mcp.json
PulseAugur coverage of mcp.json — every cluster mentioning mcp.json across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
Anthropic's Claude Code detailed for developers and GTM engineers
Anthropic's Claude Code, an agent designed for terminal use, is being detailed for developers and go-to-market engineers. Resources include a security checklist for AI-assisted development and a guide for setting up Cla…
-
Hidden Unicode characters in agent skills pose security risks
A security vulnerability has been identified in agent skills, where malicious instructions can be hidden using invisible Unicode characters that models can still interpret. A scanner developed by the author, agent-skill…
-
Few AI tools implement basic agent-readability measures despite claims · 10 sources tracked
A recent analysis of 166 AI tools revealed that while many claim to be agent-friendly, few have implemented basic measures for AI agent readability. Only 39% of the tools publish an `llms.txt` file, 10% declare an AI cr…
-
AI tools' agent-friendly claims often superficial, analysis finds · 2 sources tracked
A recent analysis of 163 AI tools claiming to be agent-friendly revealed that a significant portion only implemented the most basic measures for accessibility. Specifically, 37% published an `llms.txt` file, 10% include…
-
New tool grades AI coding agent security settings
A new, free browser-based tool has been released that analyzes AI coding agent configuration files, specifically `settings.json` and `.mcp.json`. The tool identifies security vulnerabilities such as blanket shell allowa…
-
Developer maps mcp.json misconfigurations to OWASP MCP Top 10
A developer has created a mapping of common misconfigurations found in MCP server manifests (mcp.json) to the OWASP MCP Top 10 security categories. This mapping, which includes categories from the OWASP LLM Top 10, is i…
-
MCP configuration flaw creates backdoor for untrusted code execution
A security vulnerability has been identified in the MCP (Model Communication Protocol) configuration, where a `.mcp.json` file can act as a backdoor, allowing untrusted code execution. This configuration file, often ove…
-
Only 5% of AI Tools Expose Agent-Friendly mcp.json Standard
A recent analysis revealed that a mere 5% of 163 evaluated AI tools properly expose an mcp.json file, a standard for agent-friendly applications. The majority of these tools only provide an llms.txt file, falling short …
-
Troubleshooting Claude Code MCP Server Configuration Issues
This article details troubleshooting steps for users experiencing issues with their MCP (Multi-Cloud Platform) server configurations not being recognized by Claude Code. It clarifies that the 'Added' status from `claude…
-
Qwen Code 0.21.11 adds Agent Plugins v1 support, with caveats
Qwen Code version 0.21.11 introduces native support for Agent Plugins v1, allowing users to install and link these packages without needing to convert their manifest files. However, not all components of an Agent Plugin…
-
Few AI tools properly expose agent-friendly capabilities
A recent analysis of 162 AI tools found that a significant majority do not properly expose their manifest capabilities, a crucial component for agent-friendly interactions. Only 5% of these tools provided a complete mcp…
-
AI tools claim agent-friendliness, but few implement basic readability measures · 10 sources tracked
A study examining 163 AI tools found that while many claim to be agent-friendly, few implement basic measures for AI agent readability. Only 37% publish an llms.txt file, 10% declare an AI crawler policy, and a mere 5% …
-
MCP Setup Guide for Antigravity and Claude Code
This item details how to set up MCP (Meta-Command Protocol) for two tools: Antigravity and Claude Code. It provides specific configuration file examples, `mcp_config.json` for Antigravity and `.mcp.json` for Claude Code…