall paths remains ungated pending future work. Multi-model validation across three architectures (HarmBench 98-99% non-copyright block, XSTest 98.5-100% unsafe recall, ToxicChat parity with Llama Guard 3) shows the underlying primitive is architecture-agnostic. Governed MCP demonstrates that tool-call governance is feasible as an OS primitive, not just an application-layer concern.

Daeyeon Son

Independent Researcher · Republic of Korea

MCP Security AI Agent Security Safety Filtering Runtime Enforcement for AI Agents AI Agent Governance Access Control+1

Jan 30, 2026cs.CR

Verifiable Manifest Signing and Transparency Enforcement for Secure MCP-Based LLM Pipelines

Large Language Models (LLMs) are increasingly deployed in tool-driven environments such as healthcare analytics, financial systems, retrieval-augmented generation (RAG), and multi-agent workflows. Although the Model Context Protocol (MCP) standardizes how LLM applications expose and invoke external tools, its baseline model does not require tool-use manifests to be cryptographically authenticated, freshness-checked, policy-bound, or independently auditable before execution. As a result, MCP pipelines may remain vulnerable to manifest tampering, unauthorized tool invocation, replay of stale requests, and weak accountability. This paper presents a manifest-level enforcement layer for MCP-based LLM pipelines. It treats each MCP tool-use manifest as a first-class security object whose canonical form must be policy-validated, freshness-checked, digitally signed, verified before execution, and linked to tamper-evident audit evidence. The framework binds tool invocation to verifiable manifest integrity and fail-closed authorization, separates user-visible request parameters from execution metadata, rejects non-compliant or stale manifests before execution, and records accepted invocations in a Merkle-based transparency log. Evaluation across GPT-5.3, LLaMA-3.5, and DeepSeek-V3 using up to 50,000 manifest instances shows near-linear scalability (R^2 = 0.998), bounded verification latency (<= 9.4 ms on edge devices), and rejection of expired, malformed, replayed, and policy-violating manifests, with rejection rates above 98.7%. Experiments in healthcare, finance, RAG, and multi-agent settings show that manifest-level cryptographic enforcement enables low-overhead, traceable, and auditable execution control for heterogeneous LLM-tool pipelines.

Saeid Jamshidi, Kawser Wazed Nafi, Arghavan Moradi Dakhel +2

SWAT Laboratory, Polytechnique Montr´eal, Montr´eal, Canada · SæT Laboratory, Polytechnique Montr´eal, Montr´eal, Canada

LLM Auditing MCP Security LLM Security