{ "run_id": "mcp-use--mcp-use-claude-haiku-5-5-1792767269192623503", "date": "2026-10-23T15:09:35.968911+00:00", "repo": "mcp-use/mcp-use", "kind": "mcp", "source": "https://github.com/mcp-use/mcp-use", "commit": "f877f789e7b4979e62e5cbe221bfb29ebb86d1bd", "model": "claude-haiku-5-5", "model_version": "claude-haiku-5-5", "test_version": "readme-bdc1b9b3c0d2673aef87e076d14084a8123ddcf09d520c1ee2e364a37c3f4bb9", "pass": true, "outcome": "pass", "time_to_working_s": 827.4348083219957, "total_s": 906.7762579917908, "steps": [ "cd && pwd && ls -la && id -u && python3 --version && cat /etc/os-release | head -3 && git --version 2>&1; ls /inputs 2>&1; ls 2>&1", "cd && cat README.md | head -300", "cd && which node npm npx; node -v 2>&1; npm -v 2>&1; ls -la .coldpass; ls libraries examples; grep -n -i \"node\\|requir\\|prereq\" README.md | head -40; find . -name package.json -not -path \"*/node_modules/*\" | head -30", "cd && ls; grep -n '\"engines\"' -A3 package.json; grep -n '\"packageManager\"\\|\"node\"' package.json; grep -n -i \"node\\|npm\\|pnpm\" README.md | head -30; cat package.json | head -60", "cd && grep -rn '\"node\"' package.json packages/server/package.json packages/create-mcp-use-app/package.json packages/client/package.json 2>/dev/null; grep -n -i \"node.js\\|node 2\\|node>=\\|>= *2\" README.md ../../CONTRIBUTING.md | head; sudo -n true && echo SUDO_OK; apt-cache policy nodejs 2>/dev/null | head -3; curl -sI https://deb.nodesource.com 2>&1 | head -1", "cd /tmp && (curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash - && sudo apt-get install -y nodejs) > /tmp/node_install.log 2>&1; echo rc=$?; tail -5 /tmp/node_install.log; node -v; npm -v", "cd && git init -q && git remote add origin https://github.com/mcp-use/mcp-use && git fetch --depth 1 origin f877f789e7b4979e62e5cbe221bfb29ebb86d1bd 2>&1 | tail -3; git reset --mixed FETCH_HEAD 2>&1 | tail -2; git log --oneline -1; git status --short | head -5", "cd && sudo npm install -g pnpm@11.13.1 > /tmp/pnpm_install.log 2>&1; echo rc=$?; tail -3 /tmp/pnpm_install.log; pnpm -v; export NODE_USE_ENV_PROXY=1; timeout 900 pnpm install --frozen-lockfile > /tmp/pnpm_i.log 2>&1; echo install_rc=$?; tail -15 /tmp/pnpm_i.log", "cd && sed -n 645,665p README.md; export NODE_USE_ENV_PROXY=1; timeout 1500 pnpm build > /tmp/pnpm_build.log 2>&1; echo build_rc=$?; tail -12 /tmp/pnpm_build.log", "mkdir -p /tmp/mcpdemo && cd /tmp/mcpdemo && export NODE_USE_ENV_PROXY=1 && timeout 300 npx -y create-mcp-use-app@latest --help 2>&1 | head -40; echo rc=$?", "cd /tmp/mcpdemo && export NODE_USE_ENV_PROXY=1 && timeout 900 npx -y create-mcp-use-app@latest weather-app --npm --install --no-skills > /tmp/scaffold.log 2>&1; echo rc=$?; tail -20 /tmp/scaffold.log; ls -la /tmp/mcpdemo/weather-app 2>&1 | head -30", "cd /tmp/mcpdemo/weather-app && cat index.ts; echo ----; cat package.json; echo ----; export NODE_USE_ENV_PROXY=1; timeout 600 npm run build > /tmp/app_build.log 2>&1; echo build_rc=$?; tail -8 /tmp/app_build.log", "cd /tmp/mcpdemo/weather-app && export NODE_USE_ENV_PROXY=1; nohup npm run dev > /tmp/app_dev.log 2>&1 & echo started; sleep 25; tail -20 /tmp/app_dev.log; curl -s -o /dev/null -w \"%{http_code}\\n\" http://localhost:3000/mcp", "cd /tmp/mcpdemo/weather-app && export NODE_USE_ENV_PROXY=1; timeout 120 npx mcp-use client connect local http://localhost:3000/mcp 2>&1 | tail -5; echo connect_rc=$?; timeout 120 npx mcp-use client local tools list 2>&1 | tail -15; timeout 120 npx mcp-use client local tools call fetch-weather city=Tokyo 2>&1 | tail -15", "pkill -f \"mcp-use dev\" ; pkill -f \"npm run dev\"; sleep 3; (curl -s -o /dev/null -w \"%{http_code}\\n\" http://localhost:3000/mcp || true); pgrep -fa \"mcp-use|npm run dev\" | head; cd && grep -rln -i \"cron\\|setInterval\\|--once\\|--now\\|schedule\" packages/*/src 2>/dev/null | head -20; grep -n \"^Start development mode\\|^Inspect the same server\\|^Create the production build\" ", "ps -eo pid,args | grep -E \"mcp-use|vite|tsx|node\" | grep -v grep | head; curl -s -o /dev/null -w \"%{http_code}\\n\" http://localhost:3000/mcp; echo done", "cd && grep -rln -i \"cron\\|setInterval\\|--once\\|--now\" packages/*/src 2>/dev/null | head -10; echo ---; cd && grep -n \"Start development mode\\|Inspect the same server\\|Create the production build\" README.md; grep -n \"npx mcp-use client connect\" README.md", "cd /tmp/mcpdemo && export NODE_USE_ENV_PROXY=1 && timeout 300 npx -y create-mcp-use-app@latest --list-templates 2>/dev/null | head -20; echo rc=$?; cd && grep -n '\"test\"' package.json; (timeout 900 pnpm test > /tmp/server_test.log 2>&1; echo test_rc=$? >> /tmp/server_test.log) ; tail -12 /tmp/server_test.log", "cd && mkdir -p .coldpass && cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"mcp_http\",\"argv\":[\"npm\",\"run\",\"dev\"],\"cwd\":\"/tmp/mcpdemo/weather-app\",\"url\":\"http://localhost:3000/mcp\",\"tool\":\"fetch-weather\",\"arguments\":{\"city\":\"Tokyo\"},\"expected_text\":\"sunny\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[\n {\"kind\":\"claim\",\"claim\":\"Start development mode serves the MCP endpoint at localhost:3000/mcp and a tool call returns the requested city's weather\",\"source\":\"Start development mode to serve the MCP endpoint at [`http://localhost:3000/mcp`](http://localhost:3000/mcp). The Inspector is automatically available at [`http://localhost:3000/mcp/inspector`](http://localhost:3000/mcp/inspector):\",\"input\":\"fetch-weather city=Tokyo\",\"expected\":\"sunny weather result for Tokyo\",\"probe_kind\":\"mcp_http\",\"argv\":[\"npm\",\"run\",\"dev\"],\"url\":\"http://localhost:3000/mcp\",\"tool\":\"fetch-weather\",\"arguments\":{\"city\":\"Tokyo\"},\"expected_text\":\"sunny\",\"cwd\":\"/tmp/mcpdemo/weather-app\"},\n {\"kind\":\"claim\",\"claim\":\"Create the production build runs and reports the built entry\",\"source\":\"Create the production build:\",\"input\":\"npm run build\",\"expected\":\"build output names the built index.ts entry\",\"probe_kind\":\"cli\",\"argv\":[\"npm\",\"run\",\"build\"],\"expected_text\":\"built index.ts\",\"cwd\":\"/tmp/mcpdemo/weather-app\"}\n]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[\n {\"kind\":\"example\",\"claim\":\"Scaffold a new project with the quickstart tool and list its templates\",\"source\":\"README.md Start with code (npx -y create-mcp-use-app@latest)\",\"input\":\"--list-templates\",\"expected\":\"lists the blank, mcp-apps and mcp-server templates\",\"argv\":[\"npx\",\"-y\",\"create-mcp-use-app@latest\",\"--list-templates\"],\"cwd\":\"/tmp/mcpdemo\",\"env\":{},\"expected_text\":\"mcp-server\"},\n {\"kind\":\"example\",\"claim\":\"Repository offline test suite for the server package passes\",\"source\":\"libraries/typescript/README.md Development Setup\",\"input\":\"pnpm test in libraries/typescript/packages/server\",\"expected\":\"all server tests pass\",\"argv\":[\"pnpm\",\"test\"],\"cwd\":\"\",\"env\":{},\"expected_text\":\"859 passed\"}\n]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"Entry points inspected: packages/cli, packages/server, packages/client and packages/tunnel. Grep for cron, setInterval, --once and --now found only UI or polling timers (views-plugin, useMcp-helpers, popup, ToolResultDisplay, PromptResultDisplay, useChatHistory, manufact-auth, tunnel index). No scheduler or product cycle exists; the product runs on demand via npm run dev (HTTP server) and npx mcp-use client commands.\",\"checks\":[]}\nEOF\nfor f in .coldpass/*.json; do python3 -I -m json.tool \"$f\" >/dev/null && echo \"ok $f\"; done; ls -la .coldpass", "cd && = timeout 1500 python3 -I --validate --replay; echo checker_rc=$?", "cd && (curl -s -o /dev/null -w \"port3000=%{http_code}\\n\" http://localhost:3000/mcp || true); ps -eo pid,args | grep -E \"mcp-use dev|npm run dev\" | grep -v grep || echo \"no server processes\"; cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Scaffold an mcp-use MCP server with the README quickstart, run the dev server, and call its fetch-weather tool over MCP HTTP\",\"operation_scope\":\"Linux Ubuntu 24.04 guest, Node 22.23.4, pnpm 11.13.1 for the monorepo, npm for the scaffolded project; local HTTP on localhost:3000 only; no credentials, browser or external services\",\"steps\":[\"git init; git remote add origin https://github.com/mcp-use/mcp-use; git fetch --depth 1 origin f877f789e7b4979e62e5cbe221bfb29ebb86d1bd; git reset --mixed FETCH_HEAD\",\"cd libraries/typescript && pnpm install --frozen-lockfile\",\"pnpm build (libraries/typescript)\",\"npx -y create-mcp-use-app@latest weather-app --npm --install --no-skills (run from /tmp/mcpdemo)\",\"npm run build (in /tmp/mcpdemo/weather-app)\",\"npm run dev (in /tmp/mcpdemo/weather-app)\",\"npx mcp-use client connect local http://localhost:3000/mcp\",\"npx mcp-use client local tools list\",\"npx mcp-use client local tools call fetch-weather city=Tokyo\",\"pnpm test (libraries/typescript/packages/server): 859 passed\"],\"deviations\":[\"Node was not installed in the guest; installed Node 22.23.4 via NodeSource (curl -fsSL https://deb.nodesource.com/setup_22.x | sudo -E bash -; sudo apt-get install -y nodejs) to meet the >=22.22.2 engine requirement.\",\"pnpm was not installed; installed pnpm@11.13.1 (the packageManager pin) with sudo npm install -g pnpm@11.13.1.\",\"pnpm install printed non-fatal WARN lines 'Failed to create bin' for unbuilt example packages (mcp-use bin missing before build); the install still completed and the build succeeded.\",\"The workspace had no .git; applied the task's pinned git init/fetch/reset steps.\",\"The probe and example commands use the scaffolded app in /tmp/mcpdemo/weather-app (outside the checkout) because the README quickstart uses the published create-mcp-use-app package via npx.\",\"Telemetry/consent prompts were not encountered in the non-interactive runs; no telemetry option was changed.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nEOF\npython3 -I -m json.tool .coldpass/report.json >/dev/null && echo report_ok; = timeout 1500 python3 -I --validate --replay > /tmp/final_check.json 2>&1; echo checker_rc=$?; python3 -I -c \"import json,sys; d=json.load(open('/tmp/final_check.json')) if False else None\" ; grep -o '\"valid\": [a-z]*\\|\"status\": \"[A-Z]*\"' /tmp/final_check.json | head" ], "stuck_step": null, "error_excerpt": null, "what_it_did": "Scaffold an mcp-use MCP server with the README quickstart, run the dev server, and call its fetch-weather tool over MCP HTTP", "suggested_fix": null, "tokens_in": 554688, "tokens_out": 15494, "cost_usd": 0.021549170000000003, "usage_complete": true, "checks": [ { "check": "operation", "status": "PASS", "details": { "working": true, "kind": "mcp_http", "url": "http://localhost:3000/mcp", "hosting": "local", "transport": "streamable-http", "scope": "remote hosted MCP initialize + tools/list", "argv": [ "npm", "run", "dev" ], "serverInfo": { "name": "weather-app", "version": "1.0.0", "title": "weather-app", "description": "An MCP server built with mcp-use" }, "protocolVersion": "2025-06-18", "tools": [ "fetch-weather" ], "tool_schema_bytes": 549, "tool_result": { "content": [ { "type": "text", "text": "{\"city\":\"Tokyo\",\"conditions\":\"sunny\",\"temperature\":\"22\u00b0C\"}" } ], "structuredContent": { "city": "Tokyo", "conditions": "sunny", "temperature": "22\u00b0C" } }, "tool_result_checked": true } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "Review signals: 1 connection review, 4 encoded blob, 5 hardcoded secret, 26 known vulnerability. 10 static matches retained as context.", "expected": "Reviewed as expected for a test run: resolver address lookups that send no data.", "findings": [ { "kind": "connection-review", "count": 1, "note": "Repository processes attempted these non-loopback connections; proxies can hide the final hostname.", "location_count": 3, "process_count": 7 }, { "kind": "encoded-blob", "count": 4, "note": "Source contains encoded blob; review its purpose.", "location_count": 2 }, { "kind": "hardcoded-secret", "count": 5, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 5 }, { "kind": "known-vulnerability", "count": 21, "note": "OSV reports a known vulnerability in this dependency version.", "location_count": 10 } ], "context": [ { "kind": "hardcoded-secret", "count": 10, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 6 } ], "limitations": [ "A short run cannot establish that code is safe.", "Connections show IP addresses; proxies can hide the final hostname.", "Tracing covers dispatched commands and their children, not the whole OS; guest root can interfere with tracing." ], "static": { "dependency_note": "OSV scanned supported lockfiles; unpinned dependencies and unsupported formats are outside this check." }, "evidence_url": "/safety/?run=mcp-use--mcp-use-claude-haiku-5-5-1792767269192623503", "evidence_file": "/data/safety/mcp-use--mcp-use-claude-haiku-5-5-1792767269192623503.json.gz" }, "agent_execution": "native_agent", "agent_runtime": "claude-code", "agent_runtime_version": "2.1.300 (Claude Code)", "tool_transport": "mcp-assigned-vm", "platform": "linux", "reasoning": "low", "service_tier": null, "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "native_tool_calls": 21, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "f877f789e7b4979e62e5cbe221bfb29ebb86d1bd", "url": "https://github.com/mcp-use/mcp-use" }, "purpose": "initial", "profile": { "model": "claude-haiku-5-5", "reasoning": "low" }, "fault": { "owner": null, "status": "resolved", "reason": null }, "fix_id": null, "verifies_run_id": null, "hosting": "local", "operation_scope": "remote hosted MCP initialize + tools/list", "tool_calls": 21, "guest_setup": null, "runtime": null, "runtime_version": null, "runtime_revision": null, "source_revision": null, "evidence_version": null, "failure_origin": null, "evidence_strength": "readme_checked", "works": "yes", "install_s": null, "first_use_s": null, "mcp": "local", "needs": [], "needs_which": null, "agent_interface": [ "mcp" ], "license": "MIT", "repo_url": "https://github.com/mcp-use/mcp-use", "cost_to_try": "free", "hardware": null, "what_failed": null, "local_or_hosted": "local", "cycle_checks": [ { "kind": "cycle", "claim": "Scheduled or looping main behavior", "source": "repository entry points", "input": "source inspection", "expected": "identify the product trigger", "verdict": "yes", "outcome": "Entry points inspected: packages/cli, packages/server, packages/client and packages/tunnel. Grep for cron, setInterval, --once and --now found only UI or polling timers (views-plugin, useMcp-helpers, popup, ToolResultDisplay, PromptResultDisplay, useChatHistory, manufact-auth, tunnel index). No scheduler or product cycle exists; the product runs on demand via npm run dev (HTTP server) and npx mcp-use client commands.", "evidence": "Entry points inspected: packages/cli, packages/server, packages/client and packages/tunnel. Grep for cron, setInterval, --once and --now found only UI or polling timers (views-plugin, useMcp-helpers, popup, ToolResultDisplay, PromptResultDisplay, useChatHistory, manufact-auth, tunnel index). No scheduler or product cycle exists; the product runs on demand via npm run dev (HTTP server) and npx mcp-use client commands.", "command": "" } ], "claims": [ { "kind": "claim", "claim": "Start development mode serves the MCP endpoint at localhost:3000/mcp and a tool call returns the requested city's weather", "source": "Start development mode to serve the MCP endpoint at [`http://localhost:3000/mcp`](http://localhost:3000/mcp). The Inspector is automatically available at [`http://localhost:3000/mcp/inspector`](http://localhost:3000/mcp/inspector):", "input": "{\"tool\": \"fetch-weather\", \"arguments\": {\"city\": \"Tokyo\"}}", "expected": "sunny weather result for Tokyo", "command": "npm run dev tools/call {\"tool\": \"fetch-weather\", \"arguments\": {\"city\": \"Tokyo\"}}", "verdict": "yes", "outcome": "Real input produced the expected result: sunny", "evidence": "sunny\\\",\\\"temperature\\\":\\\"22\u00b0C\\\"}\"}], \"structuredContent\": {\"city\": \"Tokyo\", \"conditions\": \"sunny\", \"temperature\": \"22\u00b0C\"}}", "source_checked": true, "source_file": "README.md" }, { "kind": "claim", "claim": "Create the production build runs and reports the built entry", "source": "Create the production build:", "input": "npm run build", "expected": "build output names the built index.ts entry", "command": "npm run build", "verdict": "yes", "outcome": "Real input produced the expected result: built index.ts", "evidence": "built index.ts \u2192 .mcp-use/build/index.js (754ms)\n", "returncode": 0, "source_checked": true, "source_file": "README.md" } ], "claims_note": null, "example_checks": [ { "kind": "example", "claim": "Scaffold a new project with the quickstart tool and list its templates", "source": "README.md Start with code (npx -y create-mcp-use-app@latest)", "input": "--list-templates", "command": "npx -y create-mcp-use-app@latest --list-templates", "evidence": "\u2550\u255d \u001b[0m\n\u001b[1;37m \u2588\u2588\u2551 \u255a\u2550\u255d \u2588\u2588\u2551 \u255a\u2588\u2588\u2588\u2588\u2588\u2588\u2557 \u2588\u2588\u2551 \u255a\u2588\u2588\u2588\u2588\u2588\u2588\u2554\u255d \u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2551 \u2588\u2588\u2588\u2588\u2588\u2588\u2588\u2557\u001b[0m\n\u001b[1;37m \u255a\u2550\u255d \u255a\u2550\u255d \u255a\u2550\u2550\u2550\u2550\u2550\u255d \u255a\u2550\u255d \u255a\u2550\u2550\u2550\u2550\u2550\u255d \u255a\u2550\u2550\u2550\u2550\u2550\u2550\u255d \u255a\u2550\u2550\u2550\u2550\u2550\u2550\u255d\u001b[0m\n\n\u001b[90m\u001b[1m by Manufact\u001b[0m\u001b[0m\n\n\u001b[1mAvailable Templates:\u001b[0m\n\n\u001b[36m blank \u001b[0m \u001b[90ma minimal mcp-use server with no tools registered, ready to add your own\u001b[0m\n\u001b[36m mcp-apps \u001b[0m \u001b[90man mcp-use server with React views for MCP Apps\u001b[0m\n\u001b[36m mcp-server \u001b[0m \u001b[90man mcp-use server with example tools and zod validated input\u001b[0m\n\n\u001b[90m\ud83d\udca1 Use with: npx create-mcp-use-app my-project --template