[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78ZC6773RSDQMT06ABQCKCS":3,"skill-same:01M78ZC6773RSDQMT06ABQCKCS":67},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M78ZC6773RSDQMT06ABQCKCS","mcp",null,"Expose LitServe LitAPI endpoints as Model Context Protocol tools with schema extraction, streamable HTTP mounting, and connection troubleshooting.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flitserve\u002Fsub-skills\u002Fmcp\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: mcp\ndescription: \"Expose LitServe LitAPI endpoints as Model Context Protocol tools\n  with schema extraction, streamable HTTP mounting, and connection\n  troubleshooting.\"\nmetadata:\n  disco-role: operating\ndisable-model-invocation: true\nlicense: Apache 2.0\n---\n\n# LitServe MCP sub-skill\n\nUse this sub-skill when a user wants to expose a `LitAPI` as a Model Context Protocol (MCP) tool, build or debug the tool schema, mount the streamable HTTP MCP route, or connect an MCP client such as Claude Desktop to a LitServe app.\n\n## Routing\n\n- Start here for requests like “add MCP to my LitServe app”, “make a tool from `decode_request`”, “why does MCP say it is not connected”, “mount the streamable HTTP MCP route”, or “build the MCP schema from Pydantic\u002Ftype hints”.\n- Use the root LitServe router at `..\u002F..\u002FSKILL.md` when the request is broader than MCP.\n- Use `..\u002Fserver-basics\u002FSKILL.md` when the user needs the underlying `LitAPI`, `LitServer`, request\u002Fresponse, batching, streaming, auth, middleware, or deployment model first.\n- Route OpenAI-compatible chat and embedding endpoint work to `..\u002Fopenai-specs\u002FSKILL.md`.\n- Do not cover benchmark-only, torch-heavy, parity-throughput, or accelerator-specific workflows here.\n\n## Operating checklist\n\n1. Confirm the runtime has `fastmcp` installed. LitServe MCP construction raises a runtime error when MCP support packages are unavailable.\n2. Create an `MCP` object with at least a useful `description`; optionally set a unique `name` and a manual `input_schema`.\n3. Pass the `MCP` object into the `LitAPI` constructor (`super().__init__(mcp=...)` or a base class that accepts `mcp`). This connects the MCP object to the `LitAPI`; do not call private connection methods in user code.\n4. Prefer automatic schema extraction from `decode_request` when the endpoint accepts a Pydantic request model or well-annotated parameters. Use a manual `input_schema` only when it matches the actual LitServe endpoint handler arguments.\n5. Build the server with `ls.LitServer(api)` and run it normally. LitServe registers the tool and mounts the streamable HTTP MCP app automatically when MCP support is available.\n6. Tell MCP clients to connect to the same host and port with the `\u002Fmcp\u002F` suffix, for example `http:\u002F\u002Flocalhost:8000\u002Fmcp\u002F`.\n7. If the client lists the tool but tool calls fail, debug the schema shape, tool name uniqueness, and endpoint path mapping before changing core server code.\n\n## Reference map\n\n- `references\u002Fapi-reference.md` — exact MCP constructor behavior, schema helper behavior, connector internals, and streamable HTTP route details.\n- `references\u002Fworkflows.md` — copyable patterns for adding MCP to a `LitAPI`, using Pydantic\u002Ftype-hint schemas, checking the tool object, connecting clients, and Claude Desktop setup.\n- `references\u002Ftroubleshooting.md` — common failures: missing `fastmcp`, disconnected MCP, missing name\u002Fdescription, malformed schema, endpoint collisions, missing mounted route, beta warning, and Claude Desktop confusion.\n- `scripts\u002Fmcp_server.py` — safe bundled example adapted from LitServe MCP behavior; it can print the generated tool metadata or run a local MCP-enabled LitServe server.\n\n## Facts to preserve\n\n- `MCP(description=None, input_schema=None, name=None)` accepts `description`, `input_schema`, and `name`.\n- `extract_input_schema(func) -> dict[str, Any]` is available from `litserve.mcp`.\n- `_python_type_to_json_schema` and `_param_name_to_title` are available helper functions.\n- `MCP.as_tool()` requires a connected `LitAPI` and returns a `ToolEndpointType` with `name`, `description`, `inputSchema`, and `endpoint`.\n- The tool name is sanitized by removing a leading slash and replacing remaining slashes with underscores.\n- The MCP streamable HTTP endpoint is `\u002Fmcp\u002F` on the LitServe server.\n- MCP support is beta and its APIs may change.\n","# LitServe MCP sub-skill\n\nUse this sub-skill when a user wants to expose a `LitAPI` as a Model Context Protocol (MCP) tool, build or debug the tool schema, mount the streamable HTTP MCP route, or connect an MCP client such as Claude Desktop to a LitServe app.\n\n## Routing\n\n- Start here for requests like “add MCP to my LitServe app”, “make a tool from `decode_request`”, “why does MCP say it is not connected”, “mount the streamable HTTP MCP route”, or “build the MCP schema from Pydantic\u002Ftype hints”.\n- Use the root LitServe router at `..\u002F..\u002FSKILL.md` when the request is broader than MCP.\n- Use `..\u002Fserver-basics\u002FSKILL.md` when the user needs the underlying `LitAPI`, `LitServer`, request\u002Fresponse, batching, streaming, auth, middleware, or deployment model first.\n- Route OpenAI-compatible chat and embedding endpoint work to `..\u002Fopenai-specs\u002FSKILL.md`.\n- Do not cover benchmark-only, torch-heavy, parity-throughput, or accelerator-specific workflows here.\n\n## Operating checklist\n\n1. Confirm the runtime has `fastmcp` installed. LitServe MCP construction raises a runtime error when MCP support packages are unavailable.\n2. Create an `MCP` object with at least a useful `description`; optionally set a unique `name` and a manual `input_schema`.\n3. Pass the `MCP` object into the `LitAPI` constructor (`super().__init__(mcp=...)` or a base class that accepts `mcp`). This connects the MCP object to the `LitAPI`; do not call private connection methods in user code.\n4. Prefer automatic schema extraction from `decode_request` when the endpoint accepts a Pydantic request model or well-annotated parameters. Use a manual `input_schema` only when it matches the actual LitServe endpoint handler arguments.\n5. Build the server with `ls.LitServer(api)` and run it normally. LitServe registers the tool and mounts the streamable HTTP MCP app automatically when MCP support is available.\n6. Tell MCP clients to connect to the same host and port with the `\u002Fmcp\u002F` suffix, for example `http:\u002F\u002Flocalhost:8000\u002Fmcp\u002F`.\n7. If the client lists the tool but tool calls fail, debug the schema shape, tool name uniqueness, and endpoint path mapping before changing core server code.\n\n## Reference map\n\n- `references\u002Fapi-reference.md` — exact MCP constructor behavior, schema helper behavior, connector internals, and streamable HTTP route details.\n- `references\u002Fworkflows.md` — copyable patterns for adding MCP to a `LitAPI`, using Pydantic\u002Ftype-hint schemas, checking the tool object, connecting clients, and Claude Desktop setup.\n- `references\u002Ftroubleshooting.md` — common failures: missing `fastmcp`, disconnected MCP, missing name\u002Fdescription, malformed schema, endpoint collisions, missing mounted route, beta warning, and Claude Desktop confusion.\n- `scripts\u002Fmcp_server.py` — safe bundled example adapted from LitServe MCP behavior; it can print the generated tool metadata or run a local MCP-enabled LitServe server.\n\n## Facts to preserve\n\n- `MCP(description=None, input_schema=None, name=None)` accepts `description`, `input_schema`, and `name`.\n- `extract_input_schema(func) -> dict[str, Any]` is available from `litserve.mcp`.\n- `_python_type_to_json_schema` and `_param_name_to_title` are available helper functions.\n- `MCP.as_tool()` requires a connected `LitAPI` and returns a `ToolEndpointType` with `name`, `description`, `inputSchema`, and `endpoint`.\n- The tool name is sanitized by removing a leading slash and replacing remaining slashes with underscores.\n- The MCP streamable HTTP endpoint is `\u002Fmcp\u002F` on the LitServe server.\n- MCP support is beta and its APIs may change.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Flitserve\u002Fsub-skills\u002Fmcp",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill mcp",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill mcp",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill mcp","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flitserve\u002Fsub-skills\u002Fmcp\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fapi-reference.md","REFERENCE","参考文档",9707,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flitserve\u002Fsub-skills\u002Fmcp\u002Freferences\u002Fapi-reference.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Ftroubleshooting.md",8631,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flitserve\u002Fsub-skills\u002Fmcp\u002Freferences\u002Ftroubleshooting.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Fworkflows.md",7741,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flitserve\u002Fsub-skills\u002Fmcp\u002Freferences\u002Fworkflows.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fmcp_server.py","SCRIPT","脚本",3271,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Flitserve\u002Fsub-skills\u002Fmcp\u002Fscripts\u002Fmcp_server.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]