{
  "run_id": "marcorusc--mcp-biomodelling-servers-gpt-6-luna-1793176891293074730",
  "date": "2026-10-28T08:48:25.592348+00:00",
  "repo": "marcorusc/mcp-biomodelling-servers",
  "kind": "mcp",
  "source": "https://github.com/marcorusc/mcp-biomodelling-servers",
  "commit": "d9079ee2eb8965d27939631da98117abe774091b",
  "model": "gpt-6-luna",
  "model_version": "gpt-6-luna",
  "test_version": "readme-604d73685be33b2939b2632791fb1de37972f659febb28a139c60d6e81057c18",
  "pass": true,
  "outcome": "pass",
  "time_to_working_s": 376.95486877700023,
  "total_s": 414.29924750328064,
  "steps": [
    "pwd; rg --files -g 'README*' -g 'pyproject.toml' -g 'requirements*' -g 'package.json' -g 'Dockerfile' -g 'Makefile' -g '*.md' | head -80; git status --short; python3 --version; sed -n '1,240p' README.md",
    "sed -n '240,520p' README.md; find . -maxdepth 2 -type f | head -70; python3 -m pip install mcp-biomodelling-servers",
    "python3 -m venv <guest-path>; <guest-path> -m pip install mcp-biomodelling-servers",
    "sed -n '1,160p' NeKo/README.md; sed -n '1,120p' NeKo/server.py; rg -n \"@mcp.tool|def .*list|def .*guide|instructions\" NeKo/server.py",
    "mcp-neko-server --help; grep -n 'def list_sessions\\|def create_session' NeKo/server.py | head; mkdir -p .coldpass; <guest-path> -m pip show mcp-biomodelling-servers | head",
    "grep -n 'project.scripts\\|mcp-neko' pyproject.toml; sed -n '1450,1525p' NeKo/server.py; ls <guest-path>",
    "<env-var>=<guest-path> python3 -I <guest-path> --help",
    "find <guest-path> -maxdepth 3 -name check.py -o -name '*preflight*'",
    "ls -la .coldpass; <guest-path> --help",
    "python3 - <<'PY'\nimport json\nfrom mcp import ClientSession, StdioServerParameters\nfrom mcp.client.stdio import stdio_client\nimport anyio\nasync def main():\n async with stdio_client(StdioServerParameters(command='<guest-path>',args=[],env={'MCP_BIOMODELLING_ARTIFACT_ROOT':'<guest-path>'})) as (r,w):\n  async with ClientSession(r,w) as s:\n   await s.initialize(); x=await s.call_tool('create_session',{'label':'coldpass probe'}); print(x)\nanyio.run(main)\nPY",
    "cat > <guest-path> <<'PY'\nimport anyio\nfrom mcp import ClientSession, StdioServerParameters\nfrom mcp.client.stdio import stdio_client\nasync def main():\n async with stdio_client(StdioServerParameters(command='<guest-path>',args=[],env={'MCP_BIOMODELLING_ARTIFACT_ROOT':'<guest-path>'})) as (r,w):\n  async with ClientSession(r,w) as s:\n   await s.initialize()\n   x=await s.call_tool('create_session',{'label':'coldpass probe'})\n   print(x)\nanyio.run(main)\nPY\n<guest-path> <guest-path>",
    "sudo -n apt-get -o DPkg::Lock::Timeout=300 update && sudo -n apt-get -o DPkg::Lock::Timeout=300 install -y libxrender1 libxext6 libx11-6",
    "sed -i \"s/print(x)/print(x.content[0].text)/\" <guest-path>; <guest-path> <guest-path>",
    "cat > .coldpass/probe.json <<'EOF'\n{\"kind\":\"mcp\",\"argv\":[\"<guest-path>\"],\"cwd\":\"<guest-path>\",\"tool\":\"create_session\",\"arguments\":{\"label\":\"coldpass probe\"},\"expected_text\":\"Created session:\",\"env\":{\"MCP_BIOMODELLING_ARTIFACT_ROOT\":\"<guest-path>\"}}\nEOF\ncat > .coldpass/claims.json <<'EOF'\n[{\"kind\":\"claim\",\"claim\":\"Create an isolated modelling session\",\"source\":\"Every modelling hypothesis should have its own NeKo session.\",\"input\":\"label=coldpass probe\",\"expected\":\"Created session:\",\"probe_kind\":\"mcp\",\"argv\":[\"<guest-path>\"],\"tool\":\"create_session\",\"arguments\":{\"label\":\"coldpass probe\"},\"expected_text\":\"Created session:\",\"cwd\":\"<guest-path>\",\"env\":{\"MCP_BIOMODELLING_ARTIFACT_ROOT\":\"<guest-path>\"}}]\nEOF\ncat > .coldpass/examples.json <<'EOF'\n[{\"kind\":\"example\",\"claim\":\"Start the installed NeKo MCP server\",\"source\":\"NeKo/README.md \u2014 Installation and startup\",\"input\":\"stdio MCP session\",\"expected\":\"Created session:\",\"argv\":[\"<guest-path>\"],\"cwd\":\"<guest-path>\",\"env\":{\"MCP_BIOMODELLING_ARTIFACT_ROOT\":\"<guest-path>\"},\"expected_text\":\"Created session:\"}]\nEOF\ncat > .coldpass/cycles.json <<'EOF'\n{\"detected\":false,\"checks\":[],\"reason\":\"Inspected the root README and NeKo README workflows; no scheduled job, recurring loop, webhook trigger, or one-shot cycle entrypoint is documented.\"}\nEOF",
    "<env-var>=<guest-path> python3 -I <guest-path> --validate --replay",
    "python3 - <<'PY'\np='.coldpass/claims.json';import json\nx=json.load(open(p));x[0]['source']='Every modelling hypothesis should have its own NeKo session.';json.dump(x,open(p,'w'))\nPY\n<env-var>=<guest-path> python3 -I <guest-path> --validate --replay",
    "python3 - <<'PY'\np='.coldpass/claims.json';import json\nx=json.load(open(p));x[0]['source']='Each server can maintain multiple isolated modelling sessions.';json.dump(x,open(p,'w'))\nPY\n<env-var>=<guest-path> python3 -I <guest-path> --validate --replay",
    "cat > .coldpass/report.json <<'EOF'\n{\"outcome\":\"working\",\"fault_owner\":null,\"operation\":\"Start the NeKo stdio MCP server and create an isolated modelling session\",\"operation_scope\":\"Python 3.12.3; mcp-biomodelling-servers 2.5.2 and declared modelling dependencies installed in <guest-path>\",\"steps\":[\"Read README requirements and NeKo installation/workflow guide\",\"Created a Python 3.12 virtual environment after global pip installation was rejected by PEP 668\",\"Installed mcp-biomodelling-servers and declared dependencies\",\"Installed missing Ubuntu runtime library libxrender1 after PyGraphviz raised ImportError\",\"Started NeKo via its installed console entrypoint and called create_session\",\"Validated and replayed probe, README claim, example, and cycle assessment successfully\"],\"deviations\":[\"Initial global install command `python3 -m pip install mcp-biomodelling-servers` failed: externally-managed-environment; retried successfully inside virtualenv.\",\"First MCP start reported missing libXrender.so.1; installed libxrender1 and retried successfully.\"],\"stuck_step\":null,\"main_blocker\":null,\"plain_failure\":null,\"suggested_fix\":null}\nEOF\nls -la .coldpass/report.json .coldpass/probe.json .coldpass/claims.json"
  ],
  "stuck_step": null,
  "error_excerpt": null,
  "what_it_did": "Start the NeKo stdio MCP server and create an isolated modelling session",
  "suggested_fix": null,
  "tokens_in": 720596,
  "tokens_out": 2429,
  "cost_usd": null,
  "usage_complete": true,
  "checks": [
    {
      "check": "operation",
      "status": "PASS",
      "details": {
        "working": true,
        "argv": [
          "<guest-path>"
        ],
        "kind": "mcp",
        "serverInfo": {
          "description": "Build and analyze signalling networks from biological interaction databases.",
          "name": "NeKo",
          "title": "NeKo Signalling Network Builder",
          "version": "2.5.2"
        },
        "tools": [
          "analyze_gene_set",
          "analyze_connectivity",
          "edit_interactions",
          "export_handoff_bundle",
          "list_network_history",
          "navigate_network_history",
          "compare_network_states",
          "set_network_history_limit",
          "create_network",
          "add_nodes",
          "remove_gene",
          "remove_interaction",
          "export_network",
          "export_neko_handoff",
          "list_genes_and_interactions",
          "find_paths",
          "reset_network",
          "clean_generated_files",
          "remove_bimodal_interactions",
          "remove_undefined_interactions",
          "list_bnet_files",
          "get_references",
          "set_default_params",
          "filter_interactions",
          "create_session",
          "list_sessions",
          "list_artifact_sessions",
          "set_default_session",
          "delete_session",
          "status",
          "preview_connection_impact",
          "bridge_components",
          "connect_targeted_nodes",
          "apply_global_connection",
          "export_biomass_handoff"
        ],
        "tool_schema_bytes": 93149,
        "tool_result": {
          "content": [
            {
              "text": "Created session: c135f2bb-b749-428e-8fd5-6577ac55df94 (coldpass probe)",
              "type": "text"
            }
          ],
          "isError": false,
          "structuredContent": {
            "result": "Created session: c135f2bb-b749-428e-8fd5-6577ac55df94 (coldpass probe)"
          }
        },
        "tool_result_checked": true,
        "scope": "product operation"
      }
    }
  ],
  "safety": {
    "version": "z2x-1",
    "rules_version": "z2x-1",
    "summary": "No problems traced to this repository code in these checks.",
    "expected": "Reviewed as expected for a test run: attempted writes that failed, so nothing was written.",
    "findings": [],
    "context": [],
    "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=marcorusc--mcp-biomodelling-servers-gpt-6-luna-1793176891293074730",
    "evidence_file": "/data/safety/marcorusc--mcp-biomodelling-servers-gpt-6-luna-1793176891293074730.json.gz"
  },
  "agent_execution": "native_agent",
  "agent_runtime": "codex",
  "agent_runtime_version": "codex-cli 0.164.0",
  "tool_transport": "mcp-assigned-vm",
  "platform": "linux",
  "reasoning": "low",
  "service_tier": "standard",
  "resources": {
    "cpus": 2,
    "memory_mib": 4096,
    "disk_mib": 32768
  },
  "native_tool_calls": 18,
  "native_bundle": null,
  "architecture": null,
  "backend": "hyperv",
  "platform_details": {
    "backend": "hyperv",
    "os": "linux"
  },
  "platform_conflicts": null,
  "sandbox_source": null,
  "source_pin": {
    "commit": "d9079ee2eb8965d27939631da98117abe774091b",
    "url": "https://github.com/marcorusc/mcp-biomodelling-servers"
  },
  "purpose": "initial",
  "profile": {
    "model": "gpt-6-luna",
    "reasoning": "low"
  },
  "fault": {
    "owner": null,
    "status": "resolved",
    "reason": null
  },
  "fix_id": null,
  "verifies_run_id": null,
  "hosting": null,
  "operation_scope": "product operation",
  "tool_calls": 18,
  "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": "GPL-3.0",
  "repo_url": "https://github.com/marcorusc/mcp-biomodelling-servers",
  "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": "Inspected the root README and NeKo README workflows; no scheduled job, recurring loop, webhook trigger, or one-shot cycle entrypoint is documented.",
      "evidence": "Inspected the root README and NeKo README workflows; no scheduled job, recurring loop, webhook trigger, or one-shot cycle entrypoint is documented.",
      "command": ""
    }
  ],
  "claims": [
    {
      "kind": "claim",
      "claim": "Create an isolated modelling session",
      "source": "Each server can maintain multiple isolated modelling sessions.",
      "input": "{\"tool\": \"create_session\", \"arguments\": {\"label\": \"coldpass probe\"}}",
      "expected": "Created session:",
      "command": "<guest-path> tools/call {\"tool\": \"create_session\", \"arguments\": {\"label\": \"coldpass probe\"}}",
      "verdict": "yes",
      "outcome": "Real input produced the expected result: Created session:",
      "evidence": "\u2026Created session: 78f3b230-5bf9-4f84-958e-3facd8191b72 (coldpass probe)\", \"type\": \"text\"}], \"isError\": false, \"structuredContent\": {\"result\": \"Created session: 78f3b230-5bf9-4f84-958e-3facd8191b72 (coldpass probe)\"}}",
      "source_checked": true,
      "source_file": "README.md"
    }
  ],
  "claims_note": null,
  "example_checks": [
    {
      "kind": "example",
      "claim": "Start the installed NeKo MCP server",
      "source": "NeKo/README.md \u2014 Installation and startup",
      "input": "stdio MCP session",
      "command": "<guest-path>",
      "evidence": "",
      "deferred": false,
      "expected": "Created session:",
      "returncode": 0,
      "verdict": "yes",
      "outcome": "command completed successfully with no output"
    }
  ],
  "does_what_it_says": "yes",
  "maintenance": {
    "archived": false,
    "commits_90d": 105,
    "last_commit_at": "2026-10-28T07:04:28Z",
    "last_release_at": "2026-10-22T11:54:36Z",
    "median_reply_hours": 56.5,
    "merged_prs_90d": 13,
    "note": "actively maintained: last commit 0 days ago; 105 commits and 13 merged PRs in 90 days; 0 open issues, 0 open PRs; 3 of 4 recent threads got a maintainer reply, median first reply 56.5h; latest release 2026-10-22",
    "open_issues": 0,
    "open_prs": 0,
    "reply_share": 0.75,
    "reply_threads": 4,
    "verdict": "maintained"
  },
  "maintenance_verdict": "maintained",
  "maintenance_note": "actively maintained: last commit 0 days ago; 105 commits and 13 merged PRs in 90 days; 0 open issues, 0 open PRs; 3 of 4 recent threads got a maintainer reply, median first reply 56.5h; latest release 2026-10-22",
  "maintained": "active",
  "maintained_note": "last commit 0 days ago; 0 open issues, 2 answered or closed",
  "last_commit_at": "2026-10-28T07:05:58Z",
  "last_release_at": "2026-10-22T11:54:36Z",
  "open_issues": 0,
  "answered_issues": 2,
  "platforms_claimed": [
    "linux",
    "mac",
    "windows"
  ],
  "topic": "mcp-server",
  "agent_interfaces": [
    {
      "interface": "mcp",
      "evidence": "independent checker",
      "observed": true,
      "operation_checked": true
    }
  ],
  "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": 35,
    "schema_bytes": 93149,
    "tokens_approx": 23288,
    "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": "2026-10-28T08:48:25.592348+00:00",
  "tested_commit": "d9079ee2eb8965d27939631da98117abe774091b",
  "tested_with": {
    "agent": "codex",
    "agent_version": "codex-cli 0.164.0",
    "model": "gpt-6-luna",
    "model_route": "gpt-6-luna",
    "reasoning": "low",
    "os": "linux",
    "backend": "hyperv",
    "transport": "mcp-assigned-vm"
  },
  "setup_identity": {
    "repo": "marcorusc/mcp-biomodelling-servers",
    "source": "https://github.com/marcorusc/mcp-biomodelling-servers",
    "commit": "d9079ee2eb8965d27939631da98117abe774091b",
    "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 0.164.0",
    "tool_transport": "mcp-assigned-vm",
    "runtime": null,
    "runtime_version": null,
    "runtime_revision": null,
    "sandbox_source": null,
    "guest_setup": null,
    "source_pin": {
      "commit": "d9079ee2eb8965d27939631da98117abe774091b",
      "url": "https://github.com/marcorusc/mcp-biomodelling-servers"
    },
    "platform_details": {
      "os": "linux",
      "backend": "hyperv"
    },
    "platform_conflicts": null,
    "reasoning": "low",
    "service_tier": "standard",
    "resources": {
      "cpus": 2,
      "memory_mib": 4096,
      "disk_mib": 32768
    },
    "operation": "Start the NeKo stdio MCP server and create an isolated modelling session",
    "operation_scope": "product operation",
    "hosting": null,
    "kind": "mcp",
    "test_version": "readme-604d73685be33b2939b2632791fb1de37972f659febb28a139c60d6e81057c18",
    "evidence_version": null
  },
  "other_model": null,
  "other_run_id": null,
  "models_agree": null,
  "furthest_model": null,
  "transcript_url": "/transcripts/marcorusc--mcp-biomodelling-servers-gpt-6-luna-1793176891293074730.txt",
  "report_url": "/reports/marcorusc--mcp-biomodelling-servers-gpt-6-luna-1793176891293074730.json"
}