Update to Manufact
Snapshot Nov 10, 2026 · 12:00 UTC · version 2.2.0
Declared capabilities changed
Full description — Now says: Build, deploy, test, and monitor MCP servers and plugins for the most popular AI Agents.
Observed in instructions or declared skills. Runtime behavior has not been tested.
Up to 3 plugins free · no card required.
All fields and original values.
Full description
Oct 29, 2026 · 00:00 UTC
Deploy, manage, and prepare MCP servers for publishing with Manufact Cloud.
Nov 10, 2026 · 12:00 UTC
Build, deploy, test, and monitor MCP servers and plugins for the most popular AI Agents.
Long description
Oct 29, 2026 · 00:00 UTC
deploy MCP servers from GitHub, inspect deployment status and logs, configure servers, and prepare publishing checklists and submission assets.
Nov 10, 2026 · 12:00 UTC
build, deploy, test, and monitor MCP servers and plugins for the most popular AI Agents. Deploy from GitHub or a starter template, inspect deployment status and logs, configure servers, test behavior with evals in supported clients, anal...
Short description
Oct 29, 2026 · 00:00 UTC
Deploy and manage MCP servers
Nov 10, 2026 · 12:00 UTC
Build, test & ship MCP servers
Declared skills
Oct 29, 2026 · 00:00 UTC
[{"description":"Read Manufact Cloud server analytics and investigate usage, errors, latency, clients, actors, sessions, or issues. Choose focused evidence tools or catalog-driven metrics, with scoped read-only SQL for questions the type...
Nov 10, 2026 · 12:00 UTC
[{"description":"Get started with Manufact Cloud to build, deploy, test, and monitor MCP servers and plugins. Use right after a user connects Manufact, or when they ask what Manufact does or where to start. Covers the account model, a qu...
Compare saved observations
Download comparison JSONFull technical diff · 13 changed fields
changed /release/description
"Deploy, manage, and prepare MCP servers for publishing with Manufact Cloud."
"Build, deploy, test, and monitor MCP servers and plugins for the most popular AI Agents."
changed /release/id
"pluginrel_e78d41100b2c8191ad1a6aa1d6d9e0a1"
"pluginrel_506140d76cd8819191899a906c936567"
changed /release/interface/composer_icon_dark_url
"https://files.openai.com/content?id=file_000000002c34823094e71228f470c89f"
null
changed /release/interface/composer_icon_url
"https://files.openai.com/content?id=file_000000001668823094d8c0397595d277"
"https://files.openai.com/content?id=file_00000000216881f7a25f5de2befa621c"
changed /release/interface/default_prompt
"Help me get started with Manufact."
null
changed /release/interface/default_prompts
[ "Help me get started with Manufact.", "Show the status of my MCP servers.", "Check whether my MCP server is ready to publish." ]
null
changed /release/interface/logo_url
"https://files.openai.com/content?id=file_000000008ad48230af971c16030bb11d"
"https://files.openai.com/content?id=file_000000008ad481f7abf44b728b4e837d"
changed /release/interface/logo_url_dark
"https://files.openai.com/content?id=file_000000007914823085271a1de8a0042a"
null
changed /release/interface/long_description
"Manufact helps you deploy MCP servers from GitHub, inspect deployment status and logs, configure servers, and prepare publishing checklists and submission assets. Connect your Manufact account to use these workflows."
"Manufact helps you build, deploy, test, and monitor MCP servers and plugins for the most popular AI Agents. Deploy from GitHub or a starter template, inspect deployment status and logs, configure servers, test behavior with evals in supported clients, analyze usage and errors, check publishing readiness for supported directories, and package plugins with guided listing and review preparation. Connect your Manufact account to use these workflows."
changed /release/interface/short_description
"Deploy and manage MCP servers"
"Build, test & ship MCP servers"
changed /release/onboarding_skill_name
"manufact-onboarding"
"manufact-getting-started"
changed /release/skills
[
{
"description": "Read Manufact Cloud server analytics and investigate usage, errors, latency, clients, actors, sessions, or issues. Choose focused evidence tools or catalog-driven metrics, with scoped read-only SQL for questions the typed metrics cannot express. Use for existing server telemetry, not deployment changes or payload-capture configuration.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "manufact-analytics",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "chart",
"short_description": "Read Manufact Cloud server analytics and investigate usage, errors, latency, clients, actors, sessions, or issues. Choose focused evidence tools or catalog-driven metrics, with scoped read-only SQL for questions the typed metrics cannot express. Use for existing server telemetry, not deployment changes or payload-capture configuration."
},
"name": "manufact-analytics",
"plugin_release_skill_id": "pluginrsk_6ae23a4de4d08191988e895aec3ac1a7"
},
{
"description": "Use when a user wants to deploy an MCP server or MCP app to Manufact Cloud, redeploy or promote a deployment, set up preview branches, environment variables, or domains, or find out why a deployment failed. Covers repository requirements, the GitHub-to-live-URL flow, and the build/runtime log troubleshooting loop.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "manufact-deploy",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "bolt",
"short_description": "Use when a user wants to deploy an MCP server or MCP app to Manufact Cloud, redeploy or promote a deployment, set up preview branches, environment variables, or domains, or find out why a deployment failed. Covers repository requirements, the GitHub-to-live-URL flow, and the build/runtime log troubleshooting loop."
},
"name": "manufact-deploy",
"plugin_release_skill_id": "pluginrsk_6ae23a4ded1c8191aa1fcaf568723182"
},
{
"description": "Use right after a user connects the Manufact Cloud MCP server, or when they ask what Manufact is, what they can do with it, or where to start. Explains the platform model (users, organizations, servers, deployments), inspects the user's account, and routes them to deploying, managing, or publishing an MCP server.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "manufact-onboarding",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "hierarchy",
"short_description": "Use right after a user connects the Manufact Cloud MCP server, or when they ask what Manufact is, what they can do with it, or where to start. Explains the platform model (users, organizations, servers, deployments), inspects the user's account, and routes them to deploying, managing, or publishing an MCP server."
},
"name": "manufact-onboarding",
"plugin_release_skill_id": "pluginrsk_6ae23a4de3d081919ab533233592cb8b"
},
{
"description": "Use when a user wants to know whether their MCP server or MCP app is ready to publish to ChatGPT, Claude, or another app directory, wants to run or fix the Manufact publishing checklist, test the server with evals, or prepare submission assets such as screenshots, a demo video, and submission metadata.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "manufact-publish-ready",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "code",
"short_description": "Use when a user wants to know whether their MCP server or MCP app is ready to publish to ChatGPT, Claude, or another app directory, wants to run or fix the Manufact publishing checklist, test the server with evals, or prepare submission assets such as screenshots, a demo video, and submission metadata."
},
"name": "manufact-publish-ready",
"plugin_release_skill_id": "pluginrsk_6ae23a4e0b1c81919e1abfa019072f9a"
}
][
{
"description": "Get started with Manufact Cloud to build, deploy, test, and monitor MCP servers and plugins. Use right after a user connects Manufact, or when they ask what Manufact does or where to start. Covers the account model, a quick-start template deploy that needs no GitHub, and routing to deployment, testing, analytics, or publishing for the most popular AI Agents.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "manufact-getting-started",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "code",
"short_description": "Get started with Manufact Cloud to build, deploy, test, and monitor MCP servers and plugins. Use right after a user connects Manufact, or when they ask what Manufact does or where to start. Covers the account model, a quick-start template deploy that needs no GitHub, and routing to deployment, testing, analytics, or publishing for the most popular AI Agents."
},
"name": "manufact-getting-started",
"plugin_release_skill_id": "pluginrsk_6aee158773a881919632740ecdcfb68b"
},
{
"description": "Analyze MCP server and plugin usage, errors, latency, and client traffic on Manufact Cloud. Use to investigate a deployed server's usage, errors, latency, clients, actors, sessions, or issues. Choose focused evidence tools or catalog-driven metrics, with scoped read-only SQL for questions the typed metrics cannot express. Use for existing server telemetry, not deployment changes or payload-capture configuration.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "mcp-plugin-analytics",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "chart",
"short_description": "Analyze MCP server and plugin usage, errors, latency, and client traffic on Manufact Cloud. Use to investigate a deployed server's usage, errors, latency, clients, actors, sessions, or issues. Choose focused evidence tools or catalog-driven metrics, with scoped read-only SQL for questions the typed metrics cannot express. Use for existing server telemetry, not deployment changes or payload-capture configuration."
},
"name": "mcp-plugin-analytics",
"plugin_release_skill_id": "pluginrsk_6aee158788d88191af36129f3719095b"
},
{
"description": "Deploy MCP servers and plugins on Manufact Cloud; configure builds, domains, and environments. Use when a user wants to deploy an MCP server or MCP app from GitHub or a starter template, redeploy or promote a deployment, set up preview branches, environment variables, or domains, or find out why a deployment failed. The live MCP URL works with the most popular AI Agents.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "mcp-plugin-deploy",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "bolt",
"short_description": "Deploy MCP servers and plugins on Manufact Cloud; configure builds, domains, and environments. Use when a user wants to deploy an MCP server or MCP app from GitHub or a starter template, redeploy or promote a deployment, set up preview branches, environment variables, or domains, or find out why a deployment failed. The live MCP URL works with the most popular AI Agents."
},
"name": "mcp-plugin-deploy",
"plugin_release_skill_id": "pluginrsk_6aee158754208191bd4e40c1629955bd"
},
{
"description": "Check publishing readiness for MCP servers and plugins; prepare supported directory submissions. Use when a user wants to know whether an MCP server or MCP app is ready for supported AI agent directories, run or fix the Manufact publishing checklist, or package an Agent Plugin with listing metadata, review cases, and a demo recording. For standalone behavior testing, use mcp-plugin-testing.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "mcp-plugin-publishing",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "hierarchy",
"short_description": "Check publishing readiness for MCP servers and plugins; prepare supported directory submissions. Use when a user wants to know whether an MCP server or MCP app is ready for supported AI agent directories, run or fix the Manufact publishing checklist, or package an Agent Plugin with listing metadata, review cases, and a demo recording. For standalone behavior testing, use mcp-plugin-testing."
},
"name": "mcp-plugin-publishing",
"plugin_release_skill_id": "pluginrsk_6aee1587b00081918058bc550d344855"
},
{
"description": "Test MCP servers and plugins across supported clients; create evals and investigate failures. Use when a user wants to check whether models pick the right tools and give useful answers in real clients, compare models or clients, rerun tests after a change, or understand why a test failed. Discover supported clients, models, and agent runtimes with get_eval_options.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "mcp-plugin-testing",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "code",
"short_description": "Test MCP servers and plugins across supported clients; create evals and investigate failures. Use when a user wants to check whether models pick the right tools and give useful answers in real clients, compare models or clients, rerun tests after a change, or understand why a test failed. Discover supported clients, models, and agent runtimes with get_eval_options."
},
"name": "mcp-plugin-testing",
"plugin_release_skill_id": "pluginrsk_6aee158802108191aeca53a3e2a3d463"
}
]changed /release/version
"2.1.2"
"2.2.0"
Full snapshot data
{
"canonical_app_id": "asdk_app_69cbfd610c3881919163e080ede4d042",
"connector_id": "asdk_app_69cbfd610c3881919163e080ede4d042",
"created_at": "2026-06-04T16:10:35.512033Z",
"discoverability": "LISTED",
"id": "plugin_asdk_app_69cbfd610c3881919163e080ede4d042",
"is_template": false,
"is_template_instance": false,
"name": "app-69cbfd610c3881919163e080ede4d042",
"release": {
"app_ids": [
"asdk_app_69cbfd610c3881919163e080ede4d042"
],
"app_manifest": {
"apps": {
"manufact": {
"id": "asdk_app_69cbfd610c3881919163e080ede4d042",
"required": true
}
}
},
"app_templates": [],
"description": "Build, deploy, test, and monitor MCP servers and plugins for the most popular AI Agents.",
"display_name": "Manufact",
"id": "pluginrel_506140d76cd8819191899a906c936567",
"interface": {
"brand_color": null,
"capabilities": [
"Read",
"Write"
],
"category": "Developer Tools",
"composer_icon_dark_url": null,
"composer_icon_url": "https://files.openai.com/content?id=file_00000000216881f7a25f5de2befa621c",
"default_prompt": null,
"default_prompts": null,
"developer_name": "Manufact",
"logo_url": "https://files.openai.com/content?id=file_000000008ad481f7abf44b728b4e837d",
"logo_url_dark": null,
"long_description": "Manufact helps you build, deploy, test, and monitor MCP servers and plugins for the most popular AI Agents. Deploy from GitHub or a starter template, inspect deployment status and logs, configure servers, test behavior with evals in supported clients, analyze usage and errors, check publishing readiness for supported directories, and package plugins with guided listing and review preparation. Connect your Manufact account to use these workflows.",
"plugin_category_id": "developer tools",
"privacy_policy_url": "https://manufact.com/privacy",
"screenshot_urls": [],
"short_description": "Build, test & ship MCP servers",
"terms_of_service_url": "https://manufact.com/terms",
"website_url": "https://manufact.com"
},
"keywords": [],
"onboarding_skill_name": "manufact-getting-started",
"requires_local_executor": false,
"skills": [
{
"description": "Get started with Manufact Cloud to build, deploy, test, and monitor MCP servers and plugins. Use right after a user connects Manufact, or when they ask what Manufact does or where to start. Covers the account model, a quick-start template deploy that needs no GitHub, and routing to deployment, testing, analytics, or publishing for the most popular AI Agents.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "manufact-getting-started",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "code",
"short_description": "Get started with Manufact Cloud to build, deploy, test, and monitor MCP servers and plugins. Use right after a user connects Manufact, or when they ask what Manufact does or where to start. Covers the account model, a quick-start template deploy that needs no GitHub, and routing to deployment, testing, analytics, or publishing for the most popular AI Agents."
},
"name": "manufact-getting-started",
"plugin_release_skill_id": "pluginrsk_6aee158773a881919632740ecdcfb68b"
},
{
"description": "Analyze MCP server and plugin usage, errors, latency, and client traffic on Manufact Cloud. Use to investigate a deployed server's usage, errors, latency, clients, actors, sessions, or issues. Choose focused evidence tools or catalog-driven metrics, with scoped read-only SQL for questions the typed metrics cannot express. Use for existing server telemetry, not deployment changes or payload-capture configuration.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "mcp-plugin-analytics",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "chart",
"short_description": "Analyze MCP server and plugin usage, errors, latency, and client traffic on Manufact Cloud. Use to investigate a deployed server's usage, errors, latency, clients, actors, sessions, or issues. Choose focused evidence tools or catalog-driven metrics, with scoped read-only SQL for questions the typed metrics cannot express. Use for existing server telemetry, not deployment changes or payload-capture configuration."
},
"name": "mcp-plugin-analytics",
"plugin_release_skill_id": "pluginrsk_6aee158788d88191af36129f3719095b"
},
{
"description": "Deploy MCP servers and plugins on Manufact Cloud; configure builds, domains, and environments. Use when a user wants to deploy an MCP server or MCP app from GitHub or a starter template, redeploy or promote a deployment, set up preview branches, environment variables, or domains, or find out why a deployment failed. The live MCP URL works with the most popular AI Agents.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "mcp-plugin-deploy",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "bolt",
"short_description": "Deploy MCP servers and plugins on Manufact Cloud; configure builds, domains, and environments. Use when a user wants to deploy an MCP server or MCP app from GitHub or a starter template, redeploy or promote a deployment, set up preview branches, environment variables, or domains, or find out why a deployment failed. The live MCP URL works with the most popular AI Agents."
},
"name": "mcp-plugin-deploy",
"plugin_release_skill_id": "pluginrsk_6aee158754208191bd4e40c1629955bd"
},
{
"description": "Check publishing readiness for MCP servers and plugins; prepare supported directory submissions. Use when a user wants to know whether an MCP server or MCP app is ready for supported AI agent directories, run or fix the Manufact publishing checklist, or package an Agent Plugin with listing metadata, review cases, and a demo recording. For standalone behavior testing, use mcp-plugin-testing.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "mcp-plugin-publishing",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "hierarchy",
"short_description": "Check publishing readiness for MCP servers and plugins; prepare supported directory submissions. Use when a user wants to know whether an MCP server or MCP app is ready for supported AI agent directories, run or fix the Manufact publishing checklist, or package an Agent Plugin with listing metadata, review cases, and a demo recording. For standalone behavior testing, use mcp-plugin-testing."
},
"name": "mcp-plugin-publishing",
"plugin_release_skill_id": "pluginrsk_6aee1587b00081918058bc550d344855"
},
{
"description": "Test MCP servers and plugins across supported clients; create evals and investigate failures. Use when a user wants to check whether models pick the right tools and give useful answers in real clients, compare models or clients, rerun tests after a change, or understand why a test failed. Discover supported clients, models, and agent runtimes with get_eval_options.",
"interface": {
"brand_color": null,
"default_prompt": null,
"display_name": "mcp-plugin-testing",
"icon_large_url": null,
"icon_small_url": null,
"iconography": "code",
"short_description": "Test MCP servers and plugins across supported clients; create evals and investigate failures. Use when a user wants to check whether models pick the right tools and give useful answers in real clients, compare models or clients, rerun tests after a change, or understand why a test failed. Discover supported clients, models, and agent runtimes with get_eval_options."
},
"name": "mcp-plugin-testing",
"plugin_release_skill_id": "pluginrsk_6aee158802108191aeca53a3e2a3d463"
}
],
"version": "2.2.0"
},
"scope": "GLOBAL",
"status": "ENABLED"
}SHA-256 of public snapshot: a556c0b49a4a52f64cf4bfb72a3de5767ba2e408c24e0519671a5a8e78f33944