Skip to main content
Glama
notasandy

MCP Code Sanitizer

by notasandy
OverviewSchemaRelated ServersScoreDiscussions
Python

generate_report

Generate a structured HTML report from code analysis results to document bugs, vulnerabilities, and security findings for review.

Instructions

Generates a beautiful HTML report from analyze_code or analyze_file results. Args: analysis_json: JSON string from analyze_code or analyze_file. output_path: Path to save the HTML file (optional). source_name: File/fragment name for the report title. Returns: JSON with fields: html, saved_to, length.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
analysis_jsonYes
output_pathNo
source_nameNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • tools/report.py:159-187 (handler)
    The main handler function for the generate_report tool. Accepts analysis_json (JSON string from analyze_code or analyze_file), optional output_path and source_name. Parses JSON, builds HTML via build_html(), optionally saves to a file, and returns JSON with html, saved_to, and length fields.
    async def generate_report(
    analysis_json: str,
    output_path: str = "",
    source_name: str = "",
) -> str:
    """
    Generates a beautiful HTML report from analyze_code or analyze_file results.
    Args:
        analysis_json: JSON string from analyze_code or analyze_file.
        output_path:   Path to save the HTML file (optional).
        source_name:   File/fragment name for the report title.
    Returns:
        JSON with fields: html, saved_to, length.
    """
    try:
        data = json.loads(analysis_json)
    except json.JSONDecodeError as e:
        return error_response("Invalid JSON in analysis_json", str(e))
    html     = build_html(data, source_name=source_name)
    saved_to = ""
    if output_path:
        out = Path(output_path).expanduser().resolve()
        try:
            out.parent.mkdir(parents=True, exist_ok=True)
            out.write_text(html, encoding="utf-8")
            saved_to = str(out)
        except OSError as e:
            return error_response("Failed to save file", str(e))
    return json.dumps({"html": html, "saved_to": saved_to, "length": len(html)}, ensure_ascii=True)
  • tools/report.py:105-158 (helper)
    build_html() helper - constructs the full HTML report from analysis data. Includes score ring, severity pills, issues, warnings, suggestions sections with inline CSS styling.
    def build_html(data: dict, source_name: str = "") -> str:
    score       = data.get("score", 0)
    summary     = data.get("summary", "")
    issues      = data.get("issues", [])
    warnings    = data.get("warnings", [])
    suggestions = data.get("suggestions", [])
    stats       = data.get("stats", {})
    filename    = data.get("file", source_name)
    lang        = data.get("language", "")
    lines       = data.get("lines", "")
    meta = "".join([
        f'<span><b>{filename}</b></span>' if filename else "",
        f'<span>Language: <b>{lang}</b></span>' if lang else "",
        f'<span>Lines: <b>{lines}</b></span>' if lines else "",
    ])
    header = (
        f'<div class="header">'
        f'<h1>Code Sanitizer <span>Report</span></h1>'
        f'<div class="meta">{meta}</div>'
        f'<div class="score-row">'
        f'{_ring(score)}'
        f'<div class="verdict"><b>Verdict:</b> {summary}</div>'
        f'</div></div>'
    )
    pills = "".join(
        f'<div class="pill {s}"><div class="n">{stats.get(s, 0)}</div><div class="l">{s}</div></div>'
        for s in _SEVERITY_ORDER
    ) if stats else ""
    sorted_issues = sorted(issues, key=lambda x: _SEVERITY_ORDER.index(x.get("severity", "low")))
    issues_html   = "".join(_issue_card(i) for i in sorted_issues) or '<div class="empty">No issues found</div>'
    warns_html    = "".join(
        f'<div class="warn"><div class="warn-title">{w.get("title","")}</div>'
        f'<div class="warn-desc">{w.get("description","")}</div></div>'
        for w in warnings
    ) or '<div class="empty">No warnings</div>'
    sugs_html = "".join(
        f'<div class="sug"><div class="sug-text">{s}</div></div>'
        for s in suggestions
    ) or '<div class="empty">No suggestions</div>'
    body = (
        header
        + (f'<div class="pills">{pills}</div>' if pills else "")
        + _section("    ", "Issues", issues_html, len(issues))
        + _section("      ", "Warnings", warns_html, len(warnings))
        + _section("    ", "Suggestions", sugs_html, len(suggestions))
        + '<div class="footer">Generated by <b>mcp-code-sanitizer</b>    Powered by Groq</div>'
    )
    return (
        f'<!DOCTYPE html><html lang="en"><head>'
        f'<meta charset="UTF-8"><meta name="viewport" content="width=device-width,initial-scale=1">'
        f'<title>Code Sanitizer - {filename or "Report"}</title>'
        f'<style>{_CSS}</style></head>'
        f'<body><div class="wrap">{body}</div></body></html>'
    )
  • tools/report.py:1-104 (helper)
    Supporting helper functions (_section, _issue_card, _ring, _score_color) and CSS styles used by build_html to generate the HTML report.
    import json
import math
from pathlib import Path
from groq_client import error_response
_SEVERITY_ORDER = ["critical", "high", "medium", "low"]
_CSS = """
:root {
  --bg:#0f1117; --surface:#1a1d2e; --surface2:#252840; --border:#2e3150;
  --text:#e2e8f0; --muted:#8892a4; --green:#2ed573; --yellow:#ffa502; --red:#ff4757;
  --critical:#ff4757; --high:#ff6b35; --medium:#ffa502; --low:#2ed573;
  --blue:#5352ed; --purple:#8c7ae6; --r:10px; --shadow:0 4px 24px rgba(0,0,0,.4);
}
*{box-sizing:border-box;margin:0;padding:0}
body{background:var(--bg);color:var(--text);font-family:-apple-system,BlinkMacSystemFont,"Segoe UI",sans-serif;padding:2rem 1rem}
.wrap{max-width:960px;margin:0 auto}
.card{background:var(--surface);border:1px solid var(--border);border-radius:var(--r);box-shadow:var(--shadow)}
.card+.card{margin-top:1.25rem}
.header{background:linear-gradient(135deg,var(--surface),var(--surface2));padding:2rem;border-radius:var(--r);margin-bottom:1.5rem;border:1px solid var(--border);box-shadow:var(--shadow)}
.header h1{font-size:1.6rem;font-weight:700}
.header h1 span{color:var(--purple)}
.meta{display:flex;gap:1.5rem;margin-top:.6rem;flex-wrap:wrap;font-size:.85rem;color:var(--muted)}
.meta b{color:var(--text)}
.score-row{display:flex;align-items:center;gap:2rem;margin-top:1.25rem}
.ring{position:relative;width:80px;height:80px;flex-shrink:0}
.ring svg{transform:rotate(-90deg)}
.ring-val{position:absolute;inset:0;display:flex;align-items:center;justify-content:center;font-size:1.3rem;font-weight:800}
.verdict{font-size:1rem;line-height:1.6;color:var(--muted)}
.verdict b{color:var(--text)}
.pills{display:flex;gap:.75rem;margin-bottom:1.25rem;flex-wrap:wrap}
.pill{flex:1;min-width:110px;text-align:center;padding:.9rem 1rem;border-radius:var(--r);border:1px solid var(--border);background:var(--surface);box-shadow:var(--shadow)}
.pill .n{font-size:1.8rem;font-weight:800;line-height:1}
.pill .l{font-size:.72rem;color:var(--muted);margin-top:.3rem;text-transform:uppercase;letter-spacing:.05em}
.pill.critical .n{color:var(--critical)}
.pill.high .n{color:var(--high)}
.pill.medium .n{color:var(--medium)}
.pill.low .n{color:var(--low)}
.sec-head{display:flex;align-items:center;gap:.6rem;padding:.9rem 1.25rem;font-weight:700;font-size:.95rem;border-bottom:1px solid var(--border);background:var(--surface2);border-radius:var(--r) var(--r) 0 0}
.sec-head .cnt{margin-left:auto;background:var(--border);border-radius:20px;padding:.1rem .55rem;font-size:.78rem;color:var(--muted)}
.issue{padding:1.1rem 1.25rem;border-bottom:1px solid var(--border)}
.issue:last-child{border-bottom:none}
.issue-top{display:flex;align-items:flex-start;gap:.75rem;margin-bottom:.5rem}
.badge{padding:.2rem .6rem;border-radius:4px;font-size:.72rem;font-weight:700;text-transform:uppercase;letter-spacing:.04em;flex-shrink:0}
.badge.critical{background:rgba(255,71,87,.15);color:var(--critical);border:1px solid rgba(255,71,87,.3)}
.badge.high{background:rgba(255,107,53,.15);color:var(--high);border:1px solid rgba(255,107,53,.3)}
.badge.medium{background:rgba(255,165,2,.15);color:var(--medium);border:1px solid rgba(255,165,2,.3)}
.badge.low{background:rgba(46,213,115,.15);color:var(--low);border:1px solid rgba(46,213,115,.3)}
.issue-title{font-weight:600;font-size:.95rem}
.issue-line{color:var(--muted);font-size:.8rem;margin-left:auto;flex-shrink:0}
.issue-desc{color:var(--muted);font-size:.88rem;line-height:1.6;margin-bottom:.6rem}
.fix-label{font-size:.72rem;color:var(--muted);margin-bottom:.35rem;text-transform:uppercase;letter-spacing:.05em}
.fix{background:var(--bg);border:1px solid var(--border);border-radius:6px;padding:.7rem 1rem;font-family:monospace;font-size:.85rem;color:var(--green);white-space:pre-wrap;word-break:break-all}
.warn,.sug{padding:.85rem 1.25rem;border-bottom:1px solid var(--border)}
.warn:last-child,.sug:last-child{border-bottom:none}
.warn-title{font-weight:600;font-size:.9rem;color:var(--medium);margin-bottom:.3rem}
.warn-desc,.sug-text{color:var(--muted);font-size:.87rem;line-height:1.5}
.sug-text::before{content:"-> ";color:var(--blue);font-weight:700}
.empty{padding:1.5rem;text-align:center;color:var(--muted);font-size:.9rem}
.empty::before{content:"    ";color:var(--green)}
.footer{text-align:center;color:var(--muted);font-size:.8rem;margin-top:2rem;padding-top:1rem;border-top:1px solid var(--border)}
"""
def _score_color(score: int) -> str:
    if score >= 80:
        return "#2ed573"
    if score >= 60:
        return "#ffa502"
    return "#ff4757"
def _ring(score: int) -> str:
    color = _score_color(score)
    r = 34
    circ = 2 * math.pi * r
    dash = circ * score / 100
    return (
        f'<div class="ring">'
        f'<svg width="80" height="80" viewBox="0 0 80 80">'
        f'<circle cx="40" cy="40" r="{r}" fill="none" stroke="#2e3150" stroke-width="8"/>'
        f'<circle cx="40" cy="40" r="{r}" fill="none" stroke="{color}" stroke-width="8" '
        f'stroke-dasharray="{dash:.1f} {circ:.1f}" stroke-linecap="round"/>'
        f'</svg>'
        f'<div class="ring-val" style="color:{color}">{score}</div>'
        f'</div>'
    )
def _issue_card(issue: dict) -> str:
    sev      = issue.get("severity", "low")
    line     = f'line {issue["line"]}' if issue.get("line") else ""
    fix      = issue.get("fix", "")
    fix_html = f'<div class="fix-label">Fix</div><div class="fix">{fix}</div>' if fix else ""
    return (
        f'<div class="issue">'
        f'<div class="issue-top">'
        f'<span class="badge {sev}">{sev}</span>'
        f'<span class="issue-title">{issue.get("title", "")}</span>'
        f'<span class="issue-line">{line}</span>'
        f'</div>'
        f'<div class="issue-desc">{issue.get("description", "")}</div>'
        f'{fix_html}'
        f'</div>'
    )
def _section(icon: str, title: str, items_html: str, count: int) -> str:
    return (
        f'<div class="card">'
        f'<div class="sec-head">{icon} {title}<span class="cnt">{count}</span></div>'
        f'{items_html}'
        f'</div>'
    )

Tool Definition Quality

A4.2/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description carries full burden. It discloses output format (JSON with fields html, saved_to, length) and optional parameters. Lacks details on side effects (e.g., file overwriting) or performance considerations, but adequately outlines basic behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is concise with clear structure: purpose sentence, then list of args and returns. No wasted words, all information earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the presence of an output schema, the description covers input source, optional parameters, and return format. Minor gaps in error handling or limitations, but sufficient for a tool that wraps other tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description compensates well: explains analysis_json as JSON from specific sources, output_path as save path, and source_name as report title. Adds meaning beyond bare schema, though could include data type or format constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it generates an HTML report from analyze_code or analyze_file results, distinguishing it from sibling tools that perform analysis. Verb 'Generates' and specific resource 'HTML report' are explicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly specifies that input should come from analyze_code or analyze_file, providing clear context. However, no exclusion criteria or alternatives are discussed, though implied by sibling tool list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/notasandy/mcp-code-sanitizer'

If you have feedback or need assistance with the MCP directory API, please join our Discord server