What Do You Build With a Brand-New MCP? We Built a "Launch War Room"
ToolJet was the first internal tool builder to go AI-native, but ToolJet MCP takes that idea...
#MCP
3108 articles tagged with MCP
How to Plug Claude Routines Into Your SaaS With MCP
We shipped an MCP server so Claude routines can shorten links, pull stats, and manage Jo4 accounts. Turns out it's mostly OAuth — here's the recipe that worked.
rokbenko/quackd: 🦆🧠 Give your Microduck a brain. Tell a small robot with two legs what you want in plain language. An LLM (Claude, OpenAI, Gemini, Grok, or a local model via Ollama, vLLM or llama.cpp) uses the skills it already has to do it. Includes a simulator, .duck task files, MCP and a flock mode where multiple simulated ducks cooperate. Apache 2.0 license.
🦆🧠 Give your Microduck a brain. Tell a small robot with two legs what you want in plain language. An LLM (Claude, OpenAI, Gemini, Grok, or a local model via Ollama, vLLM or llama.c...
Best Enterprise MCP Gateway for Security & Governance in 2026: A Practical Guide to Securing AI Agent Tool Access
MCP is changing how AI applications interact with the systems around them. An AI agent can now do...
An MCP Server Is Not Interoperable Just Because It Connects
An MCP handshake proves that two endpoints can start a session. It does not prove that an Agent can...
いくら艦長とはいえ、MCPについてはただ見守るしかないかもしれませんMBSDとChillStack、AIエージェントのセキュリティ技術を学べるハンズオントレーニングを提供 https://cloud.watch.impress.co.jp/...
いくら艦長とはいえ、MCPについてはただ見守るしかないかもしれませんMBSDとChillStack、AIエージェントのセキュリティ技術を学べるハンズオントレーニングを提供 https://cloud.watch.impress.co.jp/docs/news/2136095.html#Apple #LLM #news #bot
MCP-инструменты научились возвращать интерфейс: разбираем OpenSearch MCP AppsОбычный MCP-инструмент возвращает агенту те...
MCP-инструменты научились возвращать интерфейс: разбираем OpenSearch MCP AppsОбычный MCP-инструмент возвращает агенту текст или структурированные данные. Агент анализирует результа...
From the .NET blog...In case you missed it earlier...How Uno Platform uses .NET, MCP, and AI to build high quality appsh...
From the .NET blog...In case you missed it earlier...How Uno Platform uses .NET, MCP, and AI to build high quality appshttps://devblogs.microsoft.com/dotnet/how-uno-platform-uses-d...
I gave my data-file tool an MCP server — so an AI assistant can explore your CSVs and hand you an offline HTML report
For the last few weeks I've been building dataloupe, a small tool that turns a data file (CSV, TSV,...
via @dotnet : How Uno Platform uses .NET, MCP, and AI to build high quality appshttps://ift.tt/Dmwyc9i#UnoPlatform #MCP ...
via @dotnet : How Uno Platform uses .NET, MCP, and AI to build high quality appshttps://ift.tt/Dmwyc9i#UnoPlatform #MCP #AI #dotnet #NET #AIinIDE #crossplatform #CSharp #Roslyn #Pl...
How Uno Platform uses .NET, MCP, and AI to build high quality appshttps://devblogs.microsoft.com/dotnet/how-uno-platform...
How Uno Platform uses .NET, MCP, and AI to build high quality appshttps://devblogs.microsoft.com/dotnet/how-uno-platform-uses-dotnet-mcp-ai-to-build-high-quality-apps/#microsoft #N...
From the .NET blog...How Uno Platform uses .NET, MCP, and AI to build high quality appshttps://devblogs.microsoft.com/do...
From the .NET blog...How Uno Platform uses .NET, MCP, and AI to build high quality appshttps://devblogs.microsoft.com/dotnet/how-uno-platform-uses-dotnet-mcp-ai-to-build-high-quali...
I Made an MCP Server Stop Calling Any AI API, and It Got More Useful
brainstorm-mcp runs multi-model debates. Hosted mode flipped who calls the model APIs, and the server stopped calling any of them. Design notes, two bugs from release day, and what...
Back in July I wrote about what it takes to wire an AI agent into social platforms: six OAuth flows,...#ai #api #mcp #we...
Back in July I wrote about what it takes to wire an AI agent into social platforms: six OAuth flows,...#ai #api #mcp #webdev #software #coding #development #engineering #inclusive ...
JordyZomer/lemmalog: A Datalog engine for LLM agent memory: stratified rules, provenance-tracked facts, incremental derivation, and an MCP server that lets your harness use it as a shared brain.
A Datalog engine for LLM agent memory: stratified rules, provenance-tracked facts, incremental derivation, and an MCP server that lets your harness use it as a shared brain.
A Practical Pattern for Giving AI Agents Access to External APIs with MCP
Connecting an AI agent to one API is straightforward. Connecting it to many changing APIs—without...
My portfolio IS the product. MCP at mcp.djaouad.tech — connect your AI and it can brief, scope, hire me. LangGraph + Nex...
My portfolio IS the product. MCP at mcp.djaouad.tech — connect your AI and it can brief, scope, hire me. LangGraph + Next.js. #MCP #AI #BuildInPublic
MCP Describe Injection: Audit Tool Descriptions Like Code
Tool poisoning hides malicious instructions in MCP tool descriptions before any code runs. Practical guide to the MCPTox data, the spec boundary, and a no-vendor hardening checklis...
I scanned 50,000 MCP server manifests: 543 violate the registry's own schema (here's the data)
A data-backed audit of the official MCP registry — four verified defect classes, zero false positives, and a cross-validation of the community fix PR.
Shadowfetch Linux 3.0 “Umbra” introduces the Fireline safety system for coding agents, with sandboxing, checkpoints, MCP...
Shadowfetch Linux 3.0 “Umbra” introduces the Fireline safety system for coding agents, with sandboxing, checkpoints, MCP tools, and local AI features.https://linuxiac.com/shadowfet...
Built this with my teammate for DataHub's "Build with DataHub: The Agent Hackathon." The hackathon...#ai #agents #mcp #s...
Built this with my teammate for DataHub's "Build with DataHub: The Agent Hackathon." The hackathon...#ai #agents #mcp #software #coding #development #engineering #inclusive #commun...
Stop manual dice rolling: Giving LLMs a proper tabletop math engine via MCP
Why prompting an LLM for RPG math is a recipe for failure, and how MCP tools solve core gameplay mechanics like advantage/disadvantage and damage resistance.
Why prompting an LLM for RPG math is a recipe for failure, and how MCP tools solve core gameplay mechanics like advantag...
Why prompting an LLM for RPG math is a recipe for failure, and how MCP tools solve core gameplay mechanics like advantage/disadvantage and damage resistance.#ai #mcp #programming #...
Here are two numbers that should ruin your morning coffee: 71,929 tokens versus 123 tokens. Same 255...#agents #llm #mcp...
Here are two numbers that should ruin your morning coffee: 71,929 tokens versus 123 tokens. Same 255...#agents #llm #mcp #performance #software #coding #development #engineering #i...