68 stories tagged mcp, newest first.
195 points by vardhan1237 | 72 comments
GitHub repository for PaperPilot, a local, zero-cloud pure-Rust PDF engine and AI document copilot with WASM builds and an MCP server.
3 points by mariuscarlsson | 0 comments
GitHub repository for JUKEBOX-OS, a Rust and Python runtime offering deterministic replay, a copy-on-write ACID tool sandbox, and time-travel debugging for multi-agent systems.
59 points by lumbroso | 32 comments
Landing page for ADRs4AI, a Git-versioned framework, template, VS Code extension, and iOS app for recording human–AI design deliberations as decision records.
3 points by ankitg12 | 0 comments
Landing page for CowAgent, an open-source self-hosted AI assistant and agent harness supporting multiple LLMs, chat channels, memory, skills, and multi-agent teams.
4 points by botacode | 0 comments
GitHub repository for CATT, an MIT-licensed tool for testing MCP servers, APIs and apps against surrogate Muse/Instinct-like consumer agents locally or in CI.
45 points by Andydy25 | 21 comments
Launch HN post introducing Respan, an open-source Rust AI/LLM gateway with a small core where providers, protocols, and features are plugins.
7 points by jvonb | 1 comments
GitHub repository for an SDK that provides an in-memory privacy shield to keep sensitive context from leaking through MCP tool calls.
110 points by scottfalconer | 116 comments
Dries Buytaert's blog post recapping his DrupalCon Rotterdam 2026 keynote on Drupal CMS, Canvas Headless, Drupal AI, the Tool module, and a new Advocacy Program.
15 points by zoozla | 2 comments
GitHub repository for YaraReads, an open-source early-reader app where kids tap words to hear phonemes, with MCP support for importing books via AI assistants.
139 points by zoozla | 70 comments
GitHub repository for a read-only MCP server that lets an AI agent search and read your personal WhatsApp messages, running on Cloudflare Workers.
15 points by contextetech | 9 comments
An article discussing whether the Model Context Protocol (MCP) is becoming a common foundation for smart, decentralised search.
30 points by invalidmonk | 18 comments
Landing page for ThingsToDo Events API, an API and MCP server providing localized event data (shows, pop-ups, markets, festivals) for agentic apps.
18 points by _wesley | 13 comments
Landing page for Stoke, a personal finance app that projects account cash flow from recurring transactions instead of using budgets.
81 points by panoramas4good | 16 comments
Signals Corps blog post analyzing HTTP headers from 217 million crawled web responses for text aimed at AI agents, including prompt injection attempts.
97 points by edpin2000 | 75 comments
Landing page for Clova.Email, an email service offering infinite inboxes that lock to a single sender, temporary inboxes, and prefix-based auto-created aliases.
37 points by KarLexAI | 11 comments
GitHub repository for Graphicle, a Rust program providing a code graph and memory for coding agents like Claude Code, Codex, Cursor and MCP clients.
51 points by ricotico060 | 56 comments
A personal project write-up about building a Garmin "MCP" to ask an AI questions about one's workout and health data.
111 points by bherbruck | 27 comments
GitHub repository for SolidCraft, an open-source parametric 3D CAD application written in Rust with desktop, web, and MCP-based automation support.
71 points by androsynth89 | 30 comments
GitHub repository for blokkily, an experimental pattern-first digital audio workstation with Model Context Protocol (MCP) support.
31 points by edris0077 | 7 comments
GitHub repository for Edi Life OS, a self-hosted PHP life dashboard for habits, goals, Kanban, finance and focus with an MCP server for AI assistants.
39 points by trollied | 9 comments
GitHub repository for treg, an open-source "OpenRouter for agent tools" that provides a registry, proxy, and credential management for AI agent tools.
138 points by Tomte | 60 comments
Armin Ronacher blog post explaining Codemode and why Pi 1.0 added MCP support through it, revisiting his earlier argument that agents should use code over tools.
5 points by FredEdison | 0 comments
GitHub repository for GlyphDNA MCP adapter, providing machine-native identity, verifiable meeting rooms, and script provenance for AI agents via MCP calls.
8 points by qwikhost | 1 comments
Product page for G Maps Crawl's MCP server that lets AI agents search Google Maps businesses and retrieve structured listing data via API key.
7 points by alexandroskyr | 0 comments
GitHub repository for pi-codex-connectors, an extension that lets any Pi model or MCP harness use Codex (ChatGPT) connectors and plugins.
36 points by jv22222 | 5 comments
Landing page for Breadcrumb, a free local encrypted Mac app that records screen, meetings, and AI transcripts and exposes them as memory to AI tools via MCP.
158 points by thdr | 93 comments
X post thread where David Soria Parra asks Figma to fix its remote MCP server, which only accepts whitelisted client names like Claude Code and rejects Pi.
10 points by ajoski9 | 6 comments
Free trial page for Strata, a semantic layer and BI platform with dashboards and LLM/MCP access that runs locally via Docker.
641 points by yarapavan | 351 comments
Earendil Engineering post explaining why their Pi coding agent, previously opposed to MCP, now supports the Model Context Protocol.
32 points by topaztee | 8 comments
Vespper blog post launching its DOCX MCP, a fine-tuned model that lets AI agents edit Word documents via an HTML projection, claiming 3× speed and 2× lower cost.
54 points by avinashjetwani | 38 comments
GitHub repository for jevmem, an MIT-licensed tool providing automatic project memory for Claude Code, also working with Cursor and Codex.
5 points by snyy | 1 comments
Landing page for Critic, a code review platform where AI agents annotate their changes and reviewers can chat with the agent that wrote the code.
29 points by Loren_SL | 5 comments
Landing page for ForensicDbg, a post-mortem debugger for native Windows x64/x86 crash dumps with an MCP server, currently in private beta.
45 points by botacode | 28 comments
Homepage of Coverage Cat, a licensed insurance broker for comparing home and umbrella coverage, with an MCP/agent API for personal AI agents.
27 points by ZaharaHussain | 2 comments
Landing page for ai·rete·rag, a hosted product pairing a Rete rule engine for deterministic decisions with RAG-generated plain-language explanations.
674 points by bookofjoe | 178 comments
GitHub repository for Hister, an open-source Go personal search engine that indexes visited web pages and local files, licensed AGPL-3.0.
333 points by aquir | 169 comments
OpenAI developer documentation page introducing the Agents API, which provides managed access to the Codex harness for building durable cloud agents.
360 points by tosh | 204 comments
Simon Willison blog post on the stateless MCP 2.0 specification release and the mcp-explorer and datasette-mcp tools it inspired him to build.
357 points by Areibman | 206 comments
Bottleneck Labs blog post describing an experiment giving GPT 5.6 Sol a wallet, computer, iOS app, and debit card to run a business autonomously, which lost $447.
327 points by chenglong-hn | 118 comments
Project homepage for Flint, a Microsoft Research visualization intermediate language that lets AI agents generate charts rendered via Vega-Lite, ECharts, or Chart.js.
372 points by nadis | 351 comments
Quandri engineering blog post by backend engineer Chloe Kim titled "MCP is dead," arguing about the Model Context Protocol for AI agents.
374 points by arps18 | 228 comments
A long blog guide by Arpan Patel on using Claude Code as a daily driver, covering CLAUDE.md, skills, subagents, plugins, and MCP servers.
415 points by Bibabomas | 137 comments
GitHub repository for Semble, an open-source CPU-based code search tool and MCP server for AI coding agents combining static embeddings with BM25.
413 points by gmays | 335 comments
A blog post arguing that the Model Context Protocol (MCP) is preferable to agent skills for extending LLM tools.
383 points by jasonjmcghee | 229 comments
Claude Code documentation page explaining channels, a research-preview feature that lets MCP servers push messages, alerts, and webhooks into a running session.
563 points by xnx | 221 comments
Chrome for Developers blog post explaining how the Chrome DevTools MCP server lets coding agents connect to and debug a running browser session.
340 points by andsoitis | 185 comments
Chrome for Developers blog post announcing an early preview program for WebMCP, a way for websites to expose structured interactions to AI agents.
404 points by ejholmes | 257 comments
Blog post by Eric Holmes arguing that Anthropic's Model Context Protocol is dying and that LLM agents should use command-line tools instead.
524 points by mksglu | 100 comments
Blog post introducing Context Mode, an open-source MCP server that sits between Claude Code and tool outputs to cut context window consumption by about 98%.
398 points by hugs | 113 comments
GitHub repository for Vibium, an Apache-2.0 browser automation tool for AI agents and humans from Selenium's creator, using a Go binary with BiDi and MCP support.
642 points by weinzierl | 332 comments
Simon Willison's blog post about Anthropic's newly introduced Claude Skills, folders of instructions and scripts the model loads when needed, arguing they may matter more than MCP.
449 points by alvis | 363 comments
OpenAI developer documentation home for the Apps SDK, a preview framework for building apps that run inside ChatGPT using MCP servers.
495 points by meetpateltech | 270 comments
OpenAI platform documentation page for ChatGPT Developer Mode with full MCP client access; the capture shows an authentication error page.
370 points by Anon84 | 150 comments
Mistral AI product announcement that Le Chat now supports custom MCP connectors to 20+ enterprise platforms and a Memories feature.
406 points by vismit2000 | 109 comments
Simon Willison's annotated presentation of his Bay Area AI Security Meetup talk on prompt injection, the lethal trifecta, and securing MCP-based systems.
318 points by yodon | 165 comments
Medium essay by Julien Simon arguing that the Model Context Protocol ignores decades of RPC and distributed systems best practices, creating risks for enterprises.
798 points by rexpository | 433 comments
A General Analysis blog post describing how Supabase's MCP server can be exploited via prompt injection to leak an entire private SQL database.
729 points by Stwerner | 322 comments
A Substack essay by Scott Werner arguing that Anthropic's Model Context Protocol works as an accidental universal plugin system, using a USB-C analogy.
552 points by charleszyong | 214 comments
Launch HN post for Vassar Robotics' $219 desktop robot arm kit based on LeRobot SO-101, with cameras and an MCP server letting LLMs invoke learned skills.
573 points by ecz | 431 comments
Cursor's changelog entry for version 1.0, introducing BugBot code review, memories, one-click MCP install, Jupyter support, and general availability of Background Agent.
360 points by makeboss | 170 comments
GitHub repository for Microsandbox, a self-hosted platform for securely executing untrusted user or AI-generated code in lightweight virtual machines.
477 points by andy99 | 287 comments
Invariant Labs blog post describing a vulnerability in the official GitHub MCP server that lets attackers access private repository data via AI agent prompt injection.
556 points by ablekh | 304 comments
A blog post on Raz Blog critically examining the Model Context Protocol (MCP), covering its protocol and transport design.
678 points by bryanh | 240 comments
Anthropic announcement from May 1, 2025 that Claude can now connect to external apps and services through Integrations.
467 points by sshh12 | 201 comments
A Substack essay by Shrivu Shankar explaining the Model Context Protocol (MCP) and its problems, from security risks to limitations in LLM tool integration.
578 points by namukang | 205 comments
Landing page for Browser MCP, a Chrome extension and MCP server that lets AI apps like Cursor, Claude, and VS Code automate your browser.
668 points by skilldeliver | 165 comments
Medium article by Elena Cross arguing that the Model Context Protocol (MCP) for AI agents has significant security weaknesses.
337 points by tanelpoder | 64 comments
GitHub repository for GhidraMCP, a Model Context Protocol server that lets LLMs interact with the Ghidra reverse engineering tool.