Mcp

MCP was always a bad idea?

hackernews · 원본 ID 49779329

Measure contraction property on isometric leaves and monotone fibres

For finite measures with positive densities on convex Euclidean supports, we prove that $MCP(κ,N)$ passes with unchanged parameters to almost every isometric leaf of an arbitrary nonexpansive map. The proof rests on a sharp contraction inequality for geometric conditional densities, with exponent equal to the leaf codimension. The inherited dimension parameter is optimal. A total-variation limit on resolvent graphs extends the result to inverse fibres of maximal monotone relations, including convex gradient fibres...

arxiv · 원본 ID http://arxiv.org/abs/2609.21510v1

Oracle high-dimensional $M$-estimation using smooth reparameterization for sparsity

This paper establishes a unified non-linear regularization framework for high-dimensional $M$-estimation, encompassing both linear models and Cox's proportional hazards models. Rather than relying on traditional additive non-convex penalties which pose severe optimization challenges, the proposed paradigm embeds sparsity directly into the transformation for the physical parameter $θ=φ^{(ν)}(β)$ using a smooth ($C^2$) component-wise "ReParametrization map for Sparsity (RePS)" $φ^{(ν)}$, and the penalty term is $λ\V...

arxiv · 원본 ID http://arxiv.org/abs/2609.19558v1

Closed-World Resolution Against Tool Hallucination in LLM Agents

Tool-augmented large language model (LLM) agents fail in a way no tool-selection or tool-security method addresses: they call tools that do not exist and pass arguments no schema declares. Existing defenses either pick the right tool (selection) or constrain what an agent may do with real tools (gating), both of which presuppose the emitted call refers to a real tool at all. We show this is a structural blind spot: a hallucinated call is by construction not a decision any gate made, so no gate can reject it. This...

arxiv · 원본 ID http://arxiv.org/abs/2609.19425v1

Characterizing Network Centralization and Observability in the Remote MCP Ecosystem

The Model Context Protocol (MCP) has emerged as the dominant interface for connecting autonomous agents to external data sources and execution environments. The ecosystem's transition from local process execution to remote Streamable HTTP deployments introduces unmeasured architectural and security constraints at scale. This paper presents a three-tier observability framework comprising catalog metadata (O_0), passive compliance signals (O_1), and live vulnerability analysis (O_2), applied to empirically character...

arxiv · 원본 ID http://arxiv.org/abs/2609.19100v1

When Agents Look Like Beacons: NIDS Evasion by Model Context Protocol Traffic

The Model Context Protocol (MCP) standardizes communication between autonomous Artificial Intelligence (AI) agents and remote tools over Streamable HTTP. This shift introduces a class of machine-generated, authenticated, and high-frequency JSON-RPC traffic directly into enterprise networks. Enterprise network defenders have historically relied on machine-like cadence as an Indicator of Compromise (IoC). In this study, we show that without explicit network-layer indication, MCP traffic structurally and temporally r...

arxiv · 원본 ID http://arxiv.org/abs/2609.19091v1

Position: It is Time to Virtualize Foundation Models with a Self-evolving Operating System Layer

AI applications have shifted from single, monolithic foundation models (FM) to compound agentic systems. Yet today's stacks remain fragmented: even as protocols (e.g., MCP, A2A) ease tool/agent connectivity, each framework embeds an implicit runtime for state, memory, budgets, and guardrails, making behavior non-portable and governance brittle. It mirrors computing before operating systems, when every program re-implemented basic services. This position paper argues that the field now needs a Foundation Model Oper...

arxiv · 원본 ID http://arxiv.org/abs/2609.19203v1

Measuring and Exploiting Implicit Trust in LLM Tool-Calling Pipelines

The Model Context Protocol (MCP) enables LLMs to invoke external tools, but every tool interaction exposes the model to attacker-controlled text through multiple input channels (tool descriptions, tool results, sampling messages) that share a single context window without privilege separation. In this paper, we present a framework to measure the trust profile of an arbitrary LLM based on a variety of payload framings sent through different channels. Following this assessment, we devise cross-channel fragmentation...

arxiv · 원본 ID http://arxiv.org/abs/2609.18217v1

PentestChain: A Cost-Aware, MCP-Orchestrated Framework for Automated Penetration Testing with Free-Tier LLMs

AI-driven penetration testing has been demonstrated with premium frontier models such as GPT-4, but the per-engagement token cost makes continuous, automated testing unaffordable for the smaller organisations that need it most. This paper presents PentestChain, a ten-phase automated penetration testing framework that couples a curated, deterministic exploit map with a cost-aware AI cascade-a local Ollama model (qwen2.5-7b) first, then free-tier OpenRouter and Cerebras, with a rule-based fallback that always produc...

arxiv · 원본 ID http://arxiv.org/abs/2609.18120v2

TuiML: Machine Learning for AI Agents

Machine-learning libraries such as Weka and scikit-learn were designed for human programmers. Language-model agents now use these same libraries by recalling APIs from memory and writing code, an approach that hides what a library offers, delays errors until runtime, and loses experimental state between turns. We present TuiML, a self-contained machine-learning library built for AI agents, with native algorithms across supervised, unsupervised, time-series, data handling, tuning, and evaluation tasks. Every compon...

arxiv · 원본 ID http://arxiv.org/abs/2609.17984v1

A reanalysis of the megamaser Hubble constant: from spot catalogues to peculiar velocities

The Hubble tension motivates careful scrutiny of the redshift-independent distances underpinning the local distance ladder. Water megamasers afford a purely geometric distance from orbital dynamics in an accretion disc. For five of the six Megamaser Cosmology Project (MCP) galaxies, we present a Bayesian forward model that infers the angular-diameter distance and warped Keplerian disc parameters jointly from the very long baseline interferometry quasi-observables: maser spot positions, velocities, and acceleration...

arxiv · 원본 ID http://arxiv.org/abs/2609.17684v1

Graphify-Labs/graphify

Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.

github · 원본 ID 1200597263