MCP & Skills Standardization
41 records · 7 notes · records tagged with this as a related axis are included.
When everyone hooks up tools their own way, a standard eventually emerges
The more tools agents use, the more the way they connect becomes a problem. If every company plugs tools in with its own spec, every new tool means work multiplied by the number of models. This axis follows attempts to turn the rules between models and tools into open standards — protocol announcements, adoption by other companies, spec revisions. In this area, "who adopted it" matters more than the technology itself, so announcements and actual support are recorded separately.
A how-to that builds a research agent which runs on its own at a set time each week, using nothing but a scheduling feature. It likens building one to hiring a person and splits it into four stages — deciding what to ask
A hands-on run that attaches a reverse-engineering toolkit — one that takes a finished program apart and recovers its structure — to a coding agent. On a request the toolkit runs the specialist analyzers on your behalf a
As skill and plugin marketplaces grow, the supply chain becomes an attack surface. A structure that runs vetting through benchmarks from multiple participants rather than a single vendor follows the path package reposito
An approach that retrieves and adapts skills from repositories instead of learning them anew for each harness, turning skills from outputs tied to a model and harness into transferable assets. Read together with ClawScan
A design that treats agents not as personal assistants but as shared team assets. Bundling context, credentials and memory per bot means organizational knowledge builds up in the bot, but the bot in turn becomes a concen
A design proposal that points to the layer missing beneath agent frameworks. This week alone, the observation topic "agent security and sandboxing" reached the same conclusion from both industry (NVIDIA) and academia (th
The first mainstream release to name agents explicitly as "users" of robot software. The design that lets people and agents call skills through the same interface is the MCP and Skills standardization trend crossing into
This introductory walkthrough recasts an agent known as a coding tool as a general-purpose office-automation tool to hand document, spreadsheet and image work to, checking its features one at a time on real tasks. The ke
The stage of selling a separate "agent product" closed in less than a year. It reflects the judgment that agents are not a separate app but the default behavior of chat, and bringing deliverables (documents, slides) into
After the maker of a professional production tool officially released a command-line interface, an integration module and a skills repository holding domain knowledge, this sets out step by step the procedure for attachi
A hands-on record that follows a game engine's newly released command-line tool in one pass, from installation through MCP server setup and skill injection to generating an actual 2D game. What's worth taking away is not
The point at which the agent harness hardened from a product feature into a platform contract — loops, sandboxes and subagent delegation have become API primitives.
This hands-on walkthrough shows that if you install a plugin in a desktop 3D tool, start a bridge server and register its address under the coding agent's Settings → Customize → Connectors, someone who has never learned
Anthropic's /design skill is a feature aimed at the inefficiency of revising designs over and over through text conversation alone. The skill is designed to ask detailed questions step by step — for example, when no colo
An attempt to standardize the control of physical equipment, just as MCP standardized access to software tools. A boundary event that extends agents' reach into lab hardware, with the lead on the standard once again rest
With MCP and A2A unified under a single neutral foundation, the governance of agent standards is reorganized around a foundation
MCP is redesigned from the ground up, from a protocol of stateful sessions into a stateless, per-request one. The largest break in backward compatibility yet
Removes initialize and Mcp-Session-Id, introduces MRTR, adds server/discover, and promotes the Tasks and MCP Apps extensions
On-device AI frameworks shifted from a closed single model to a hybrid, multi-provider platform
A skill distribution standard was proposed as a vendor-led open spec, beyond a single project
A stable-channel case of an on-device model exposed as a web platform API rather than an app. Responsibility for model distribution and storage management passes to the browser vendor
AAIF reached 170 member companies in 4 months, MCP SDK monthly downloads passed 110 million, and security — including a DNS rebinding demo — was the biggest topic
A protocol that used to carry only text and structured data now extends to on-screen interfaces
Released a specification and a reference SDK; the second standardization attempt after MCP
The founding projects were MCP, goose and AGENTS.md, at a point when public MCP servers exceeded 10,000
Aligned the auth model with standard OAuth practice and moved spec governance to committee procedures
Cut tool tokens by 85% while MCP evaluation accuracy rose from 49% to 74% on Opus 4 — the paradox that showing fewer tools makes the model more accurate
Lets servers provide interactive UIs via the ui:// scheme and sandboxed iframes; co-authored by competing camps
Packages procedural knowledge as folders and loads it only when needed, in three stages: metadata, body, bundled files
A distribution unit that bundles slash commands, subagents, MCP servers and hooks into a single git repository
Responds with a dedicated, browser-specialized model; states explicitly that it is not yet optimized for desktop OS control
MCP goes beyond backend connections to become a distribution layer for consumer apps
A proposal to convert MCP tools into a TypeScript API and have the LLM write code; the gain is that intermediate results never pass through the context
Resolves the fragmentation of server discovery, with a structure of a central registry plus private subregistries
Safety figures for browser control published — attack success rate in autonomous mode cut from 23.6% to 11.2%, and for browser-specific attacks from 35.7% to 0%
Computer use repositioned as one tool rather than a standalone product
Vendor neutrality at the protocol layer; moved to a foundation half a year before MCP
Introduces a standard procedure for servers to ask the user for more input; adds a new security best practices section
Remote MCP became a standard feature of a commercial API
Adoption reached down to the OS level, and governance began to become multilateral
Showed that a malicious server can manipulate model behavior before any call, using only the descriptions in its tools/list response
Proposed a separate agent-to-agent layer and stated explicitly that it complements MCP
Introduced a transport that replaces HTTP+SSE and a standard authorization framework
A competitor accepting its rival's standard made it the de facto industry standard
The first official adoption by a large platform; the turning point from a single vendor's spec to an industry spec
A commercial agent specialized for the browser; OSWorld 38.1%, WebArena 58.1%
Replaced the combinatorial explosion of N models times M data sources with a single open standard
The first frontier model to operate GUIs through screenshots and coordinates, without dedicated APIs