A developer built rungraph, a free, MIT-licensed tool that turns session transcripts from coding agents like Claude Code, Codex CLI, and Hermes Agent into an interactive, queryable graph. The tool sca…
OWASP BLT's summer project has produced BLT-CLI, a Rust-based terminal interface, and BLT-MCP, a server connecting AI models with the BLT API. The CLI now supports browsing vulnerabilities, submitting…
An open-source MCP server that runs on Android and exposes tap, type, scroll, and screenshot actions to AI agents has been released on GitHub, with a FOSS build heading to F-Droid. The app, which regi…
AgentBadge, a platform for AI agents, has launched its MCP (Model Context Protocol) server, enabling agents to post, claim, deliver, and complete tasks with HBAR payments, with full lifecycle support …
Amazon, Cursor, Microsoft, OpenAI, and Vercel have launched Agent Plugins, an open, vendor-neutral standard for packaging reusable components into portable plugins for AI agents. Version 1.0.0 defines…
DeepBlue Dynamics released Hyperia v0.17.5, a terminal built for the agent era that combines an Electron front end with a Rust sidecar, exposing the entire terminal as an MCP server. The update transf…
The developer community has released an open-source shared memory graph for Claude and ChatGPT that runs over the Message-Centric Protocol (MCP). The lightweight in-memory structure stores conversatio…
A developer warns that a connected MCP server does not guarantee correct tool calls, emphasizing that MCP is an access protocol, not a competence protocol. The developer advises checking raw responses…
A developer argues that traditional APIs are insufficient for AI agents, which need to dynamically discover and interact with capabilities. The Model Context Protocol (MCP) offers a standardized way f…
Klo, a video editing app for Mac, released an MCP server that lets coding agents like Claude Code, Codex, or Cursor drive a full video editor—import, cut, caption, grade, and export—while footage stay…
Kozou, an open-source tool that exposes PostgreSQL context to AI agents, has extended its OAuth-based resource-server model to remote MCP connections in v1.13.0. The design deliberately avoids becomin…
N8n has published a guide to MCP server security, arguing that production deployments of LLM tool calls require a dedicated MCP control plane to govern agent actions, credentials, and audit trails. Th…
A developer's guide to extending Claude Code with MCP servers, subagents, and hooks details how to connect external services, manage scopes, and create custom subagents. The guide covers adding MCP se…
A developer testing MCP server tool calls in Rust found that combining 7 related functions into 1 function with a `command` argument is superior, as small models like LFM and Ling Tiny perform equally…
Notion has released Lore, an open-source tool under the MIT license, to provide shared, persistent memory for AI agents using Notion as the backing store. Lore stores experiential knowledge, follow-up…
A developer argues that storing long-lived API keys in an agent's .env file is a security risk and proposes replacing them with short-lived, action-scoped credentials obtained via OAuth flows such as …
A developer building AI assistants for financial data identified three critical problems and their fixes: raw LLMs cannot be trusted for facts, provenance must be enforced, and multiple surfaces must …
A developer built sentrymcp, a static and runtime security scanner for MCP servers, in Rust. The tool detects code vulnerabilities, tool poisoning, and missing authentication, and includes a runtime p…
Ampcode.com now supports connecting remote Model Context Protocol (MCP) servers via Streamable HTTP with OAuth or Bearer tokens, enabling use of MCP-provided tools in orbs, the TUI, and Puck. Personal…
Runbook.v1, a new application-layer contract for Model Context Protocol (MCP) hosts, enables governed, versioned, and auditable workflow execution with fail-closed semantics, ensuring that enterprise …