{ "run_id": "jkudish--jev-mcp-gpt-6-luna-1792845533962590952", "date": "2026-10-24T12:48:51.166752+00:00", "repo": "jkudish/jev-mcp", "kind": "mcp", "source": "https://github.com/jkudish/jev-mcp", "commit": "6faa53961ade29edd0a9a2381ce74f84d64540b0", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "test_version": "readme-df4b35fa98302b0e4e98e2674b9b06ded355b64401f37cded16cfd580be506df", "pass": null, "outcome": "needs_credentials", "time_to_working_s": null, "total_s": 597.204108953476, "steps": [ "pwd; rg --files -g 'README*' -g 'AGENTS.md' -g 'pyproject.toml' -g 'package.json' -g 'requirements*' -g 'uv.lock' -g 'Makefile' -g '.github/workflows/*'; python3 --version; id -u; ls -la", "cat README.md; cat package.json; find src examples -maxdepth 3 -type f; git status --short --branch; node --version; npm --version", "sudo -n apt-get update && sudo -n apt-get install -y nodejs npm", "node -v; cd /tmp && npm view node@22 version --json", "cd /tmp && npm install --prefix node@22.23.4", "export PATH=; node -v; npm -v; cd && npm install && npm run build && npm test", "find -maxdepth 3 -type f -name 'check.py' -o -name 'coldpass-preflight.py'; env | cut -d= -f1 | sort | grep -E 'KEY|TOKEN|CDP' || true; sed -n '/^## When to call which tool/,$p' README.md | head -1; mkdir -p .coldpass; cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"mcp\",\"argv\":[\"\",\"\"],\"cwd\":\"\",\"tool\":\"jev_verify\",\"arguments\":{\"claims\":[\"The Earth orbits the Sun.\"],\"evidence\":{\"text\":\"The Earth orbits the Sun.\"}},\"expected_returncode\":-1,\"expected_text\":\"TYPESAFE_API_KEY\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Check claims against evidence\",\"source\":\"Check each claim in a report, PR description, or agent brief against the sources it cites.\",\"testable\":false,\"reason\":\"Provider credential required; no API key is present in the guest environment.\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"README development build\",\"source\":\"README.md#development\",\"input\":\"npm run build\",\"expected\":\"TypeScript build succeeds\",\"argv\":[\"\",\"run\",\"build\"],\"cwd\":\"\",\"env\":{\"PATH\":\"\"}}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"reason\":\"Inspected README and package scripts; this MCP server exposes request/response judgment tools and has no scheduler or cycle entry point.\",\"checks\":[]}\nEOF\n= python3 -I --validate --replay", "ls -l /usr/bin/npm; sed -n '1,240p' ", "cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"mcp\",\"argv\":[\"\",\"\"],\"cwd\":\"\",\"tool\":\"jev_verify\",\"arguments\":{\"claims\":[\"The Earth orbits the Sun.\"],\"evidence\":{\"text\":\"The Earth orbits the Sun.\"}},\"expected_text\":\"No TYPESAFE_API_KEY\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Check claims against evidence\",\"source\":\"Check each claim in a report, PR description, or agent brief against the sources it cites.\",\"testable\":false,\"reason\":\"The actual jev_verify call reports that no supported provider API key is configured; this guest has no provider credential.\"}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"README development build\",\"source\":\"README.md#development\",\"input\":\"npm run build\",\"expected\":\"TypeScript build succeeds\",\"argv\":[\"/usr/bin/npm\",\"run\",\"build\"],\"cwd\":\"\",\"env\":{\"PATH\":\"\"}}]\nEOF\n= python3 -I --validate --replay", "cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"mcp\",\"argv\":[\"\",\"\"],\"cwd\":\"\",\"tool\":\"jev_verify\",\"arguments\":{\"claims\":[\"The Earth orbits the Sun.\"],\"evidence\":{\"text\":\"The Earth orbits the Sun.\"}},\"expected_text\":\"No TYPESAFE_API_KEY\",\"checks\":[{\"check\":\"credentials_error\",\"argv\":[\"\",\"\"],\"tool\":\"jev_verify\",\"arguments\":{\"claims\":[\"The Earth orbits the Sun.\"],\"evidence\":{\"text\":\"The Earth orbits the Sun.\"}},\"expected_text\":\"No TYPESAFE_API_KEY\"}]}\nEOF\n= python3 -I --validate --replay", "cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"mcp\",\"argv\":[\"\",\"\"],\"cwd\":\"\",\"tool\":\"jev_verify\",\"arguments\":{\"claims\":[\"The Earth orbits the Sun.\"],\"evidence\":{\"text\":\"The Earth orbits the Sun.\"}},\"expected_text\":\"No TYPESAFE_API_KEY\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Check claims against evidence\",\"source\":\"Check each claim in a report, PR description, or agent brief against the sources it cites.\",\"input\":{\"claims\":[\"The Earth orbits the Sun.\"],\"evidence\":{\"text\":\"The Earth orbits the Sun.\"}},\"expected\":\"verified\",\"probe_kind\":\"mcp\",\"argv\":[\"\",\"\"],\"tool\":\"jev_verify\",\"arguments\":{\"claims\":[\"The Earth orbits the Sun.\"],\"evidence\":{\"text\":\"The Earth orbits the Sun.\"}},\"expected_text\":\"No TYPESAFE_API_KEY\",\"cwd\":\"\"}]\nEOF\n= python3 -I --validate --replay", "cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"mcp\",\"argv\":[\"\",\"\"],\"cwd\":\"\",\"tool\":\"jev_verify\",\"arguments\":{\"claims\":[\"The Earth orbits the Sun.\"],\"evidence\":{\"text\":\"The Earth orbits the Sun.\"}},\"expected_text\":\"The Earth orbits the Sun.\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Check claims against evidence\",\"source\":\"Check each claim in a report, PR description, or agent brief against the sources it cites.\",\"testable\":false,\"reason\":\"The provider call requires a credential; the observed call returned the actual missing key message, so no judgment result can be produced in this guest.\"}]\nEOF\n= python3 -I --validate --replay", "cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"mcp\",\"argv\":[\"\",\"\"],\"cwd\":\"\",\"tool\":\"jev_verify\",\"arguments\":{\"claims\":[\"The Earth orbits the Sun.\"],\"evidence\":{\"text\":\"The Earth orbits the Sun.\"}},\"expected_text\":\"No TYPESAFE_API_KEY\"}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[]\nEOF\ncat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"needs_credentials\",\"fault_owner\":\"prerequisite\",\"operation\":\"Build and run Jev MCP, then call jev_verify\",\"operation_scope\":\"Node.js 22.23.4 installed in guest; npm dependencies installed; README build and unit suite pass. Real MCP request replayed but provider credential absent.\",\"steps\":[\"npm install\",\"npm run build\",\"npm test\",\"Started documented stdio server and called jev_verify with an evidence-backed claim\"],\"deviations\":[\"Ubuntu apt Node was v18.19.1; installed Node 22.23.4 using npm package in for README compatibility.\"],\"stuck_step\":\"Complete provider judgment\",\"main_blocker\":\"No supported provider API key available in guest environment.\",\"plain_failure\":\"The server builds and starts and advertises all twelve tools, but a judgment call cannot reach the provider without a provider API key.\",\"suggested_fix\":\"Provide a supported provider credential in the server environment, then replay jev_verify.\"}\nEOF\n= python3 -I --validate --replay" ], "stuck_step": "Complete provider judgment", "error_excerpt": "MCP tool reported missing credentials: {\"content\": [{\"type\": \"text\", \"text\": \"No TYPESAFE_API_KEY, OPENROUTER_API_KEY (sk-or-), Cloudflare token (CLOUDFLARE_API_TOKEN or JEV_CLOUDFLARE_API_TOKEN) + CLOUDFLARE_ACCOUNT_ID, or AI_GATEWAY_API_KEY found. Set one, or JEV_PROVIDER to choose explicitly.\"}],", "what_it_did": "Build and run Jev MCP, then call jev_verify", "suggested_fix": "Provide a supported provider credential in the server environment, then replay jev_verify.", "tokens_in": 672131, "tokens_out": 2797, "cost_usd": null, "usage_complete": true, "checks": [ { "check": "operation", "status": "FAIL", "details": { "working": false, "argv": [ "", "" ], "kind": "mcp", "serverInfo": { "name": "jev-mcp", "version": "0.14.5" }, "tools": [ "jev_verify", "jev_screen", "jev_noul", "jev_find", "jev_classify", "jev_decide", "jev_rerank", "jev_compare", "jev_extract", "jev_audit", "jev_review", "jev_gate" ], "tool_schema_bytes": 24135, "tool_result": { "content": [ { "type": "text", "text": "No TYPESAFE_API_KEY, OPENROUTER_API_KEY (sk-or-), Cloudflare token (CLOUDFLARE_API_TOKEN or JEV_CLOUDFLARE_API_TOKEN) + CLOUDFLARE_ACCOUNT_ID, or AI_GATEWAY_API_KEY found. Set one, or JEV_PROVIDER to choose explicitly." } ], "isError": true }, "needs_credentials": true, "blocker": "MCP tool reported missing credentials: {\"content\": [{\"type\": \"text\", \"text\": \"No TYPESAFE_API_KEY, OPENROUTER_API_KEY (sk-or-), Cloudflare token (CLOUDFLARE_API_TOKEN or JEV_CLOUDFLARE_API_TOKEN) + CLOUDFLARE_ACCOUNT_ID, or AI_GATEWAY_API_KEY found. Set one, or JEV_PROVIDER to choose explicitly.\"}], \"isError\": true}" } } ], "safety": { "version": "z2x-1", "rules_version": "z2x-1", "summary": "No problems traced to this repository code in these checks. 1 static matches retained as context.", "findings": [], "context": [ { "kind": "hardcoded-secret", "count": 1, "note": "Gitleaks found a possible hardcoded secret; value withheld.", "location_count": 1, "path": "test/mock.test.mjs" } ], "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=jkudish--jev-mcp-gpt-6-luna-1792845533962590952", "evidence_file": "/data/safety/jkudish--jev-mcp-gpt-6-luna-1792845533962590952.json.gz" }, "agent_execution": "native_agent", "agent_runtime": "codex", "agent_runtime_version": "codex-cli 0.163.0", "tool_transport": "mcp-assigned-vm", "platform": "linux", "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "native_tool_calls": 13, "native_bundle": null, "architecture": null, "backend": "hyperv", "platform_details": { "backend": "hyperv", "os": "linux" }, "platform_conflicts": null, "sandbox_source": null, "source_pin": { "commit": "6faa53961ade29edd0a9a2381ce74f84d64540b0", "url": "https://github.com/jkudish/jev-mcp" }, "purpose": "test_rerun", "profile": { "model": "gpt-6-luna", "reasoning": "low" }, "fault": { "owner": "prerequisite", "status": "diagnosed", "reason": "MCP tool reported missing credentials: {\"content\": [{\"type\": \"text\", \"text\": \"No TYPESAFE_API_KEY, OPENROUTER_API_KEY (sk-or-), Cloudflare token (CLOUDFLARE_API_TOKEN or JEV_CLOUDFLARE_API_TOKEN) + CLOUDFLARE_ACCOUNT_ID, or AI_GATEWAY_API_KEY found. Set one, or JEV_PROVIDER to choose explicitly.\"}], \"isError\": true}" }, "fix_id": null, "verifies_run_id": "jkudish--jev-mcp-gpt-6-luna-1792800077334745358", "hosting": null, "operation_scope": "Node.js 22.23.4 installed in guest; npm dependencies installed; README build and unit suite pass. Real MCP request replayed but provider credential absent.", "tool_calls": 13, "guest_setup": null, "runtime": null, "runtime_version": null, "runtime_revision": null, "source_revision": null, "evidence_version": null, "failure_origin": null, "evidence_strength": "nothing_checked", "works": "partly", "install_s": null, "first_use_s": null, "mcp": "local", "needs": [ "credentials" ], "needs_which": "TYPESAFE_API_KEY", "agent_interface": [ "mcp" ], "license": "MIT", "repo_url": "https://github.com/jkudish/jev-mcp", "cost_to_try": "needs an account or key", "hardware": null, "what_failed": "MCP tool reported missing credentials: {\"content\": [{\"type\": \"text\", \"text\": \"No TYPESAFE_API_KEY, OPENROUTER_API_KEY (sk-or-), Cloudflare token (CLOUDFLARE_API_TOKEN or JEV_CLOUDFLARE_API_TOKEN) + CL", "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": "Inspected README and package scripts; this MCP server exposes request/response judgment tools and has no scheduler or cycle entry point.", "evidence": "Inspected README and package scripts; this MCP server exposes request/response judgment tools and has no scheduler or cycle entry point.", "command": "" } ], "claims": [], "claims_note": "README makes no concrete product claims.", "example_checks": [ { "kind": "example", "claim": "README development build", "source": "README.md#development", "input": "npm run build", "command": "/usr/bin/npm run build", "evidence": "> @jkudish/jev-mcp@0.14.5 build\n> tsc", "deferred": false, "expected": "TypeScript build succeeds", "returncode": 0, "verdict": "yes", "outcome": "command completed successfully" } ], "does_what_it_says": null, "maintenance": { "archived": false, "commits_90d": 107, "last_commit_at": "2026-10-21T21:34:27Z", "last_release_at": "2026-10-21T22:00:16Z", "median_reply_hours": 17.7, "merged_prs_90d": 22, "note": "actively maintained: last commit 2 days ago; 107 commits and 22 merged PRs in 90 days; 1 open issues, 3 open PRs; 28 of 39 recent threads got a maintainer reply, median first reply 17.7h; latest release 2026-10-21", "open_issues": 1, "open_prs": 3, "reply_share": 0.72, "reply_threads": 39, "verdict": "maintained" }, "maintenance_verdict": "maintained", "maintenance_note": "actively maintained: last commit 2 days ago; 107 commits and 22 merged PRs in 90 days; 1 open issues, 3 open PRs; 28 of 39 recent threads got a maintainer reply, median first reply 17.7h; latest release 2026-10-21", "maintained": "active", "maintained_note": "last commit 2 days ago; 1 open issues, 10 answered or closed", "last_commit_at": "2026-10-21T22:00:14Z", "last_release_at": "2026-10-21T22:00:16Z", "open_issues": 1, "answered_issues": 10, "platforms_claimed": [ "linux" ], "topic": "mcp-server", "agent_interfaces": [ { "interface": "mcp", "evidence": "independent checker", "observed": true, "operation_checked": false } ], "agent_interfaces_note": "README metadata is a discovery hint, not pinned documentation proof. Observed interfaces were exercised in this run. An empty list means unknown.", "mcp_context": { "tool_count": 12, "schema_bytes": 24135, "tokens_approx": 6034, "estimate_method": "ceil(compact UTF-8 tools/list JSON bytes / 4)", "scope": "returned tools/list page only; excludes client framing and tool results" }, "tested_at": "2026-10-24T12:48:51.166752+00:00", "tested_commit": "6faa53961ade29edd0a9a2381ce74f84d64540b0", "tested_with": { "agent": "codex", "agent_version": "codex-cli 0.163.0", "model": "gpt-6-luna", "model_route": "gpt-6-luna", "reasoning": "low", "os": "linux", "backend": "hyperv", "transport": "mcp-assigned-vm" }, "setup_identity": { "repo": "jkudish/jev-mcp", "source": "https://github.com/jkudish/jev-mcp", "commit": "6faa53961ade29edd0a9a2381ce74f84d64540b0", "source_revision": null, "os": "linux", "architecture": null, "backend": "hyperv", "model": "gpt-6-luna", "model_version": "gpt-6-luna", "agent_execution": "native_agent", "agent_runtime": "codex", "agent_runtime_version": "codex-cli 0.163.0", "tool_transport": "mcp-assigned-vm", "runtime": null, "runtime_version": null, "runtime_revision": null, "sandbox_source": null, "guest_setup": null, "source_pin": { "commit": "6faa53961ade29edd0a9a2381ce74f84d64540b0", "url": "https://github.com/jkudish/jev-mcp" }, "platform_details": { "os": "linux", "backend": "hyperv" }, "platform_conflicts": null, "reasoning": "low", "service_tier": "standard", "resources": { "cpus": 2, "memory_mib": 4096, "disk_mib": 32768 }, "operation": "Build and run Jev MCP, then call jev_verify", "operation_scope": "Node.js 22.23.4 installed in guest; npm dependencies installed; README build and unit suite pass. Real MCP request replayed but provider credential absent.", "hosting": null, "kind": "mcp", "test_version": "readme-df4b35fa98302b0e4e98e2674b9b06ded355b64401f37cded16cfd580be506df", "evidence_version": null }, "transcript_url": null, "report_url": "/reports/jkudish--jev-mcp-gpt-6-luna-1792845533962590952.json" }