[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7ETBSKSWM5866ZKZEM8JXEM":3,"skill-same:01M7ETBSKSWM5866ZKZEM8JXEM":47},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M7ETBSKSWM5866ZKZEM8JXEM","mcp-integration",null,"Integrate with the Model Context Protocol — its primitives (tools, resources, prompts), transports, auth, and debugging. Use when connecting agents to external data and capabilities through this open protocol.","TanNhatCMS\u002Fjarvis","TanNhatCMS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113796420?v=4","01M753MV17KG5CD3152G3WQEQY","KietNT","01M7EKEDYVYQ6PWVJJMZ911VMX",0,"MIT","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-mcp-integration\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: mcp-integration\ndescription: Integrate with the Model Context Protocol — its primitives (tools, resources, prompts), transports, auth, and debugging. Use when connecting agents to external data and capabilities through this open protocol.\ncategory: ai-research\n---\n\n# Model Context Protocol (MCP) Integration\n\nMCP is an open protocol for connecting AI agents to external capabilities: a standard way for \n\"servers\" to expose tools, data, and prompts that any compliant client can use. Learn the \nprimitives once, integrate with anything.\n\n## Overview\n\nMCP separates concerns: servers expose capabilities; clients (agents, apps) consume them; the \nprotocol defines how they talk. A server offers three primitives — tools (actions the model can \ninvoke), resources (data the model can read), and prompts (reusable prompt templates). Transports \ncarry the messages (stdio for local, HTTP-based for remote). Because it's a standard, one client \nworks with many servers, and capabilities compose without custom glue code per integration.\n\n## When to use\n\n- Giving an agent access to external systems (files, databases, APIs, services) through a standard \ninterface.\n- Building a server that exposes your system's capabilities to any MCP-compatible agent.\n- Choosing between a custom integration and a protocol-based one (prefer the protocol when clients \nvary).\n- Debugging a misbehaving MCP connection: handshake, capability, or transport issues.\n\n## Core concepts\n\n- **Tools**: executable functions a server exposes — with names, descriptions, and input schemas. \nThe model's action interface. Design them like good APIs: narrow, typed, documented.\n- **Resources**: readable data — files, records, query results — exposed at URIs the model can \nfetch. The model's read interface; separate from tools because reading isn't acting.\n- **Prompts**: server-defined prompt templates with parameters. Let servers ship best-practice \nprompts for their own domain.\n- **Transports**: stdio (server as a subprocess — simple, local) vs. networked HTTP transports \n(remote servers, multi-client). Choose by deployment: local tools → stdio; shared services → \nnetworked.\n- **Capability negotiation**: client and server agree on what's supported at handshake. Check \nnegotiated capabilities before assuming a feature exists.\n- **Auth**: networked servers need authentication — tokens, OAuth flows — scoped to least \nprivilege. Never put credentials in the protocol messages themselves beyond the auth layer.\n\n## Practical workflow\n\n1. Decide: consume or provide? Consuming = configure a client with server endpoints. Providing = \nimplement the three primitives for your system.\n2. As a consumer: configure servers, verify the handshake, list exposed tools\u002Fresources, and test \neach tool standalone before agent use.\n3. As a provider: expose tools with clean schemas, resources with sensible URIs, and prompts for \nyour common workflows. Start with read-only.\n4. Test the round trip: client lists capabilities → invokes tool → reads resource → uses \nprompt. Verify each primitive independently.\n5. Harden: auth on networked servers, input validation on tools, rate limits, and logging of every \ninvocation.\n6. Debug systematically: transport up? handshake complete? capabilities negotiated? tool schema \nvalid? — in that order.\n\n```text\nIntegration checklist:\n[ ] Transport chosen (local stdio vs networked) and working\n[ ] Handshake + capability negotiation verified\n[ ] Tools listed, schemas inspected, each tested standalone\n[ ] Resources readable at their URIs\n[ ] Auth configured with least-privilege scopes (networked)\n[ ] Invocation logging enabled\n```\n\n## Common pitfalls\n\n- **Assuming capabilities**: calling a tool the server didn't advertise. Always list and verify \nafter handshake.\n- **No auth on networked servers**: exposing tools over the network without authentication. Treat \nit like any public API.\n- **Tools that are too broad**: one tool that does everything defeats the protocol's composability. \nKeep tools narrow.\n- **Skipping standalone tests**: wiring an untested server into an agent and debugging both at \nonce. Test the server alone first.\n- **Credential leakage**: embedding secrets in configs checked into repos. Use env vars and secret \nstores.\n- **No versioning**: changing tool schemas without versioning breaks clients. Version your server's \ninterface.\n","# Model Context Protocol (MCP) Integration\n\nMCP is an open protocol for connecting AI agents to external capabilities: a standard way for \n\"servers\" to expose tools, data, and prompts that any compliant client can use. Learn the \nprimitives once, integrate with anything.\n\n## Overview\n\nMCP separates concerns: servers expose capabilities; clients (agents, apps) consume them; the \nprotocol defines how they talk. A server offers three primitives — tools (actions the model can \ninvoke), resources (data the model can read), and prompts (reusable prompt templates). Transports \ncarry the messages (stdio for local, HTTP-based for remote). Because it's a standard, one client \nworks with many servers, and capabilities compose without custom glue code per integration.\n\n## When to use\n\n- Giving an agent access to external systems (files, databases, APIs, services) through a standard \ninterface.\n- Building a server that exposes your system's capabilities to any MCP-compatible agent.\n- Choosing between a custom integration and a protocol-based one (prefer the protocol when clients \nvary).\n- Debugging a misbehaving MCP connection: handshake, capability, or transport issues.\n\n## Core concepts\n\n- **Tools**: executable functions a server exposes — with names, descriptions, and input schemas. \nThe model's action interface. Design them like good APIs: narrow, typed, documented.\n- **Resources**: readable data — files, records, query results — exposed at URIs the model can \nfetch. The model's read interface; separate from tools because reading isn't acting.\n- **Prompts**: server-defined prompt templates with parameters. Let servers ship best-practice \nprompts for their own domain.\n- **Transports**: stdio (server as a subprocess — simple, local) vs. networked HTTP transports \n(remote servers, multi-client). Choose by deployment: local tools → stdio; shared services → \nnetworked.\n- **Capability negotiation**: client and server agree on what's supported at handshake. Check \nnegotiated capabilities before assuming a feature exists.\n- **Auth**: networked servers need authentication — tokens, OAuth flows — scoped to least \nprivilege. Never put credentials in the protocol messages themselves beyond the auth layer.\n\n## Practical workflow\n\n1. Decide: consume or provide? Consuming = configure a client with server endpoints. Providing = \nimplement the three primitives for your system.\n2. As a consumer: configure servers, verify the handshake, list exposed tools\u002Fresources, and test \neach tool standalone before agent use.\n3. As a provider: expose tools with clean schemas, resources with sensible URIs, and prompts for \nyour common workflows. Start with read-only.\n4. Test the round trip: client lists capabilities → invokes tool → reads resource → uses \nprompt. Verify each primitive independently.\n5. Harden: auth on networked servers, input validation on tools, rate limits, and logging of every \ninvocation.\n6. Debug systematically: transport up? handshake complete? capabilities negotiated? tool schema \nvalid? — in that order.\n\n```text\nIntegration checklist:\n[ ] Transport chosen (local stdio vs networked) and working\n[ ] Handshake + capability negotiation verified\n[ ] Tools listed, schemas inspected, each tested standalone\n[ ] Resources readable at their URIs\n[ ] Auth configured with least-privilege scopes (networked)\n[ ] Invocation logging enabled\n```\n\n## Common pitfalls\n\n- **Assuming capabilities**: calling a tool the server didn't advertise. Always list and verify \nafter handshake.\n- **No auth on networked servers**: exposing tools over the network without authentication. Treat \nit like any public API.\n- **Tools that are too broad**: one tool that does everything defeats the protocol's composability. \nKeep tools narrow.\n- **Skipping standalone tests**: wiring an untested server into an agent and debugging both at \nonce. Test the server alone first.\n- **Credential leakage**: embedding secrets in configs checked into repos. Use env vars and secret \nstores.\n- **No versioning**: changing tool schemas without versioning breaks clients. Version your server's \ninterface.\n",{"name":5,"category":24,"description":7},"ai-research","main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-mcp-integration",1,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis","https:\u002F\u002Fgithub.com\u002FTanNhatCMS","https:\u002F\u002Fmrkiet.name.vn","2026-11-07 14:23:08",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add TanNhatCMS\u002Fjarvis --skill mcp-integration",{"tool":39,"command":40},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill mcp-integration",{"tool":42,"command":43},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill mcp-integration","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-mcp-integration\u002FSKILL.md",true,[],[48,55,63,70,77,84],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7EWYJR0J8DARY7E59Z6Y9MV","web-scrape","Turn web pages into LLM-ready markdown via the Firecrawl API (renders JS, anti-bot handling). Use when browser_open\u002Ffetch fails on JS-heavy pages, or when you need clean markdown\u002Fstructured extraction from a site. Requires FIRECRAWL_API_KEY.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fweb-scrape\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":59,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7EWYBN5P6F2AJG3FR24T9BP","design-taste-frontend","tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict no-slop house style with a real-browser inspector, and runs a look-and-fix loop on screenshots. Use this whenever you build, design, redesign, restyle, polish or review a landing page, marketing site, portfolio, product page, one-pager, hero or any public-facing web page, in any stack (HTML\u002FCSS, React, Next.js, Vue, Svelte, Astro, Tailwind) — also when the user says a page looks generic, templated, \"AI-made\", sloppy, or asks to make it look designed, premium, award-level or less like every other site. Not for dashboards or app screens.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7EWY8FQFNQ2GB7NZZWGSSDX","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-tdd\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7EWY5SHBFRH1HDHVWM9K7TV","systematic-debugging","Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-debugging\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7EWY3NM0Z0JAKS7HDZ24K66","requesting-code-review","Use when completing tasks, implementing major features, or before merging to verify work meets requirements","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-code-review\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7EWY0WRMWX4M9ZFY0WKC593","brainstorming","You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-brainstorming\u002FSKILL.md",[],[]]