{ "checker": { "claims": [ { "claim": "The stdio MCP server runs via serve --stdio and exposes decoy tools that return fabricated results", "command": "node serve --stdio tools/call {\"tool\": \"canary_transfer_funds\", \"arguments\": {\"from_account\": \"A1\", \"to_account\": \"B2\", \"amount\": 5}}", "evidence": "\u2026T+0 (internal accounts)\\\"\\n}\"}]}", "expected": "status initiated with settlement T+0 (internal accounts)", "input": "{\"tool\": \"canary_transfer_funds\", \"arguments\": {\"from_account\": \"A1\", \"to_account\": \"B2\", \"amount\": 5}}", "kind": "claim", "outcome": "Real input produced the expected result: T+0 (internal accounts)", "source": "To run the MCP server over stdio, use agent-canary serve --stdio or run the container with -i and the same arguments.", "source_checked": true, "source_file": "README.md", "verdict": "yes" }, { "claim": "Agent Canary provides decoy tools as a security toolkit", "command": "node serve --stdio tools/call {\"tool\": \"canary_transfer_funds\", \"arguments\": {\"from_account\": \"A1\", \"to_account\": \"B2\", \"amount\": 5}}", "evidence": "\u2026T+0 (internal accounts)\\\"\\n}\"}]}", "expected": "decoy reply containing settlement T+0 (internal accounts)", "input": "{\"tool\": \"canary_transfer_funds\", \"arguments\": {\"from_account\": \"A1\", \"to_account\": \"B2\", \"amount\": 5}}", "kind": "claim", "outcome": "Real input produced the expected result: T+0 (internal accounts)", "source": "It provides decoy tools, canary tokens, a guarded execution gateway, local self-tests, and an optional risk-policy console.", "source_checked": true, "source_file": "README.md", "verdict": "yes" } ], "cycle_checks": [ { "claim": "Scheduled or looping main behavior", "command": "", "evidence": "Inspected README.md and src/ entrypoints (serve --stdio, self-test, ai console, integrate). No cron, scheduler, loop, webhook, or --once/--now trigger found; the only setInterval is browser-side UI polling in src/ai/console-page.ts, which is not a product cycle.", "expected": "identify the product trigger", "input": "source inspection", "kind": "cycle", "outcome": "Inspected README.md and src/ entrypoints (serve --stdio, self-test, ai console, integrate). No cron, scheduler, loop, webhook, or --once/--now trigger found; the only setInterval is browser-side UI polling in src/ai/console-page.ts, which is not a product cycle.", "source": "repository entry points", "verdict": "yes" } ], "details": { "argv": [ "node", "", "serve", "--stdio" ], "kind": "mcp", "scope": "product operation", "serverInfo": { "name": "agent-canary", "version": "1.2.7" }, "tool_result": { "content": [ { "text": "{\n \"status\": \"initiated\",\n \"transfer_id\": \"cnry_nruP-2JvxnsTg6X0u3_4qVYe\",\n \"from\": \"A1\",\n \"to\": \"B2\",\n \"amount\": 5,\n \"currency\": \"USD\",\n \"settlement\": \"T+0 (internal accounts)\"\n}", "type": "text" } ] }, "tool_result_checked": true, "tool_schema_bytes": 10868, "tools": [ "canary_transfer_funds", "canary_read_secrets", "canary_run_shell", "canary_delete_files", "canary_send_email", "canary_export_database", "canary_fetch_internal", "canary_disable_security", "canary_cloud_console", "canary_k8s_exec", "canary_secrets_rotate", "canary_git_force_push" ], "working": true }, "evidence_strength": "readme_checked", "example_checks": [ { "claim": "Local development verification builds, tests, and smoke-tests the package", "command": "npm run verify", "deferred": false, "evidence": "\"}\n{\"scope\":\"actual manifest bytes, not runtime certification or E4\",\"files\":181,\"mismatches\":[]}\n{\"status\":\"VERIFIED_BOUNDED_OPERATOR_DEMO\",\"mode\":\"OPERATOR_TRIGGERED_REAL_TEMPORARY_IO_NOT_MODEL_ATTACK\",\"resultFile\":\"/tmp/canary-roadshow-home-HpjlLu/roadshow-result.json\",\"fixture\":\"/tmp/agent-canary-honeypot-ii17zR\",\"caseCount\":6,\"E4\":\"NOT_VERIFIED_NO_EXTERNAL_OPERATOR\",\"sha256\":\"8f2958d4e262dd76fe92a57e247302546aae9d70640090135a0bc84bbab836fa\"}\n\n> @dorianchn/agent-canary@3.0.0 pack:check\n> node scripts/check-package.mjs\n\npackage smoke check passed: dorianchn-agent-canary-3.0.0.tgz (72 files)", "expected": "package smoke check passes", "input": "npm run verify", "kind": "example", "outcome": "command completed successfully", "returncode": 0, "source": "README.md Local development", "verdict": "yes" } ], "status": "PASS" }, "deviations": [ "README global install (npm config set @dorianchn:registry + npm login + npm install -g @dorianchn/agent-canary@3.0.0) was not run because it needs a GitHub PAT with read:packages; the README Local development path (npm ci, npm run verify) was used instead.", "Probes and claims call the package bin directly as node serve --stdio rather than the agent-canary command on PATH.", "MCP initialize reports serverInfo.version 1.2.7 (src/config.ts VERSION) while package.json and README say 3.0.0; recorded as an observation, not a test failure.", "npm ci reported 6 vulnerabilities (4 moderate, 2 high); not remediated.", "npm test in verify reported 97 pass, 0 fail, 3 skipped of 100.", "No scheduler/cycle found; cycles.json has detected=false." ], "fault_owner": null, "main_blocker": null, "operation": "Run the Agent Canary 3.0 stdio MCP server (serve --stdio) and call a decoy tool (canary_transfer_funds), plus the README Local development verification (npm run verify).", "operation_scope": "Linux guest, Node v22.23.4 and npm 10.9.9 (README requires Node 20+). No GitHub Packages login, no browser, no credentials. Decoy tools are inert and return fabricated results.", "outcome": "working", "plain_failure": null, "steps": [ "npm ci", "npm run verify", "node dist/competition.js serve --stdio (MCP tools/call canary_transfer_funds)", "= python3 -I --validate --replay" ], "stuck_step": null, "suggested_fix": "Optional: align VERSION in src/config.ts with package.json (3.0.0); run npm audit fix for the reported advisories; document that the global install needs GitHub Packages auth." }