Tootfinder

This is just one example. "MCP" the protocol for "AI agents" is basically without security measures. It's like running random code on your infrastructure and data.
(Original title: GitHub MCP Exploited: Accessing private repositories via MCP)
https://simonwillison.net…

GitHub MCP Exploited: Accessing private repositories via MCP.
#ai

GitHub MCP Exploited: Accessing private repositories via MCP
We showcase a critical vulnerability with the official GitHub MCP server, allowing attackers to access private repository data. The vulnerability is among the first discovered by Invariant's security analyzer for detecting toxic agent flows.

Man könnte ja denken das diese ganze Agent/MCP Geschichte grad doch sehr fast and loose abläuft ....
https://simonwillison.net/2025/May/26/github-mcp-exploited/

MCP is the coming of Web 2.0 2.0
"Developers, coders, nerds, even regular users — we have power. We can demand that the platforms we use give us access to control our experiences using code."
https://anildash.com/2025/05/20/mcp-web20-20/

Remember when XML-RPC got cool so everyone rushed to haphazardly attach endpoints to their stuff? And then how also everyone found that maybe they should have rushed less to a more complete solution that actually took care of things like… security?
Ok, now: MCP.

It's not just the MCP stuff (that one is extremely badly built though) but so many other pieces of that stack and the models.
"AI" as an "industry" has basically no regard for engineering. Which is why all the talk about "safety" is utter nonsense.
https://tldr.nettim…

Salesforce launches Agentforce 3 with an observability tool called Command Center and MCP support, and says 8,000 customers have signed up to deploy Agentforce (Larry Dignan/Constellation Research)
https://www.constellationr.com/blog-news/i

Salesforce launches Agentforce 3, Command Center for visibility
Salesforce launched Agentforce 3, which features Agentforce Command Center, support for Model Context Protocol (MCP), and updated Atlas architecture to speed up reasoning and performance. The rollout maintains Salesforce's Agentforce cadence, which includes updates every few months as the company learns from enterprise use cases. In addition, Salesforce has added more than 30 partners to AgentExchange including AWS, Box, Cisco, Google Cloud, IBM and payments players such as PayPal and Stripe.

Do we know if Anthropic named their (technically garbage) "Agentic AI" protocol MCP in refence to the antagonist of the TRON movie?

LLMs the Model Context Protocol (MCP) are the Yang to the Semantic Web Project's Yin.
We now have a solution to the final hurdle—visualization.
Years of Linked Data work now come alive. I explain this, with demonstrations, in a new newsletter post.
www.linkedin.com/pulse/semant...
#MCP

A Critical Look at #MCP
https://raz.sh/blog/2025-05-02_a_critical_look_at_mcp

»Over 100,000 WordPress Sites Exposed to Privilege Escalation via MCP AI Engine:
The Wordfence Threat Intelligence team identified a severe security flaw in the AI Engine plugin, a widely used tool installed on over 100,000 WordPress websites.«
This is not surprising, especially since WordPress is very popular. However, the fact that it affects this scope should generally draw our attention to it on the web.
😬

Over 100,000 WordPress Sites Exposed to Privilege Escalation via MCP AI Engine
The Wordfence Threat Intelligence team identified a severe security flaw in the AI Engine plugin, a widely used tool installed.

Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers
Mohammed Mehedi Hasan, Hao Li, Emad Fallahzadeh, Bram Adams, Ahmed E. Hassan
https://arxiv.org/abs/2506.13538

Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers
Although Foundation Models (FMs), such as GPT-4, are increasingly used in domains like finance and software engineering, reliance on textual interfaces limits these models' real-world interaction. To address this, FM providers introduced tool calling-triggering a proliferation of frameworks with distinct tool interfaces. In late 2024, Anthropic introduced the Model Context Protocol (MCP) to standardize this tool ecosystem, which has become the de facto standard with over eight million weekly SD…

My Godot MCP server is now self-contained, and includes the pending additions that were contributed to the original Godot MCP.
https://github.com/xibbon/GodotSwiftMcp
This is what I am baking directly into Xogot, so I will be maintaining this server.

GitHub - xibbon/GodotSwiftMcp: Godot MCP server written in Swift
Godot MCP server written in Swift. Contribute to xibbon/GodotSwiftMcp development by creating an account on GitHub.

So there's a thing in AI called MCP
As far as I can tell, it's literally absolutely no different from an API, except this way it can have the same initials as the main villain in Tron.
#ai #technology

GitHub #MCP #Exploited: Accessing private repositories via MCP
https://invariantlabs.ai/blog/mcp-gith

AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes
Jiahao Qiu, Xinzhe Juan, Yimin Wang, Ling Yang, Xuan Qi, Tongcheng Zhang, Jiacheng Guo, Yifu Lu, Zixin Yao, Hongru Wang, Shilong Liu, Xun Jiang, Liu Leqi, Mengdi Wang
https://arxiv.org/abs/2506.14728

AgentDistill: Training-Free Agent Distillation with Generalizable MCP Boxes
While knowledge distillation has become a mature field for compressing large language models (LLMs) into smaller ones by aligning their outputs or internal representations, the distillation of LLM-based agents, which involve planning, memory, and tool use, remains relatively underexplored. Existing agent distillation methods typically replay full teacher trajectories or imitate step-by-step teacher tool usage, but they often struggle to train student agents to dynamically plan and act in novel …

STEP 1: install #windows but your

Study on the impact of radioactive background on Dark Count Rate of 20-inch MCP-PMTs
Zeyuan Feng, Zhaoyuan Peng, Haojie Dong, Yanfeng Li, Songyi Li, Xinzhou Guo, Wan Xie, Zhonghua Qin, Weiping Liu
https://arxiv.org/abs/2506.12470

Study on the impact of radioactive background on Dark Count Rate of 20-inch MCP-PMTs
This study systematically investigates the impact of natural radioactive background on the dark count rate (DCR) of 20-inch microchannel plate photomultiplier tubes (MCP-PMTs). Variations in PMT DCR under different radiation conditions were examined via underground tests, lead shielding experiments, and irradiation with \(^{55}\mathrm{Fe}\), \(^{60}\mathrm{Co}\), and \(^{90}\mathrm{Sr}\) sources. The experimental results indicate that natural radioactivity from surrounding air and rock in the u…

Figma releases Dev Mode Model Context Protocol server, which provides more context about how AI designs are created in Figma (Jess Weatherbed/The Verge)
https://www.theverge.com/news/679439/figma-dev-mode-mcp-server-beta-release

Figma will let your AI access its design servers
Figma is launching a Dev Mode MCP Server that can help AI models more effectively translate designs into fully coded applications.

This https://arxiv.org/abs/2506.02040 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csCR_…

Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol Ecosystem
The Model Context Protocol (MCP) is an emerging standard designed to enable seamless interaction between Large Language Model (LLM) applications and external tools or resources. Within a short period, thousands of MCP services have already been developed and deployed. However, the client-server integration architecture inherent in MCP may expand the attack surface against LLM Agent systems, introducing new vulnerabilities that allow attackers to exploit by designing malicious MCP servers. In th…

Agentic Semantic Control for Autonomous Wireless Space Networks: Extending Space-O-RAN with MCP-Driven Distributed Intelligence
Eduardo Baena, Paolo Testolina, Michele Polese, Sergi Aliaga, Andrew Benincasa, Dimitrios Koutsonikolas, Josep Jornet, Tommaso Melodia
https://arxiv.org/abs/2506.10925

Agentic Semantic Control for Autonomous Wireless Space Networks: Extending Space-O-RAN with MCP-Driven Distributed Intelligence
Lunar surface operations impose stringent requirements on wireless communication systems, including autonomy, robustness to disruption, and the ability to adapt to environmental and mission-driven context. While Space-O-RAN provides a distributed orchestration model aligned with 3GPP standards, its decision logic is limited to static policies and lacks semantic integration. We propose a novel extension incorporating a semantic agentic layer enabled by the Model Context Protocol (MCP) and Agent-…

The Model Context Protocol acts as a universal translator between LLMs and data sources, eliminating complex platform-specific requirements. Our new open source MCP server for ODBC (mcp-odbc-server) enables seamless integration of any ODBC-accessible data into RAG pipelines.
Read more in my latest newsletter!

What's The Model Context Protocol & Why Is It Important?
The way Large Language Models (LLMs) interact with the vast world of data sources and APIs (Application Programming Interface) is undergoing a significant transformation, thanks to the emergence of the Model Context Protocol (MCP). MCP servers act as a crucial middleware layer, a kind of "universal

ChatGPT bekommt auf Wunsch Zugriff auf Dropbox, Google Drive und Co.
OpenAI kündigt neue Workplace-Produkte an: Konnektoren und einen Aufnahme-Modus für Meetings und Brainstorming.
https://www.…

I actually found something useful in #jetbrains #MCP server/plugin 😏
We all know the "warnings" in #phpstorm (for example) - so let

Azure cost reduction/optimization for hosted applications using Artificial Intelligence. And it's REPEATABLE. Interested? Read on...
✅ Daniel Meppiel's Project Post
https://www.linkedin.com/posts/danielmeppiel_enterpriseai-ai-…

💥 What if AI could shrink your cloud bill by 80% in the time it takes to drink your coffee? | Daniel Meppiel
💥 What if AI could shrink your cloud bill by 80% in the time it takes to drink your coffee? 💥 I recently got it to happen—firsthand. What started as a quick experiment turned into something game-changing. Using VSCode's reusable prompts and the Azure MCP server, GitHub Copilot identified key optimizations for my app's infra in a predictable manner. Then, the Coding Agent implemented them. 📉 The result? An 80% smaller cloud bill. Just like that. In this 2-minute demo (linked below …

It seems to me that MCP is a modern, cross-platform corollary to the Mac ecosystem’s AppleScript dictionaries. It's a great standard for discovering API endpoints and calling them in a standard way. (And as a bonus, it doesn't involve keeping track of four-byte codes.)
Because it's associated with the AI buzz, lots of developers are integrating it. But it's not limited to and doesn't have to be used with AI; there's a great opportunity to make it easy for humans…

Survey of LLM Agent Communication with MCP: A Software Design Pattern Centric Review
Anjana Sarkar, Soumyendu Sarkar
https://arxiv.org/abs/2506.05364 https…

Survey of LLM Agent Communication with MCP: A Software Design Pattern Centric Review
This survey investigates how classical software design patterns can enhance the reliability and scalability of communication in Large Language Model (LLM)-driven agentic AI systems, focusing particularly on the Model Context Protocol (MCP). It examines the foundational architectures of LLM-based agents and their evolution from isolated operation to sophisticated, multi-agent collaboration, addressing key communication hurdles that arise in this transition. The study revisits well-established pa…

Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol Ecosystem
Hao Song, Yiming Shen, Wenxuan Luo, Leixin Guo, Ting Chen, Jiashui Wang, Beibei Li, Xiaosong Zhang, Jiachi Chen
https://arxiv.org/abs/2506.02040

Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol Ecosystem
The Model Context Protocol (MCP) is an emerging standard designed to enable seamless interaction between Large Language Model (LLM) applications and external tools or resources. Within a short period, thousands of MCP services have already been developed and deployed. However, the client-server integration architecture inherent in MCP may expand the attack surface against LLM Agent systems, introducing new vulnerabilities that allow attackers to exploit by designing malicious MCP servers. In th…

A Study on the MCP x A2A Framework for Enhancing Interoperability of LLM-based Autonomous Agents
Cheonsu Jeong
https://arxiv.org/abs/2506.01804 https://

A Study on the MCP x A2A Framework for Enhancing Interoperability of LLM-based Autonomous Agents
This paper provides an in-depth technical analysis and implementation methodology of the open-source Agent-to-Agent (A2A) protocol developed by Google and the Model Context Protocol (MCP) introduced by Anthropic. While the evolution of LLM-based autonomous agents is rapidly accelerating, efficient interactions among these agents and their integration with external systems remain significant challenges. In modern AI systems, collaboration between autonomous agents and integration with external t…

#MCP Claude Code = 💥
#MCP Claude Code Aider = 💥 💥 💥 💥 💥 💥
https://github.com/michabbb/aider-…

An example of what’s now possible—thanks to our (@…) sophisticated MCP Server for JDBC, Oracle’s native JDBC Driver, and Anthropic's Claude Desktop as the MCP client:
A dashboard generated from Oracle’s HR database using the following natural language prompt:
Using JDBC with the following connection details:
URL: jdbc:oracle:thin:@oracle-h…

I'm not sure how this affected me, but my PCP just told me it's ending via form letter.
Making Care Primary (MCP) Model | CMS
https://www.cms.gov/priorities/innovation/innovation-models/making-care-primary

Dark Count Rate Stability of JUNO 20-inch PMTs in Mass Testing
Min Li, Narongkiat Rodphai, Caimei Liu, Zhimin Wang, Zhaoyuan Peng, Jun Wang, Nikolay Anfimov, Denis Korablev, Tobias Lachenmaier, Alexander G. Olshevskiy, Zhonghua Qin, Tobias Sterr, Alexander Felix Tietzsch, Rong Zhao, Wei Wang, Kaile Wen, Bjoern Soenke Wonsak, Wan Xie, Meihang Xu, Yu Zhang

Dark Count Rate Stability of JUNO 20-inch PMTs in Mass Testing
The Jiangmen Underground Neutrino Observatory (JUNO) is an ambitious multipurpose neutrino experiment designed to determine the neutrino mass ordering, with an impressive energy resolution goal of at least 3% at 1 MeV. To achieve a photon detection coverage of approximately 75%, JUNO will utilize two types of 20-inch photomultiplier tubes (PMTs): the large PMT (LPMT) and the microchannel plate PMT (MCP-PMT). A significant concern in high-precision neutrino measurements is the dark count rate (D…

OpenAI rolls out connectors for services like Dropbox and OneDrive for ChatGPT Team, Enterprise, and Edu users; MCP support is coming to Pro, Team, Enterprise (Ivan Mehta/TechCrunch)
https://techcrunch.com/2025/06/04/chat

ChatGPT introduces meeting recording and connectors for Google Drive, Box, and more | TechCrunch
OpenAI's ChatGPT is adding new features for business users, including integrations with different cloud services, meeting recording, and MCP connection

In Xogot, I first tried a sheet to display my MCP chat window, but popups from the app would conflict with it and auto dismiss.
A dedicated tab works, but when the UI switches tabs, it can get confusing
Started to implement a floating window instead

Don't miss today's Metacurity for the most critical infosec developments you should know, including
--Russian group Laundry Bear hacked Dutch police, targets Ukraine-allied nations
--Iranian pleads guilty to Robbinhood ransomware,
--Vietnam-tied UNC6032 uses prompt-to-video AI tools to lure malware victims,
--Russia sends former programmer to prison for 14 years,
--Czech Republic says China's APT31 hacked its comms networks,
--Nigeria arrests 20 for…

Russian group Laundry Bear hacked Dutch police, targets Ukraine-allied nations
Iranian pleads guilty to Robbinhood, UNC6032 uses prompt-to-video AI tools to lure victims, Russia sends former programmer to prison for 14 years, Czech Republic says China's APT31 hacked its comms networks, Nigeria arrests 20 for exams hacking, Bad flaw found in GitHub MCP integration, much more

Towards the Autonomous Optimization of Urban Logistics: Training Generative AI with Scientific Tools via Agentic Digital Twins and Model Context Protocol
Haowen Xu, Yulin Sun, Jose Tupayachi, Olufemi Omitaomu, Sisi Zlatanov, Xueping Li
https://arxiv.org/abs/2506.13068

Towards the Autonomous Optimization of Urban Logistics: Training Generative AI with Scientific Tools via Agentic Digital Twins and Model Context Protocol
Optimizing urban freight logistics is critical for developing sustainable, low-carbon cities. Traditional methods often rely on manual coordination of simulation tools, optimization solvers, and expert-driven workflows, limiting their efficiency and scalability. This paper presents an agentic system architecture that leverages the model context protocol (MCP) to orchestrate multi-agent collaboration among scientific tools for autonomous, simulation-informed optimization in urban logistics. The …

Beyond Formal Semantics for Capabilities and Skills: Model Context Protocol in Manufacturing
Luis Miguel Vieira da Silva, Aljosha K\"ocher, Felix Gehlhoff
https://arxiv.org/abs/2506.11180

Beyond Formal Semantics for Capabilities and Skills: Model Context Protocol in Manufacturing
Explicit modeling of capabilities and skills -- whether based on ontologies, Asset Administration Shells, or other technologies -- requires considerable manual effort and often results in representations that are not easily accessible to Large Language Models (LLMs). In this work-in-progress paper, we present an alternative approach based on the recently introduced Model Context Protocol (MCP). MCP allows systems to expose functionality through a standardized interface that is directly consumab…

The Model Context Protocol (MCP) brings Unix-style loose coupling to AI Agents.
I built a visual explainer (JSON-LD metadata included) using Google Gemini’s new Canvas feature—with an embedded Knowledge Graph to illustrate.
Check it out:
https://openlinksw.com//data/html/unix

\textit{QuantMCP}: Grounding Large Language Models in Verifiable Financial Reality
Yifan Zeng
https://arxiv.org/abs/2506.06622 https://

\textit{QuantMCP}: Grounding Large Language Models in Verifiable Financial Reality
Large Language Models (LLMs) hold immense promise for revolutionizing financial analysis and decision-making, yet their direct application is often hampered by issues of data hallucination and lack of access to real-time, verifiable financial information. This paper introduces QuantMCP, a novel framework designed to rigorously ground LLMs in financial reality. By leveraging the Model Context Protocol (MCP) for standardized and secure tool invocation, QuantMCP enables LLMs to accurately interfac…

This https://arxiv.org/abs/2506.01056 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csAI_…

MCP-Zero: Proactive Toolchain Construction for LLM Agents from Scratch
Function-calling has enabled large language models (LLMs) to act as tool-using agents, but injecting thousands of tool schemas into the prompt is costly and error-prone. We introduce MCP-Zero, a proactive agent framework that lets the LLM itself decide when and which external tools to retrieve, thereby assembling a task-specific toolchain from scratch. The framework is built upon three components: (1) Proactive Tool Request, where the model emits a structured $\left<\operatorname{tool\_assistan…

Ok, first day trying my end-to-end Xogot/Claude/MCP integration, not bad at all:

A simple GUI-based screencast demo of the @… AI Layer (OPAL), showing what’s now possible via MCP A2A—namely, composing and orchestrating agentic workflows through loosely coupled software.
How?
An Agent Host routes tasks to Agents via A2A. Agents then invoke MCP-accessible tools (functions, procedures, APIs) described using JSON/YAML and exposed …

This week’s edition of my @… newsletter shines a light on the impact of the Model Context Protocol (MCP) across multiple computing eras—leading right up to today.
We’ve arrived at a moment where loose coupling principles are cool (and super useful) again.
Naturally, there are some live demo nuggets in the post to help bring it all to life:
🔗

The Model Context Protocol: Bridging Generational Computing Experiences
The Model Context Protocol (MCP) is emerging as a transformative force in computing, with its significance uniquely appreciated across generational lines. This new protocol serves as crucial middleware for LLM-powered productivity tools, addressing needs that previous computing paradigms couldn't fu

Which #MCP package do you prefer?? 🤔
#ai #coding #php

🔧 Now available across all platforms: #API, #MCP, and integrations like #Zapier and #n8n
📚 Complete…