ToolTrust
A2/100
Smithery

icosaedro-toolsnap-mcp

mcpsmithery

@Smithery

Deterministic, context-efficient microtools for AI agents. 47 tools total, 36 free. tools/list shows a curated core of 17; the rest is one free tool_catalog call away and runs via use_tool. Free flagships: fetch_extract (median 98.1% token reduction vs raw HTML, 53,820 → 2,001 tokens on 11 real pages) and fetch_html, plus html_to_markdown, fetch_metadata, PDF text, CSV/JSON queries, sitemaps, RSS/Atom feeds, link checking and utilities (UUID, hash, Base64, regex, diff, token count...). Extraction is pure parsing: no LLM in the loop, stable output. 11 paid tools with real per-call cost (no first-call-free): screenshot_url, fetch_rendered (JS pages) and keyword_research ($0.04), remove_background ($0.03), fal.ai media tools image_generate, image_upscale, audio_transcribe, text_to_speech (from $0.02) and video_generate (from $0.08), and csv_query_xl / json_query_xl for large files ($0.02). Pay per call with USDC on Base via x402 (no account), prepay a balance (min $0.50, ~33-38% cheaper, off-chain debit, no per-call gas), or buy card credits at https://mcp.toolsnap.app/checkout. Calling a paid tool without payment returns a structured 402 with payment options: expected behaviour, not a broken tool.

By Smithery | 41 findings | Scanned 10/26/2026 | tooltrust-scanner/v0.3.20

Repository health

Popularity and maintenance signals alongside the security grade.

Stars

Not collected

Forks

Not collected

GitHub metadata pending

Contributors

Not collected

GitHub metadata pending

Last commit

Not collected

GitHub metadata pending

Last release

Not collected

GitHub metadata pending

Release version

Not collected

Latest GitHub release

Stars trend

Daily star additions · History data pending

—

No observed star events yet.

——

Pull request activity

Weekly PR events · History data pending

No observed PR events yet.

——
Last scan Oct 26, 2026
12 Low29 Info

Risk Summary

Safe With Normal Controls

Dep Visibility is the main signal, but overall risk remains within an acceptable range.

Potential impact: This finding indicates the tool should be reviewed before it is trusted.

Recommended action: No high-risk findings were detected in this scan, but you should still apply least-privilege defaults and rescan after changes.

Suggested policy: keep this tool behind manual approval, do not allow unattended runs, and re-scan after narrowing risky permissions.

Security Findings (41)

  • LowAS-011

    ℹ️Missing Rate-Limit / Timeout ×12

    tool performs network or execution operations but declares no rate-limit, timeout, or retry configuration

    fetch_extractfetch_htmlhtml_to_markdownfetch_metadatapdf_text_extractcsv_queryjson_querysitemap_parserss_parsescreenshot_urlkeyword_researchremove_background

    Fix: Declare explicit rate-limit, timeout, and retry configuration for all network and execution tools. Implement exponential back-off and surface resource state to the calling agent.

  • InfoAS-014

    ℹ️Dependency Inventory Unavailable ×17

    Tool did not expose metadata.dependencies or repo_url, so supply-chain coverage is limited.

    tool_cataloguse_tooltask_recipesmemory_snippetpricingfetch_extractfetch_htmlhtml_to_markdownfetch_metadatapdf_text_extractcsv_queryjson_querysitemap_parserss_parsescreenshot_urlkeyword_researchremove_background

    Fix: Review and remediate the identified issue.

  • InfoAS-002

    ⚠️Excessive Permissions ×12

    declared capabilities: network access, HTTP requests

    fetch_extractfetch_htmlhtml_to_markdownfetch_metadatapdf_text_extract

    declared capabilities: network access, filesystem access, database access, HTTP requests

    csv_query

    declared capabilities: network access, database access, HTTP requests

    json_query

    declared capabilities: network access

    sitemap_parserss_parsescreenshot_urlkeyword_research

    declared capabilities: network access, filesystem access

    remove_background

    Fix: Tool requests broad permissions (exec/fs/network). Validate input parameters using Enums where possible, and restrict file system operations to explicit allowed directories.

Scan this tool yourself

Reproduce this audit locally, integrate into CI, or let your agent audit its own tools.

Install once, then scan any MCP server:

$ curl -sfL https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-scanner/main/install.sh | bash
$ tooltrust-scanner scan --server "npx -y icosaedro-toolsnap-mcp"

Adjust the package name if your npm registry name differs from the tool ID. View source

Add badge to your README

Copy this Markdown to show your ToolTrust grade on GitHub.

[![ToolTrust Grade A](https://raw.githubusercontent.com/AgentSafe-AI/tooltrust-directory/main/docs/badges/grade-a.svg)](https://github.com/AgentSafe-AI/tooltrust-directory)