Development Approach

Agent Plugins vs Standalone MCP Servers (2026): Portable Packaging vs Per-Client Deployment

Agent Plugins 1.0.0 vs standalone MCP servers in 2026: a portable packaging spec backed by Vercel, AWS, Microsoft, OpenAI and Google compared with per-client packaging. Portability, governance, maturity and when each fits.

4
Agent Plugins
vs
4
Standalone MCP Servers
Quick Verdict

Adopt Agent Plugins for any extension that needs to travel across more than one compatible client. The spec is one day old, but the problem it solves is real and well-understood: repackaging the same MCP server for every client is the default failure mode of the agent-extension ecosystem, and the six launch clients plus Google's day-one products cover enough surface area that a plugin packaged today will reach the majority of the market without modification. Stay with direct per-client MCP deployment when you are shipping to a single client, when you need client-specific capabilities that the portable contract does not cover (commands, hooks, agents), or when the absence of a trust and permissions model in the spec is a disqualifier rather than a deferred item. The spec is deliberately honest about what it does not define — no install mechanism, no distribution protocol, no sandboxing, no trust verification — and for regulated or enterprise environments those gaps matter today, even if they close in future versions. The pattern Context Studios favours is a hybrid one: package the portable parts (Agent Skills, MCP server declarations) as an Agent Plugin, and keep client-specific behaviour in the namespaced extension directory. When the portable contract is too narrow, ship directly. When it is wide enough, ship once. The spec's scope discipline is its strongest feature — it standardises only what genuinely travels, and leaves the rest where it belongs.

Detailed Comparison

A side-by-side analysis of key factors to help you make the right choice.

Factor
Agent PluginsRecommended
Standalone MCP ServersWinner
Cross-client portability
One plugin directory with a plugin.json manifest, skills/ folder and mcp.json works across every compatible client — ChatGPT, Codex, Cursor, GitHub Copilot, Kiro and VS Code at launch — without repackaging.
Each client expects different top-level metadata, discovery paths and MCP configuration shapes, so the same MCP server must be repackaged for every target client.
Component independence and fault isolation
Skills and MCP servers are validated independently after the manifest is checked, so one invalid component does not disable unrelated ones in the same plugin.
A single misconfigured MCP server can break the entire extension load because there is no shared contract for independent component validation.
Client-specific optimisation
A namespaced extension directory (com.example.client/) lets each client add hooks, agents or commands without polluting the portable core, but the extension is invisible to other clients.
Direct deployment gives full control over how the MCP server is configured, discovered and presented for one specific client, with no abstraction layer in the way.
Discovery and loading contract
The spec defines fixed paths — plugin.json at root, skills/ for Agent Skills, mcp.json for MCP servers — giving client implementers a small, deterministic contract for discovery, validation and loading.
Discovery is whatever each client invents: different top-level metadata, different config shapes, different transport inference rules, so there is no single contract to implement against.
Distribution, trust and permissions
The spec deliberately defines no install mechanism, no distribution protocol, no permission model, no sandboxing requirements and no trust or provenance verification — all explicitly named as future considerations.
Each client implements its own installation, permission and trust model, so security properties differ per client but exist today rather than being deferred.
Governance and vendor neutrality
The Technical Steering Committee includes Core Maintainers from AWS, Cursor, Microsoft, OpenAI and Vercel, with Google joining at launch — no single company's product roadmap sets the format's direction.
Packaging conventions are set by each client vendor unilaterally, so the format's direction follows whichever client you deploy to first.
Implementation maturity and production track record
The specification shipped as version 1.0.0 on 6 August 2026 — one day old at the time of writing — with Google's Agents CLI and Data Agent Kit as the only shipping plugin examples beyond the launch clients' own support.
Direct MCP server deployment has a multi-year head start, a large body of production deployments, and mature tooling across every major AI client that already speaks MCP.
Scope discipline and extensibility
Version 1 focuses on two component types — Agent Skills and MCP servers — and explicitly defers commands, hooks and agents to clients until portability needs emerge and consensus forms.
Per-client packaging can include whatever the client supports — commands, hooks, agents, custom UI — with no need to wait for a multi-vendor consensus process.
Total Score4/ 84/ 80 ties
Cross-client portability
Agent Plugins
One plugin directory with a plugin.json manifest, skills/ folder and mcp.json works across every compatible client — ChatGPT, Codex, Cursor, GitHub Copilot, Kiro and VS Code at launch — without repackaging.
Standalone MCP Servers
Each client expects different top-level metadata, discovery paths and MCP configuration shapes, so the same MCP server must be repackaged for every target client.
Component independence and fault isolation
Agent Plugins
Skills and MCP servers are validated independently after the manifest is checked, so one invalid component does not disable unrelated ones in the same plugin.
Standalone MCP Servers
A single misconfigured MCP server can break the entire extension load because there is no shared contract for independent component validation.
Client-specific optimisation
Agent Plugins
A namespaced extension directory (com.example.client/) lets each client add hooks, agents or commands without polluting the portable core, but the extension is invisible to other clients.
Standalone MCP Servers
Direct deployment gives full control over how the MCP server is configured, discovered and presented for one specific client, with no abstraction layer in the way.
Discovery and loading contract
Agent Plugins
The spec defines fixed paths — plugin.json at root, skills/ for Agent Skills, mcp.json for MCP servers — giving client implementers a small, deterministic contract for discovery, validation and loading.
Standalone MCP Servers
Discovery is whatever each client invents: different top-level metadata, different config shapes, different transport inference rules, so there is no single contract to implement against.
Distribution, trust and permissions
Agent Plugins
The spec deliberately defines no install mechanism, no distribution protocol, no permission model, no sandboxing requirements and no trust or provenance verification — all explicitly named as future considerations.
Standalone MCP Servers
Each client implements its own installation, permission and trust model, so security properties differ per client but exist today rather than being deferred.
Governance and vendor neutrality
Agent Plugins
The Technical Steering Committee includes Core Maintainers from AWS, Cursor, Microsoft, OpenAI and Vercel, with Google joining at launch — no single company's product roadmap sets the format's direction.
Standalone MCP Servers
Packaging conventions are set by each client vendor unilaterally, so the format's direction follows whichever client you deploy to first.
Implementation maturity and production track record
Agent Plugins
The specification shipped as version 1.0.0 on 6 August 2026 — one day old at the time of writing — with Google's Agents CLI and Data Agent Kit as the only shipping plugin examples beyond the launch clients' own support.
Standalone MCP Servers
Direct MCP server deployment has a multi-year head start, a large body of production deployments, and mature tooling across every major AI client that already speaks MCP.
Scope discipline and extensibility
Agent Plugins
Version 1 focuses on two component types — Agent Skills and MCP servers — and explicitly defers commands, hooks and agents to clients until portability needs emerge and consensus forms.
Standalone MCP Servers
Per-client packaging can include whatever the client supports — commands, hooks, agents, custom UI — with no need to wait for a multi-vendor consensus process.

Key Statistics

Real data from verified industry sources to support your decision.

The Agent Plugins specification repository on GitHub has 348 stars and 18 forks, with the most recent push on 6 August 2026 — the day of the 1.0.0 release.

GitHub API

Six AI clients support Agent Plugins at launch: ChatGPT and Codex, Cursor, GitHub Copilot, Kiro and VS Code.

Vercel Blog

The Technical Steering Committee includes Core Maintainers from AWS, Cursor, Microsoft, OpenAI and Vercel, with Google joining as a Core Maintainer on launch day.

Agent Plugins Specification

Google shipped two products supporting Agent Plugins on day one: Agents CLI and Data Agent Kit, the latter providing skills and MCP servers for BigQuery, Spanner and Cloud SQL in a portable plugin format.

Google Developers Blog

The Agent Plugins manifest requires only two fields — $schema and name — making the portable contract intentionally minimal so that adoption cost is near zero for plugin authors.

Agent Plugins Specification

Anthropic, which created both Agent Skills and MCP, does not appear as a contributor, TSC member or launch client in the Agent Plugins 1.0.0 specification.

Vercel Blog

All statistics come from verified third-party sources. Source, year, and direct link are shown on each metric.

When to Choose Each Option

Clear guidance based on your specific situation and needs.

Choose Agent Plugins when...

  • You build extensions that need to run across multiple AI clients — ChatGPT, Cursor, GitHub Copilot, VS Code or Kiro — without repackaging for each one
  • You ship both Agent Skills and MCP servers together and want them discovered as one unit, with independent validation so a broken MCP server does not disable the Skills
  • You want your plugin to remain portable as new clients adopt the spec, without rewriting your packaging for each new client
  • You are building for the ecosystem floor: one directory, one manifest, one contract that any compatible client can load

Choose Standalone MCP Servers when...

  • You ship a single MCP server to a single client and mcp.json alone is the simpler answer — a plugin wrapper adds overhead without benefit
  • You need client-specific capabilities the portable contract does not cover — commands, hooks, agents or custom UI — and waiting for a multi-vendor consensus is not practical
  • Your environment requires a trust, permissions or sandboxing model that the spec explicitly does not define, and per-client deployment gives you that today
  • You need production maturity that a one-day-old specification cannot offer, and your MCP server already works across your target clients

Our Recommendation

Adopt Agent Plugins for any extension that needs to travel across more than one compatible client. The spec is one day old, but the problem it solves is real and well-understood: repackaging the same MCP server for every client is the default failure mode of the agent-extension ecosystem, and the six launch clients plus Google's day-one products cover enough surface area that a plugin packaged today will reach the majority of the market without modification. Stay with direct per-client MCP deployment when you are shipping to a single client, when you need client-specific capabilities that the portable contract does not cover (commands, hooks, agents), or when the absence of a trust and permissions model in the spec is a disqualifier rather than a deferred item. The spec is deliberately honest about what it does not define — no install mechanism, no distribution protocol, no sandboxing, no trust verification — and for regulated or enterprise environments those gaps matter today, even if they close in future versions. The pattern Context Studios favours is a hybrid one: package the portable parts (Agent Skills, MCP server declarations) as an Agent Plugin, and keep client-specific behaviour in the namespaced extension directory. When the portable contract is too narrow, ship directly. When it is wide enough, ship once. The spec's scope discipline is its strongest feature — it standardises only what genuinely travels, and leaves the rest where it belongs.

Frequently Asked Questions

Common questions about this comparison answered.

No. Agent Plugins is a packaging format that bundles MCP servers and Agent Skills into one portable directory. The MCP server inside a plugin is the same MCP server you would deploy directly — the spec explicitly does not redefine MCP.
No. Version 1 deliberately leaves installation, distribution, permissions, sandboxing, trust verification and user experience to each client. These are named openly in the project's future considerations, not quietly omitted.
If you are shipping one MCP server to one client, mcp.json on its own is still the simpler answer. Agent Plugins earn their keep when you have components that belong together and need to travel across multiple compatible clients.
Anthropic does not appear as a contributor, Technical Steering Committee member or launch client in the 1.0.0 specification, despite having created both technologies the spec packages — Agent Skills and the Model Context Protocol. The spec is vendor-neutral and open, so Anthropic could join at any time.

Need help deciding?

Book a free 30-minute consultation and we'll help you determine the best approach for your specific project.

Free consultation
No obligation
Response within 24h