{ "canonical_name": "mcp-use/mcp-use", "compilation_id": "pack_57058c11890d402c9fd49ad3a2836b1d", "created_at": "2026-06-13T16:54:27.180171+00:00", "created_by": "project-pack-compiler", "feedback": { "carrier_selection_notes": [ "viable_asset_types=mcp_config, recipe, host_instruction, eval, preflight", "recommended_asset_types=mcp_config, recipe, host_instruction, eval, preflight" ], "evidence_delta": { "confirmed_claims": [ "identity_anchor_present", "capability_and_host_targets_present", "install_path_declared_or_better" ], "missing_required_fields": [], "must_verify_forwarded": [ "Run or inspect `npx create-mcp-use-app@latest` in an isolated environment.", "Confirm the project exposes the claimed capability to at least one target host." ], "quickstart_execution_scope": "allowlisted_sandbox_smoke", "sandbox_command": "npx create-mcp-use-app@latest", "sandbox_container_image": "node:22-slim", "sandbox_execution_backend": "docker", "sandbox_planner_decision": "llm_execute_isolated_install", "sandbox_validation_id": "sbx_fb22a8e5bca24c6882cdb48a99e7fd58" }, "feedback_event_type": "project_pack_compilation_feedback", "learning_candidate_reasons": [], "template_gaps": [] }, "identity": { "canonical_id": "project_4951c9bed45eb3c04c8792137a39d3bd", "canonical_name": "mcp-use/mcp-use", "homepage_url": null, "license": "unknown", "repo_url": "https://github.com/mcp-use/mcp-use", "slug": "mcp-use", "source_packet_id": "phit_dc2f15a1c09a4d90b5bb9125625dc0a0", "source_validation_id": "dval_9dfeba3e5c6a4f53b5b8ce53d53128ce" }, "merchandising": { "best_for": "需要工具连接与集成能力，并使用 mcp_host的用户", "github_forks": 1329, "github_stars": 10098, "one_liner_en": "The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.", "one_liner_zh": "全栈 MCP 框架，用于开发面向 ChatGPT / Claude 的 MCP 应用，以及面向 AI Agent 的 MCP 服务器。", "primary_category": { "category_id": "tool-integrations", "confidence": "medium", "name_en": "Tool Integrations", "name_zh": "工具连接与集成", "reason": "matched_keywords:mcp, github" }, "target_user": "使用 mcp_host, claude_code, claude 等宿主 AI 的用户", "title_en": "mcp-use", "title_zh": "mcp-use 能力包", "visible_tags": [ { "label_en": "MCP Tools", "label_zh": "MCP 工具", "source": "repo_evidence_project_characteristics", "tag_id": "product_domain-mcp-tools", "type": "product_domain" }, { "label_en": "Tool Integration", "label_zh": "工具接入扩展", "source": "repo_evidence_project_characteristics", "tag_id": "user_job-tool-integration", "type": "user_job" }, { "label_en": "Project Capability", "label_zh": "项目能力包", "source": "repo_evidence_project_characteristics", "tag_id": "core_capability-project-capability", "type": "core_capability" }, { "label_en": "Verifiable Workflow", "label_zh": "可验证工作流", "source": "repo_evidence_project_characteristics", "tag_id": "workflow_pattern-verifiable-workflow", "type": "workflow_pattern" }, { "label_en": "Evidence-backed Context", "label_zh": "证据化上下文", "source": "repo_evidence_project_characteristics", "tag_id": "selection_signal-evidence-backed-context", "type": "selection_signal" } ] }, "packet_id": "phit_dc2f15a1c09a4d90b5bb9125625dc0a0", "page_model": { "artifacts": { "artifact_slug": "mcp-use", "files": [ "PROJECT_PACK.json", "QUICK_START.md", "PROMPT_PREVIEW.md", "HUMAN_MANUAL.md", "AI_CONTEXT_PACK.md", "BOUNDARY_RISK_CARD.md", "PITFALL_LOG.md", "REPO_INSPECTION.json", "REPO_INSPECTION.md", "CAPABILITY_CONTRACT.json", "EVIDENCE_INDEX.json", "CLAIM_GRAPH.json" ], "required_files": [ "PROJECT_PACK.json", "QUICK_START.md", "PROMPT_PREVIEW.md", "HUMAN_MANUAL.md", "AI_CONTEXT_PACK.md", "BOUNDARY_RISK_CARD.md", "PITFALL_LOG.md", "REPO_INSPECTION.json" ] }, "detail": { "capability_source": "Project Hit Packet + DownstreamValidationResult", "commands": [ { "command": "npx create-mcp-use-app@latest", "label": "Node.js / npx · 官方安装入口", "source": "https://github.com/mcp-use/mcp-use#readme", "verified": true } ], "display_tags": [ "MCP 工具", "工具接入扩展", "项目能力包", "可验证工作流", "证据化上下文" ], "eyebrow": "工具连接与集成", "glance": [ { "body": "判断自己是不是目标用户。", "label": "最适合谁", "value": "需要工具连接与集成能力，并使用 mcp_host的用户" }, { "body": "先理解能力边界，再决定是否继续。", "label": "核心价值", "value": "The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents." }, { "body": "未完成验证前保持审慎。", "label": "继续前", "value": "publish to Doramagic.ai project surfaces" } ], "guardrail_source": "Boundary & Risk Card", "guardrails": [ { "body": "Prompt Preview 只展示流程，不证明项目已安装或运行。", "label": "Check 1", "value": "不要把试用当真实运行" }, { "body": "mcp_host, claude_code, claude, chatgpt, cursor", "label": "Check 2", "value": "确认宿主兼容" }, { "body": "publish to Doramagic.ai project surfaces", "label": "Check 3", "value": "先隔离验证" } ], "mode": "mcp_config, recipe, host_instruction, eval, preflight", "pitfall_log": { "items": [ { "body": "Project evidence flags a installation risk. Review the linked source before relying on this workflow.", "category": "Installation risk", "evidence": [ "community_evidence:github | https://github.com/mcp-use/mcp-use/issues/1727" ], "severity": "high", "suggested_check": "Reproduce the official install and quickstart path in an isolated environment.", "title": "Installation risk requires verification", "user_impact": "May increase setup, validation, or first-run risk for the user." }, { "body": "Project evidence flags a installation risk. Review the linked source before relying on this workflow.", "category": "Installation risk", "evidence": [ "community_evidence:github | https://github.com/mcp-use/mcp-use/issues/1726" ], "severity": "high", "suggested_check": "Reproduce the official install and quickstart path in an isolated environment.", "title": "Installation risk requires verification", "user_impact": "May increase setup, validation, or first-run risk for the user." }, { "body": "Project evidence flags a configuration risk. Review the linked source before relying on this workflow.", "category": "Configuration risk", "evidence": [ "community_evidence:github | https://github.com/mcp-use/mcp-use/issues/1724" ], "severity": "high", "suggested_check": "Reproduce the official install and quickstart path in an isolated environment.", "title": "Configuration risk requires verification", "user_impact": "May increase setup, validation, or first-run risk for the user." }, { "body": "Project evidence flags a security or permission risk. Review the linked source before relying on this workflow.", "category": "Security or permission risk", "evidence": [ "community_evidence:github | https://github.com/mcp-use/mcp-use/issues/947" ], "severity": "high", "suggested_check": "Reproduce the official install and quickstart path in an isolated environment.", "title": "Security or permission risk requires verification", "user_impact": "May increase setup, validation, or first-run risk for the user." }, { "body": "Developers should check this installation risk before relying on the project: Example: Chart Library MCP for financial pattern analysis", "category": "Installation risk", "evidence": [ "failure_mode_cluster:github_issue | https://github.com/mcp-use/mcp-use/issues/1286" ], "severity": "medium", "suggested_check": "Before packaging this project, run the relevant install/config/quickstart check for: Example: Chart Library MCP for financial pattern analysis. Context: Observed when using python", "title": "Installation risk requires verification", "user_impact": "Developers may fail before the first successful local run: Example: Chart Library MCP for financial pattern analysis" }, { "body": "Project evidence flags a installation risk. Review the linked source before relying on this workflow.", "category": "Installation risk", "evidence": [ "community_evidence:github | https://github.com/mcp-use/mcp-use/issues/1286" ], "severity": "medium", "suggested_check": "Reproduce the official install and quickstart path in an isolated environment.", "title": "Installation risk requires verification", "user_impact": "May increase setup, validation, or first-run risk for the user." }, { "body": "Project evidence flags a configuration risk. Review the linked source before relying on this workflow.", "category": "Configuration risk", "evidence": [ "capability.host_targets | github_repo:956472076 | https://github.com/mcp-use/mcp-use" ], "severity": "medium", "suggested_check": "Reproduce the official install and quickstart path in an isolated environment.", "title": "Configuration risk requires verification", "user_impact": "May increase setup, validation, or first-run risk for the user." }, { "body": "Developers should check this configuration risk before relying on the project: @mcp-use/cli 3.5.0", "category": "Configuration risk", "evidence": [ "failure_mode_cluster:github_release | https://github.com/mcp-use/mcp-use/releases/tag/%40mcp-use/cli%403.5.0" ], "severity": "medium", "suggested_check": "Before packaging this project, run the relevant install/config/quickstart check for: @mcp-use/cli 3.5.0. Context: Source discussion did not expose a precise runtime context.", "title": "Configuration risk requires verification", "user_impact": "Upgrade or migration may change expected behavior: @mcp-use/cli 3.5.0" }, { "body": "Developers should check this configuration risk before relying on the project: Refactor HttpConnector and StdioConnector with per-connector configuration", "category": "Configuration risk", "evidence": [ "failure_mode_cluster:github_issue | https://github.com/mcp-use/mcp-use/issues/947" ], "severity": "medium", "suggested_check": "Before packaging this project, run the relevant install/config/quickstart check for: Refactor HttpConnector and StdioConnector with per-connector configuration. Context: Observed when using python, playwright", "title": "Configuration risk requires verification", "user_impact": "Developers may misconfigure credentials, environment, or host setup: Refactor HttpConnector and StdioConnector with per-connector configuration" }, { "body": "Developers should check this configuration risk before relying on the project: mcp-use 1.32.0", "category": "Configuration risk", "evidence": [ "failure_mode_cluster:github_release | https://github.com/mcp-use/mcp-use/releases/tag/mcp-use%401.32.0" ], "severity": "medium", "suggested_check": "Before packaging this project, run the relevant install/config/quickstart check for: mcp-use 1.32.0. Context: Source discussion did not expose a precise runtime context.", "title": "Configuration risk requires verification", "user_impact": "Upgrade or migration may change expected behavior: mcp-use 1.32.0" }, { "body": "Developers should check this configuration risk before relying on the project: mcp-use 1.32.1-canary.2", "category": "Configuration risk", "evidence": [ "failure_mode_cluster:github_release | https://github.com/mcp-use/mcp-use/releases/tag/mcp-use%401.32.1-canary.2" ], "severity": "medium", "suggested_check": "Before packaging this project, run the relevant install/config/quickstart check for: mcp-use 1.32.1-canary.2. Context: Source discussion did not expose a precise runtime context.", "title": "Configuration risk requires verification", "user_impact": "Upgrade or migration may change expected behavior: mcp-use 1.32.1-canary.2" }, { "body": "README/documentation is current enough for a first validation pass.", "category": "Capability evidence risk", "evidence": [ "capability.assumptions | github_repo:956472076 | https://github.com/mcp-use/mcp-use" ], "severity": "medium", "suggested_check": "Reproduce the official install and quickstart path in an isolated environment.", "title": "Capability evidence risk requires verification", "user_impact": "May increase setup, validation, or first-run risk for the user." }, { "body": "Project evidence flags a runtime risk. Review the linked source before relying on this workflow.", "category": "Runtime risk", "evidence": [ "community_evidence:github | https://github.com/mcp-use/mcp-use/issues/1723" ], "severity": "medium", "suggested_check": "Reproduce the official install and quickstart path in an isolated environment.", "title": "Runtime risk requires verification", "user_impact": "May increase setup, validation, or first-run risk for the user." }, { "body": "Developers should check this migration risk before relying on the project: Stateful StreamableHTTP transport hangs in mcp-use dev — tool result never reaches client (SSE response dropped, works with enableJsonResponse)", "category": "Maintenance risk", "evidence": [ "failure_mode_cluster:github_issue | https://github.com/mcp-use/mcp-use/issues/1724" ], "severity": "medium", "suggested_check": "Before packaging this project, run the relevant install/config/quickstart check for: Stateful StreamableHTTP transport hangs in mcp-use dev — tool result never reaches client (SSE response dropped, works with enableJsonResponse). Context: Observed when using node, macos", "title": "Maintenance risk requires verification", "user_impact": "Developers may hit a documented source-backed failure mode: Stateful StreamableHTTP transport hangs in mcp-use dev — tool result never reaches client (SSE response dropped, works with enableJsonResponse)" }, { "body": "Project evidence flags a maintenance risk. Review the linked source before relying on this workflow.", "category": "Maintenance risk", "evidence": [ "evidence.maintainer_signals | github_repo:956472076 | https://github.com/mcp-use/mcp-use" ], "severity": "medium", "suggested_check": "Reproduce the official install and quickstart path in an isolated environment.", "title": "Maintenance risk requires verification", "user_impact": "May increase setup, validation, or first-run risk for the user." }, { "body": "no_demo", "category": "Security or permission risk", "evidence": [ "downstream_validation.risk_items | github_repo:956472076 | https://github.com/mcp-use/mcp-use" ], "severity": "medium", "suggested_check": "Reproduce the official install and quickstart path in an isolated environment.", "title": "Security or permission risk requires verification", "user_impact": "May increase setup, validation, or first-run risk for the user." } ], "source": "ProjectPitfallLog + ProjectHitPacket + validation + community signals", "summary": "Found 29 structured pitfall item(s), including 4 high/blocking item(s). Top priority: Installation risk - Installation risk requires verification.", "title": "Pitfall Log" }, "snapshot": { "contributors": 44, "forks": 1329, "license": "unknown", "note": "站点快照，非实时质量证明；用于开工前背景判断。", "stars": 10098 }, "source_url": "https://github.com/mcp-use/mcp-use", "steps": [ { "body": "不安装项目，先体验能力节奏。", "code": "preview", "title": "先试 Prompt" }, { "body": "理解输入、输出、失败模式和边界。", "code": "manual", "title": "读说明书" }, { "body": "把上下文交给宿主 AI 继续工作。", "code": "context", "title": "带给 AI" }, { "body": "进入主力环境前先完成安装入口与风险边界验证。", "code": "verify", "title": "沙箱验证" } ], "subtitle": "The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.", "title": "mcp-use 能力包", "trial_prompt": "# mcp-use - Prompt Preview\n\n> Copy the prompt below into your AI host before installing anything.\n> Its purpose is to let you safely feel the project's workflow, not to claim the project has already run.\n\n## Copy this prompt\n\n```text\nYou are using an independent Doramagic capability pack for mcp-use/mcp-use.\n\nProject:\n- Name: mcp-use\n- Repository: https://github.com/mcp-use/mcp-use\n- Summary: The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.\n- Host target: mcp_host, claude_code, claude, chatgpt\n\nGoal:\nHelp me evaluate this project for the following task without installing it yet: The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.\n\nBefore taking action:\n1. Restate my task, success standard, and boundary.\n2. Identify whether the next step requires tools, browser access, network access, filesystem access, credentials, package installation, or host configuration.\n3. Use only the Doramagic Project Pack, the upstream repository, and the source-linked evidence listed below.\n4. If a real command, install step, API call, file write, or host integration is required, mark it as \"requires post-install verification\" and ask for approval first.\n5. If evidence is missing, say \"evidence is missing\" instead of filling the gap.\n\nPreviewable capabilities:\n- Capability 1: Use the source-backed project context to guide one small, checkable workflow step.\n\nCapabilities that require post-install verification:\n- Capability 1: Use the source-backed project context to guide one small, checkable workflow step.\n- Capability 2: Use the source-backed project context to guide one small, checkable workflow step.\n\nCore service flow:\n1. page-1: Framework Overview and Architecture. Produce one small intermediate artifact and wait for confirmation.\n2. page-2: Building MCP Servers and Widgets (MCP Apps). Produce one small intermediate artifact and wait for confirmation.\n3. page-3: MCP Client, Agents, and LLM Adapters. Produce one small intermediate artifact and wait for confirmation.\n4. page-4: Inspector, CLI, Authentication, and Deployment. Produce one small intermediate artifact and wait for confirmation.\n\nSource-backed evidence to keep in mind:\n- https://github.com/mcp-use/mcp-use\n- https://github.com/mcp-use/mcp-use#readme\n- skills/chatgpt-app-builder/SKILL.md\n- skills/mcp-apps-builder/SKILL.md\n- skills/mcp-builder/SKILL.md\n- skills/openapi-to-mcp/SKILL.md\n- README.md\n- libraries/typescript/package.json\n- libraries/python/pyproject.toml\n- libraries/typescript/packages/mcp-use/src/server/mcp-server.ts\n\nFirst response rules:\n1. Start Step 1 only.\n2. Explain the one service action you will perform first.\n3. Ask exactly three questions about my target workflow, success standard, and sandbox boundary.\n4. Stop and wait for my answers.\n\nStep 1 follow-up protocol:\n- After I answer the first three questions, stay in Step 1.\n- Produce six parts only: clarified task, success standard, boundary conditions, two or three options, tradeoffs for each option, and one recommendation.\n- End by asking whether I confirm the recommendation.\n- Do not move to Step 2 until I explicitly confirm.\n\nConversation rules:\n- Advance one step at a time and wait for confirmation after each small artifact.\n- Write outputs as recommendations or planned checks, not as completed execution.\n- Do not claim tests passed, files changed, commands ran, APIs were called, or the project was installed.\n- If the user asks for execution, first provide the sandbox setup, expected output, rollback, and approval checkpoint.\n```\n", "voices": [ { "body": "来源平台：github。github/github_issue: Refactor: adaptor deduplicate across MCP adapters（https://github.com/mcp-use/mcp-use/issues/1726）；github/github_issue: Confusing Logs for empty `resources/` folder（https://github.com/mcp-use/mcp-use/issues/1727）；github/github_issue: Refactor: adaptor deduplicate across MCP adapters（https://github.com/mcp-use/mcp-use/issues/1726）；github/github_issue: Stateful StreamableHTTP transport hangs in mcp-use dev — tool result nev（https://github.com/mcp-use/mcp-use/issues/1724）；github/github_issue: fix(cli): send unsubscribe on Ctrl+C in resources subscribe（https://github.com/mcp-use/mcp-use/issues/1723）；github/github_issue: Example: Chart Library MCP for financial pattern analysis（https://github.com/mcp-use/mcp-use/issues/1286）；github/github_issue: Refactor HttpConnector and StdioConnector with per-connector configurati（https://github.com/mcp-use/mcp-use/issues/947）；github/github_release: mcp-use 1.32.1-canary.2（https://github.com/mcp-use/mcp-use/releases/tag/mcp-use%401.32.1-canary.2）；github/github_release: @mcp-use/inspector 10.0.1-canary.2（https://github.com/mcp-use/mcp-use/releases/tag/%40mcp-use/inspector%4010.0.1-canary.2）；github/github_release: @mcp-use/cli 3.5.2-canary.2（https://github.com/mcp-use/mcp-use/releases/tag/%40mcp-use/cli%403.5.2-canary.2）；github/github_release: mcp-use 1.32.1-canary.1（https://github.com/mcp-use/mcp-use/releases/tag/mcp-use%401.32.1-canary.1）；github/github_release: mcp-use 1.32.0（https://github.com/mcp-use/mcp-use/releases/tag/mcp-use%401.32.0）。这些是项目级外部声音，不作为单独质量证明。", "items": [ { "kind": "github_issue", "source": "github", "title": "Refactor: adaptor deduplicate across MCP adapters", "url": "https://github.com/mcp-use/mcp-use/issues/1726" }, { "kind": "github_issue", "source": "github", "title": "Confusing Logs for empty `resources/` folder", "url": "https://github.com/mcp-use/mcp-use/issues/1727" }, { "kind": "github_issue", "source": "github", "title": "Refactor: adaptor deduplicate across MCP adapters", "url": "https://github.com/mcp-use/mcp-use/issues/1726" }, { "kind": "github_issue", "source": "github", "title": "Stateful StreamableHTTP transport hangs in mcp-use dev — tool result nev", "url": "https://github.com/mcp-use/mcp-use/issues/1724" }, { "kind": "github_issue", "source": "github", "title": "fix(cli): send unsubscribe on Ctrl+C in resources subscribe", "url": "https://github.com/mcp-use/mcp-use/issues/1723" }, { "kind": "github_issue", "source": "github", "title": "Example: Chart Library MCP for financial pattern analysis", "url": "https://github.com/mcp-use/mcp-use/issues/1286" }, { "kind": "github_issue", "source": "github", "title": "Refactor HttpConnector and StdioConnector with per-connector configurati", "url": "https://github.com/mcp-use/mcp-use/issues/947" }, { "kind": "github_release", "source": "github", "title": "mcp-use 1.32.1-canary.2", "url": "https://github.com/mcp-use/mcp-use/releases/tag/mcp-use%401.32.1-canary.2" }, { "kind": "github_release", "source": "github", "title": "@mcp-use/inspector 10.0.1-canary.2", "url": "https://github.com/mcp-use/mcp-use/releases/tag/%40mcp-use/inspector%4010.0.1-canary.2" }, { "kind": "github_release", "source": "github", "title": "@mcp-use/cli 3.5.2-canary.2", "url": "https://github.com/mcp-use/mcp-use/releases/tag/%40mcp-use/cli%403.5.2-canary.2" }, { "kind": "github_release", "source": "github", "title": "mcp-use 1.32.1-canary.1", "url": "https://github.com/mcp-use/mcp-use/releases/tag/mcp-use%401.32.1-canary.1" }, { "kind": "github_release", "source": "github", "title": "mcp-use 1.32.0", "url": "https://github.com/mcp-use/mcp-use/releases/tag/mcp-use%401.32.0" } ], "status": "已收录 12 条来源", "title": "社区讨论" } ] }, "homepage_card": { "category": "工具连接与集成", "desc": "The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.", "effort": "安装已验证", "forks": 1329, "icon": "link", "name": "mcp-use 能力包", "risk": "可发布", "slug": "mcp-use", "stars": 10098, "tags": [ "MCP 工具", "工具接入扩展", "项目能力包", "可验证工作流", "证据化上下文" ], "thumb": "gray", "type": "MCP 配置" }, "manual": { "markdown": "", "markdown_key": "mcp-use", "pages": "draft", "source_refs": [ { "evidence_id": "github_repo:956472076", "kind": "repo", "supports_claim_ids": [ "claim_identity", "claim_distribution", "claim_capability" ], "url": "https://github.com/mcp-use/mcp-use" }, { "evidence_id": "art_94de520ecb9b443fa15dd9b37173109d", "kind": "docs", "supports_claim_ids": [ "claim_identity", "claim_distribution", "claim_capability" ], "url": "https://github.com/mcp-use/mcp-use#readme" } ], "summary": "Full DeepWiki/Human Wiki output with Doramagic pitfall notes appended.", "title": "mcp-use Manual", "toc": [ "https://github.com/mcp-use/mcp-use Project Manual", "Table of Contents", "Framework Overview and Architecture", "Repository Structure", "High-Level Architecture", "Server Framework (TypeScript)", "Development Workflow", "Agent Runtime (Python)", "Pitfall Log" ] } }, "quality_gate": { "blocking_gaps": [], "category_confidence": "medium", "compile_status": "ready_for_review", "five_assets_present": true, "install_sandbox_verified": true, "missing_evidence": [], "next_action": "publish to Doramagic.ai project surfaces", "prompt_preview_boundary_ok": true, "publish_status": "publishable", "quick_start_verified": true, "repo_clone_verified": true, "repo_commit": "385e9fca8cdd783b4d7f2d7539b2441ef3ce6f27", "repo_inspection_error": null, "repo_inspection_files": [ "README.md", "docs/generate_docs.py", "docs/docs.json", "docs/README.md", "docs/context7.json", "docs/CLAUDE.md", "docs/snippets/snippet-intro.mdx", "docs/snippets/youtube-embed.mdx", "docs/home/index.mdx", "docs/home/templates.mdx", "docs/home/mcp101.mdx", "docs/inspector/cli.mdx", "docs/inspector/rpc-logging.mdx", "docs/inspector/command-palette.mdx", "docs/inspector/index.mdx", "docs/inspector/connection-settings.mdx", "docs/inspector/changelog.mdx", "docs/inspector/debugging-chatgpt-apps.mdx", "docs/inspector/integration.mdx", "docs/inspector/development.mdx", "docs/inspector/url-parameters.mdx", "docs/inspector/keyboard-shortcuts.mdx", "docs/inspector/self-hosting.mdx", "docs/typescript/context7.json", "docs/tunneling/index.mdx", "docs/guides/chatgpt-apps-flow.mdx", "docs/home/redirects/inspector.mdx", "docs/home/redirects/python.mdx", "docs/home/redirects/tunneling.mdx", "docs/home/redirects/typescript.mdx", "docs/python/changelog/1_3_11.mdx", "docs/python/changelog/1_3_13.mdx", "docs/python/changelog/1_3_12.mdx", "docs/python/changelog/1_4_1.mdx", "docs/python/changelog/1_4_0.mdx", "docs/python/changelog/changelog.mdx", "docs/python/changelog/1_6_0.mdx", "docs/python/changelog/1_5_2.mdx", "docs/python/changelog/1_7_0.mdx", "docs/python/changelog/1_5_0.mdx" ], "repo_inspection_verified": true, "review_reasons": [], "tag_count_ok": true, "unsupported_claims": [] }, "schema_version": "0.1", "user_assets": { "ai_context_pack": { "asset_id": "ai_context_pack", "filename": "AI_CONTEXT_PACK.md", "markdown": "# mcp-use - Doramagic AI Context Pack\n\n> Purpose: pre-work context for the user's host AI. This pack does not prove that the project has been installed, run, or validated.\n\n## Project\n\n- canonical_name: `mcp-use/mcp-use`\n- capability: The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.\n- expected_user_outcome: The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.\n\n## Operating Boundaries\n\n- Do not claim that the project has been installed, run, called through an API, or used on local files unless separate evidence proves it.\n- Project facts must come from repo evidence, Claim Graph, or explicit source references.\n- When a capability is not verified, mark it as unverified instead of completing it as fact.\n- publish_status: `publishable`\n- blocking_gaps: none\n\n---\n\n## Doramagic Context Augmentation\n\nThe following sections strengthen the repository context for a host AI. Human Manual data is a reading route, and pitfall notes become operating constraints.\n\n## Human Manual Outline\n\nUsage rule: this is only a reading route and salience signal, not factual authority. Concrete claims must still return to repo evidence or Claim Graph.\n\nHost AI hard rules:\n- Do not treat page titles, section order, summaries, or importance values as factual project evidence.\n- When explaining the Human Manual outline, state that it is only a reading route or salience signal.\n- Capability, installation, compatibility, runtime state, and risk claims must cite repo evidence, source paths, or Claim Graph.\n\n- **Framework Overview and Architecture**: importance `high`\n - source_paths: README.md, libraries/typescript/package.json, libraries/python/pyproject.toml, libraries/typescript/packages/mcp-use/src/server/mcp-server.ts, libraries/python/mcp_use/server/server.py\n- **Building MCP Servers and Widgets (MCP Apps)**: importance `high`\n - source_paths: libraries/typescript/packages/mcp-use/src/server/index.ts, libraries/typescript/packages/mcp-use/src/server/tools/tool-registration.ts, libraries/typescript/packages/mcp-use/src/server/resources/index.ts, libraries/typescript/packages/mcp-use/src/server/widgets/mount-widgets-dev.ts, libraries/typescript/packages/mcp-use/src/react/useWidget.ts\n- **MCP Client, Agents, and LLM Adapters**: importance `high`\n - source_paths: libraries/typescript/packages/mcp-use/src/client.ts, libraries/typescript/packages/mcp-use/src/agents/mcp_agent.ts, libraries/typescript/packages/mcp-use/src/managers/server_manager.ts, libraries/typescript/packages/mcp-use/src/adapters/base.ts, libraries/python/mcp_use/client/client.py\n- **Inspector, CLI, Authentication, and Deployment**: importance `high`\n - source_paths: libraries/typescript/packages/inspector/src/client/App.tsx, libraries/typescript/packages/inspector/src/server/server.ts, libraries/typescript/packages/cli/src/index.ts, libraries/typescript/packages/cli/src/commands/deploy.ts, libraries/typescript/packages/cli/src/commands/servers.ts\n\n## Repo Inspection Evidence\n\n- repo_clone_verified: true\n- repo_inspection_verified: true\n- repo_commit: `385e9fca8cdd783b4d7f2d7539b2441ef3ce6f27`\n- inspected_files: `README.md`, `docs/generate_docs.py`, `docs/docs.json`, `docs/README.md`, `docs/context7.json`, `docs/CLAUDE.md`, `docs/snippets/snippet-intro.mdx`, `docs/snippets/youtube-embed.mdx`, `docs/home/index.mdx`, `docs/home/templates.mdx`, `docs/home/mcp101.mdx`, `docs/inspector/cli.mdx`, `docs/inspector/rpc-logging.mdx`, `docs/inspector/command-palette.mdx`, `docs/inspector/index.mdx`, `docs/inspector/connection-settings.mdx`, `docs/inspector/changelog.mdx`, `docs/inspector/debugging-chatgpt-apps.mdx`, `docs/inspector/integration.mdx`, `docs/inspector/development.mdx`\n\nHost AI hard rules:\n- Without repo_clone_verified=true, do not claim that the source code has been read.\n- Without repo_inspection_verified=true, do not write README, docs, or package-file conclusions as facts.\n- Without quick_start_verified=true, do not claim that the Quick Start path has run successfully.\n\n## Doramagic Pitfall Constraints\n\nThese rules come from Doramagic discovery, validation, or compilation findings. The host AI must treat them as operating constraints, not background notes.\n\n### Constraint 1: Installation risk requires verification\n\n- Trigger: Project evidence flags a installation risk. Review the linked source before relying on this workflow.\n- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.\n- Why it matters: May increase setup, validation, or first-run risk for the user.\n- Evidence: community_evidence:github | https://github.com/mcp-use/mcp-use/issues/1727\n- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.\n\n### Constraint 2: Installation risk requires verification\n\n- Trigger: Project evidence flags a installation risk. Review the linked source before relying on this workflow.\n- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.\n- Why it matters: May increase setup, validation, or first-run risk for the user.\n- Evidence: community_evidence:github | https://github.com/mcp-use/mcp-use/issues/1726\n- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.\n\n### Constraint 3: Configuration risk requires verification\n\n- Trigger: Project evidence flags a configuration risk. Review the linked source before relying on this workflow.\n- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.\n- Why it matters: May increase setup, validation, or first-run risk for the user.\n- Evidence: community_evidence:github | https://github.com/mcp-use/mcp-use/issues/1724\n- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.\n\n### Constraint 4: Security or permission risk requires verification\n\n- Trigger: Project evidence flags a security or permission risk. Review the linked source before relying on this workflow.\n- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.\n- Why it matters: May increase setup, validation, or first-run risk for the user.\n- Evidence: community_evidence:github | https://github.com/mcp-use/mcp-use/issues/947\n- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.\n\n### Constraint 5: Installation risk requires verification\n\n- Trigger: Developers should check this installation risk before relying on the project: Example: Chart Library MCP for financial pattern analysis\n- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: Example: Chart Library MCP for financial pattern analysis. Context: Observed when using python\n- Why it matters: Developers may fail before the first successful local run: Example: Chart Library MCP for financial pattern analysis\n- Evidence: failure_mode_cluster:github_issue | https://github.com/mcp-use/mcp-use/issues/1286\n- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.\n\n### Constraint 6: Installation risk requires verification\n\n- Trigger: Project evidence flags a installation risk. Review the linked source before relying on this workflow.\n- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.\n- Why it matters: May increase setup, validation, or first-run risk for the user.\n- Evidence: community_evidence:github | https://github.com/mcp-use/mcp-use/issues/1286\n- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.\n\n### Constraint 7: Configuration risk requires verification\n\n- Trigger: Project evidence flags a configuration risk. Review the linked source before relying on this workflow.\n- Host AI rule: Reproduce the official install and quickstart path in an isolated environment.\n- Why it matters: May increase setup, validation, or first-run risk for the user.\n- Evidence: capability.host_targets | github_repo:956472076 | https://github.com/mcp-use/mcp-use\n- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.\n\n### Constraint 8: Configuration risk requires verification\n\n- Trigger: Developers should check this configuration risk before relying on the project: @mcp-use/cli 3.5.0\n- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: @mcp-use/cli 3.5.0. Context: Source discussion did not expose a precise runtime context.\n- Why it matters: Upgrade or migration may change expected behavior: @mcp-use/cli 3.5.0\n- Evidence: failure_mode_cluster:github_release | https://github.com/mcp-use/mcp-use/releases/tag/%40mcp-use/cli%403.5.0\n- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.\n\n### Constraint 9: Configuration risk requires verification\n\n- Trigger: Developers should check this configuration risk before relying on the project: Refactor HttpConnector and StdioConnector with per-connector configuration\n- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: Refactor HttpConnector and StdioConnector with per-connector configuration. Context: Observed when using python, playwright\n- Why it matters: Developers may misconfigure credentials, environment, or host setup: Refactor HttpConnector and StdioConnector with per-connector configuration\n- Evidence: failure_mode_cluster:github_issue | https://github.com/mcp-use/mcp-use/issues/947\n- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.\n\n### Constraint 10: Configuration risk requires verification\n\n- Trigger: Developers should check this configuration risk before relying on the project: mcp-use 1.32.0\n- Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: mcp-use 1.32.0. Context: Source discussion did not expose a precise runtime context.\n- Why it matters: Upgrade or migration may change expected behavior: mcp-use 1.32.0\n- Evidence: failure_mode_cluster:github_release | https://github.com/mcp-use/mcp-use/releases/tag/mcp-use%401.32.0\n- Hard boundary: Do not present this pitfall as solved, verified, or ignorable unless later evidence explicitly closes it.\n", "summary": "Context and operating boundaries for the user's host AI.", "title": "AI Context Pack" }, "boundary_risk_card": { "asset_id": "boundary_risk_card", "filename": "BOUNDARY_RISK_CARD.md", "markdown": "# Boundary & Risk Card\n\nProject: mcp-use/mcp-use\n\n## Doramagic Trial Decision\n\nCurrent decision: ready for pre-publication recommendation checks. First use should still start with least privilege, a temporary directory, and rollback.\n\n## What The User Can Do Now\n\n- Read the Human Manual first to understand purpose and main workflows.\n- Copy the Prompt Preview for a pre-install trial. This checks interaction feel, not real execution.\n- Test the official Quick Start command in an isolated environment before using a primary machine.\n\n## What Not To Do Yet\n\n- Do not treat Prompt Preview output as an actual project run.\n- Do not treat metadata-only validation as sandbox install validation.\n- Do not write unverified capabilities as supported, tested, or safe to install.\n- Do not provide production data, private files, real secrets, or primary configuration directories on first use.\n\n## Pre-install Checklist\n\n- Host AI match: mcp_host, claude_code, claude, chatgpt, cursor\n- Official install entry state: official entry found\n- Verification location: temporary directory, temporary host, or container required\n- Rollback readiness: required\n- API keys, network access, file writes, or host configuration changes: treat as high risk until confirmed\n- Install command, actual output, and failure logs: must be recorded\n\n## Current Blockers\n\n- No blockers.\n\n## Project-specific Pitfalls\n\n- Installation risk requires verification (high): May increase setup, validation, or first-run risk for the user. Suggested check: Reproduce the official install and quickstart path in an isolated environment.\n- Installation risk requires verification (high): May increase setup, validation, or first-run risk for the user. Suggested check: Reproduce the official install and quickstart path in an isolated environment.\n- Configuration risk requires verification (high): May increase setup, validation, or first-run risk for the user. Suggested check: Reproduce the official install and quickstart path in an isolated environment.\n- Security or permission risk requires verification (high): May increase setup, validation, or first-run risk for the user. Suggested check: Reproduce the official install and quickstart path in an isolated environment.\n- Installation risk requires verification (medium): Developers may fail before the first successful local run: Example: Chart Library MCP for financial pattern analysis Suggested check: Before packaging this project, run the relevant install/config/quickstart check for: Example: Chart Library MCP for financial pattern analysis. Context: Observed when using python\n\n## Risk And Permission Notes\n\n- no_demo: medium\n\n## Evidence Gaps\n\n- No structured evidence gaps found.\n", "summary": "Install, permission, validation, and recommendation risks.", "title": "Boundary & Risk Card" }, "human_manual": { "asset_id": "human_manual", "filename": "HUMAN_MANUAL.md", "markdown": "", "summary": "Full DeepWiki/Human Wiki output with Doramagic pitfall notes appended.", "title": "Human Manual" }, "pitfall_log": { "asset_id": "pitfall_log", "filename": "PITFALL_LOG.md", "markdown": "", "summary": "Identity, install, configuration, runtime, and safety issues to check before use.", "title": "Pitfall Log" }, "prompt_preview": { "asset_id": "prompt_preview", "filename": "PROMPT_PREVIEW.md", "markdown": "# mcp-use - Prompt Preview\n\n> Copy the prompt below into your AI host before installing anything.\n> Its purpose is to let you safely feel the project's workflow, not to claim the project has already run.\n\n## Copy this prompt\n\n```text\nYou are using an independent Doramagic capability pack for mcp-use/mcp-use.\n\nProject:\n- Name: mcp-use\n- Repository: https://github.com/mcp-use/mcp-use\n- Summary: The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.\n- Host target: mcp_host, claude_code, claude, chatgpt\n\nGoal:\nHelp me evaluate this project for the following task without installing it yet: The fullstack MCP framework to develop MCP Apps for ChatGPT / Claude & MCP Servers for AI Agents.\n\nBefore taking action:\n1. Restate my task, success standard, and boundary.\n2. Identify whether the next step requires tools, browser access, network access, filesystem access, credentials, package installation, or host configuration.\n3. Use only the Doramagic Project Pack, the upstream repository, and the source-linked evidence listed below.\n4. If a real command, install step, API call, file write, or host integration is required, mark it as \"requires post-install verification\" and ask for approval first.\n5. If evidence is missing, say \"evidence is missing\" instead of filling the gap.\n\nPreviewable capabilities:\n- Capability 1: Use the source-backed project context to guide one small, checkable workflow step.\n\nCapabilities that require post-install verification:\n- Capability 1: Use the source-backed project context to guide one small, checkable workflow step.\n- Capability 2: Use the source-backed project context to guide one small, checkable workflow step.\n\nCore service flow:\n1. page-1: Framework Overview and Architecture. Produce one small intermediate artifact and wait for confirmation.\n2. page-2: Building MCP Servers and Widgets (MCP Apps). Produce one small intermediate artifact and wait for confirmation.\n3. page-3: MCP Client, Agents, and LLM Adapters. Produce one small intermediate artifact and wait for confirmation.\n4. page-4: Inspector, CLI, Authentication, and Deployment. Produce one small intermediate artifact and wait for confirmation.\n\nSource-backed evidence to keep in mind:\n- https://github.com/mcp-use/mcp-use\n- https://github.com/mcp-use/mcp-use#readme\n- skills/chatgpt-app-builder/SKILL.md\n- skills/mcp-apps-builder/SKILL.md\n- skills/mcp-builder/SKILL.md\n- skills/openapi-to-mcp/SKILL.md\n- README.md\n- libraries/typescript/package.json\n- libraries/python/pyproject.toml\n- libraries/typescript/packages/mcp-use/src/server/mcp-server.ts\n\nFirst response rules:\n1. Start Step 1 only.\n2. Explain the one service action you will perform first.\n3. Ask exactly three questions about my target workflow, success standard, and sandbox boundary.\n4. Stop and wait for my answers.\n\nStep 1 follow-up protocol:\n- After I answer the first three questions, stay in Step 1.\n- Produce six parts only: clarified task, success standard, boundary conditions, two or three options, tradeoffs for each option, and one recommendation.\n- End by asking whether I confirm the recommendation.\n- Do not move to Step 2 until I explicitly confirm.\n\nConversation rules:\n- Advance one step at a time and wait for confirmation after each small artifact.\n- Write outputs as recommendations or planned checks, not as completed execution.\n- Do not claim tests passed, files changed, commands ran, APIs were called, or the project was installed.\n- If the user asks for execution, first provide the sandbox setup, expected output, rollback, and approval checkpoint.\n```\n", "summary": "A safe trial prompt for feeling the workflow before installing the project.", "title": "Prompt Preview / Pre-install Trial Prompt" }, "quick_start": { "asset_id": "quick_start", "filename": "QUICK_START.md", "markdown": "# Quick Start / Official Entry\n\nProject: mcp-use/mcp-use\n\n## Official Install Entry\n\n### Node.js / npx - Official install entry\n\n```bash\nnpx create-mcp-use-app@latest\n```\n\nSource: https://github.com/mcp-use/mcp-use#readme\n\n## Sources\n\n- repo: https://github.com/mcp-use/mcp-use\n- docs: https://github.com/mcp-use/mcp-use#readme\n", "summary": "Official entry points extracted from the project README or install docs.", "title": "Quick Start / Official Entry" } }, "validation_id": "dval_9dfeba3e5c6a4f53b5b8ce53d53128ce" }