mcp-fence report

target: {{ result.target | e }} · kind: {{ result.kind }} · generated {{ result.completed_at or result.started_at }}

verdict

{{ result.summary.verdict }}

{{ result.summary.total }} findings

risk score

{{ result.summary.score }}/100

critical {{ result.summary.by_severity.get('critical', 0) }} high {{ result.summary.by_severity.get('high', 0) }} medium {{ result.summary.by_severity.get('medium', 0) }} low {{ result.summary.by_severity.get('low', 0) }} info {{ result.summary.by_severity.get('info', 0) }}

categories

{% if result.summary.by_category %}

{% for cat, n in result.summary.by_category.items() %}
• {{ cat }} · {{ n }}
{% endfor %}

{% else %}

no findings

{% endif %}

{% if result.inventory %}

Tool inventory

{{ result.inventory.tools | length }} tool(s) · transport {{ result.inventory.transport }} · {{ result.inventory.server_info.name or 'unknown server' }}

{% for t in result.inventory.tools %} {{ t.name | e }} {% endfor %}

{% if result.inventory.warnings %}

Protocol warnings

{% for w in result.inventory.warnings %}
• {{ w | e }}
{% endfor %}

{% endif %}

{% endif %}

Top findings

{% if top_findings %} {% for f in top_findings %} {% endfor %}

Severity	Rule	Title	Where	Detail
{{ f.severity.value }}	{{ f.rule_id }}	{{ f.title | e }}	{{ f.location.short() | e }}	{{ f.description | e }}

{% else %} {% endif %}

All findings

{% if all_findings %} {% for f in all_findings %} {% endfor %}

Severity	Rule	Title	Category	Where	Evidence	Recommendation
{{ f.severity.value }}	{{ f.rule_id }}	{{ f.title | e }}	{{ f.category }}	{{ f.location.short() | e }}	{% if f.evidence %}{{ (f.evidence[:200]) | e }}{% endif %}	{{ f.recommendation | e }}

{% endif %} {% if result.fuzz_results %}

Fuzz results

{{ result.fuzz_results | length }} cases · {{ violations }} boundary violations · {{ skipped }} skipped

{% for fr in result.fuzz_results %} {% endfor %}

Tool	Category	Intent	Status	Signals
{{ fr.case.tool_name }}	{{ fr.case.payload_category }}	{{ fr.case.intent | e }}	{% if fr.skipped %}skipped{% elif fr.boundary_violation %}violation{% elif fr.response_ok %}ok{% else %}error{% endif %}	{% for sig in fr.detected_signals %}{{ sig }} {% endfor %}{% if fr.skipped %}{{ fr.skip_reason | e }}{% endif %}

{% endif %}

Remediation checklist

{% for f in remediation %}
• {{ f.rule_id }} {{ f.title | e }} — {{ f.recommendation | e }}
{% endfor %}

{% if sandbox_hint %}

Sandbox recommendation

{{ sandbox_hint | e }}

{% endif %}

Methodology

mcp-fence

{{ result.tool_version }}

started

{{ result.started_at }}

finished

{{ result.completed_at or '—' }}

findings

{{ result.summary.total }}

No external scripts, fonts, or styles are loaded. This report works offline.