Haiku 5.5
Native agent · Not testedChecked operation <host-path> https://mcp.deepwiki.com/mcp
Agent-reported scope: Installed mcpscore from the pinned checkout and ran the README's 'Audit your first server' command against https://mcp.deepwiki.com/mcp; it connected over Streamable HTTP and printed the audit with Final score 91/108 (exit 0).
Run details
- run
- mcp-box--mcpscore-claude-haiku-5-5-1792349612295314212
- date
- Oct 18, 2026
- time to working
- not recorded
- product hosting / execution
- Local command in the guest
- recorded operation scope
- product operation
- model
- claude-haiku-5-5
- agent / version
- claude-code / 2.1.300 (Claude Code)
- platform
- linux
- reported cost
- $0.005620
- Recorded source
- https://github.com/mcp-box/mcpscore
- Tool transport
- mcp-assigned-vm
- Test version
- readme-abdba4ff808874f9e3a15ab1ae88db85b1509a9d4c47daf5c1553fa8638b6951
- revision
- 8373931c162b5658d17dedd589bae3e2fc0a3546
Double-checks failed run: mcp-box/mcpscore · Oct 18, 2026.
Fix: fix-dc7748fab3ecd651f419.
What the agent did
Installed mcpscore from the pinned checkout and ran the README's 'Audit your first server' command against https://mcp.deepwiki.com/mcp; it connected over Streamable HTTP and printed the audit with Final score 91/108 (exit 0).
cd <host-path> && git log -1 --format=%H 2>/dev/null; ls -la; cat README.md 2>/dev/null | head -200
cd <host-path> && ls -la .github/workflows 2>/dev/null; ls <host-path> 2>/dev/null; echo CDP=$CDP_URL $<env-var>; which node npm python3 uv pip 2>&1
cd <host-path> && sed -n 200,400p README.md; python3 --version; python3 -m venv --help >/dev/null 2>&1 && echo venv_ok; cat <host-path> | head -80
cd /tmp && python3 -m venv <host-path> && <host-path> install -q --upgrade pip 2>&1 | tail -3; <host-path> install <host-path> 2>&1 | tail -5; ls <host-path> | grep -i mcpscore; ls <host-path>; ls <host-path> | head -50
sudo -n apt-get update -qq >/dev/null 2>&1; sudo -n DEBIAN_FRONTEND=noninteractive apt-get install -y -qq python3.12-venv >/tmp/apt.log 2>&1; echo apt=$?; rm -rf <host-path> && cd /tmp && python3 -m venv <host-path> && <host-path> install -q <host-path> 2>&1 | tail -5; echo pip=$?; ls <host-path> | grep -i mcpscore
cd /tmp && timeout 240 <host-path> https://mcp.deepwiki.com/mcp 2>&1 | tail -30; echo rc=${PIPESTATUS[0]}
cd <host-path> && mkdir -p .coldpass && cat > .coldpass/probe.json <<'EOF'
{"kind":"cli","argv":["<host-path>"}
EOF
cat > .coldpass/report.json <<'EOF'
{"outcome":"working","operation":"Installed mcpscore from the pinned checkout and ran the README's 'Audit your first server' command against https://mcp.deepwiki.com/mcp; it connected over Streamable HTTP and printed the audit with Final score 91/108 (exit 0).","operation_scope":"Remote URL audit only. Local-server audit (mcpscore path/to/server.py), --smoke, and --package were not run. Needs outbound network to the target URL.","steps":["apt-get install python3.12-venv (ensurepip missing for venv)","python3 -m venv <host-path> install <host-path>","mcpscore https://mcp.deepwiki.com/mcp (exit 0, Final score 91/108)"],"deviations":["README 'Install' shows 'pip install mcpscore'; installed from the pinned checkout instead so the tested code matches commit 8373931c. Required python3.12-venv via apt first because python3 -m venv failed with ensurepip unavailable."],"stuck_step":null,"main_blocker":null,"suggested_fix":null}
EOF
python3 -m json.tool .coldpass/probe.json >/dev/null && python3 -m json.tool .coldpass/report.json >/dev/null && echo json_ok; <env-var>=<host-path> python3 -I <host-path> --validate; echo rc=$?run JSON · checker evidence · agent report + check · transcript excerpt · error excerpt