Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

io.github.marras0914/agent-toolbelt-mcp

NPM · AGENT-TOOLBELT-MCP · SCANNED AUG 3

19 focused API tools for AI agents: contract review, prompt optimizer, context packing, and more.

Available components

+17 this week 70 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security87
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability85
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 2155 tokens (~102/item across 21 items; 20 tools + 1 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage98
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 95% of tool parameters carry a description.Partial
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · agent-toolbelt-mcp

# add to Claude Code
claude mcp add marras0914-agent-toolbelt-mcp -- npx -y agent-toolbelt-mcp
# add to Codex CLI
codex mcp add marras0914-agent-toolbelt-mcp -- npx -y agent-toolbelt-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "marras0914-agent-toolbelt-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "agent-toolbelt-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add marras0914-agent-toolbelt-mcp --command npx --arg -y --arg agent-toolbelt-mcp
# ~/.hermes/config.yaml
mcp_servers:
  marras0914-agent-toolbelt-mcp:
    command: "npx"
    args: ["-y", "agent-toolbelt-mcp"]
// mcp.json
{
  "mcpServers": {
    "marras0914-agent-toolbelt-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "agent-toolbelt-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 2 Aug 26 +44
    • Provenance: unverified → fail security
    • Install scripts: unverified → pass security
    • Known CVEs: unverified → partial security
    • Malware scan: unverified → pass security
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • Stability: unverified → 0.20 functional
    • Schema quality: unverified → excellent functional
    • License: unverified → pass functional
    • Maintenance: unverified → pass functional
    • MCP protocol: unverified → pass functional
    • Dependency health: unverified → partial functional
    • Licence: MIT functional
  • 31 Jul 26 −27
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 27 Jul 26 53

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed npm/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 95 packages

95 packages in the resolved dependency tree · 95 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 20 exposed · ~2,139 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
audit_dependencies ~91

Audit npm and PyPI packages for known CVEs using the OSV database (GitHub Dependabot's source). Pass packages directly or paste package.json / requirements.txt content.

NameTypeReqDescription
includeDevDependenciesboolean
manifeststringRaw package.json or requirements.txt
manifestTypestring
minSeveritystring
packagesarrayPackages to audit

No output schema declared.

No examples provided.

build_cron ~80

Convert natural language schedule descriptions into cron expressions. Examples: 'every weekday at 9am', 'first Monday of each month at noon', 'every 5 minutes'. Returns the expression, human-readable confirmation, and next 5 run times.

NameTypeReqDescription
descriptionstringyesNatural language schedule description
timezonestringTimezone for context

No output schema declared.

No examples provided.

build_regex ~115

Build and test regular expressions from natural language descriptions. Supports emails, URLs, phones, dates, IPs, colors, UUIDs, and 15+ more patterns. Returns the pattern, code snippets in JS/Python/TS, and optional test results.

NameTypeReqDescription
descriptionstringyesWhat to match (e.g., 'email addresses', 'hex color codes', 'semantic versions')
flagsstringRegex flags (default: 'g')
testStringsarrayOptional strings to test the regex against

No output schema declared.

No examples provided.

compare_documents ~96

Compare two versions of a document and produce a semantic diff with additions, deletions, and modifications. Works with contracts, READMEs, policies, essays, or any text. Powered by Claude.

NameTypeReqDescription
contextstringDocument type for more relevant analysis
modestringOutput format
originalstringyesThe original version of the document
revisedstringyesThe revised version of the document

No output schema declared.

No examples provided.

convert_markdown ~96

Convert HTML to clean Markdown, or Markdown to HTML. Use HTML→Markdown when you've fetched a web page and need readable text for an LLM — strips tags, preserves headings, lists, code blocks, links, and tables. Use Markdown→HTML when rendering content in a web context.

NameTypeReqDescription
contentstringyesThe content to convert
fromstringyesInput format
tostringyesOutput format

No output schema declared.

No examples provided.

count_tokens ~107

Count tokens for any text across multiple LLM models and get per-model cost estimates. Use before sending text to an LLM to check context window usage or compare costs across models. Supports GPT-4o, GPT-4, GPT-3.5-turbo, Claude 3.5 Sonnet, Claude 3 Opus, and 10+ more.

NameTypeReqDescription
modelsarrayModels to count tokens for
textstringyesThe text to count tokens for

No output schema declared.

No examples provided.

csv_to_json ~120

Convert CSV data to typed JSON. Auto-detects delimiters, uses the first row as headers, and casts values to proper types (numbers, booleans, nulls). Use when processing spreadsheet exports or any CSV-formatted data.

NameTypeReqDescription
csvstringyesThe CSV content to convert
delimiterstringColumn delimiter
hasHeaderbooleanWhether the first row contains column names
limitnumberMax rows to return
typeCastbooleanAuto-convert values to proper types

No output schema declared.

No examples provided.

extract_contract_clauses ~90

Extract key clauses from a contract — parties, payment terms, termination, liability, IP ownership, confidentiality, and more. Optionally flags risky or one-sided clauses with severity ratings. Powered by Claude.

NameTypeReqDescription
clausesarrayWhich clause types to extract
contractstringyesThe contract or legal document text
flagRisksbooleanFlag risky or unfavorable clauses

No output schema declared.

No examples provided.

extract_from_text ~120

Extract structured data from raw text: emails, URLs, phone numbers, dates, currencies, addresses, names, or JSON blocks. Useful for parsing documents, emails, web content, or any unstructured text into clean structured data.

NameTypeReqDescription
deduplicatebooleanRemove duplicate results within each type
extractorsarrayyesWhich types of data to extract. Choose one or more: emails, urls, phone_numbers, dates, currencies, addresses, names, json_blocks
textstringyesThe raw text to extract data from

No output schema declared.

No examples provided.

extract_meeting_action_items ~92

Extract structured action items, decisions, and a summary from meeting notes or transcripts. Identifies task owners, deadlines, and priorities. Powered by Claude.

NameTypeReqDescription
formatstring'full' includes summary and decisions; 'action_items_only' returns just the task list
notesstringyesMeeting notes or transcript
participantsarrayKnown participant names to help with owner attribution

No output schema declared.

No examples provided.

fetch_url_metadata ~94

Fetch a URL and extract its metadata: title, description, Open Graph tags (og:image, og:type), Twitter card tags, favicon, canonical URL, author, and publish date. Use to enrich links with context or understand what a page is about without reading the full content.

NameTypeReqDescription
timeoutnumberRequest timeout in milliseconds (default 8000)
urlstringyesThe URL to fetch metadata from

No output schema declared.

No examples provided.

generate_brand_kit ~125

Generate a complete brand kit from a company name, industry, and aesthetic keywords. Returns a color palette with WCAG accessibility scores, curated typography pairings, and design tokens in JSON, CSS, or Tailwind format.

NameTypeReqDescription
formatstringOutput format
industrystringIndustry (e.g., 'fintech', 'healthcare', 'fashion')
namestringyesCompany or brand name
vibearrayAesthetic keywords: 'modern', 'playful', 'luxurious', 'minimal', 'bold', etc.

No output schema declared.

No examples provided.

generate_color_palette ~154

Generate a color palette from a description, mood, industry, or hex seed color. Accepts moods (calm, energetic, luxurious), industries (fintech, healthcare, fashion), nature themes (sunset, ocean, forest), or a specific hex color. Returns hex/RGB/HSL values, WCAG accessibility scores, and CSS custom properties.

NameTypeReqDescription
countintegerNumber of colors (2-10)
descriptionstringyesDescription of the desired palette (e.g. 'calm fintech blue', 'sunset', '#3B82F6')
formatstringColor format in output
includeShadesbooleanInclude light/dark shades for each color

No output schema declared.

No examples provided.

generate_schema ~134

Generate a JSON Schema, TypeScript interface, or Zod validation schema from a natural language description of a data structure. Examples: 'a user profile with name, email, and signup date', 'a product listing with title, price, and inventory count'.

NameTypeReqDescription
descriptionstringyesNatural language description of the data structure you want a schema for
formatstringOutput format: json_schema (standard JSON Schema), typescript (TS interface), or zod (Zod validation schema)
strictbooleanIf true, all fields are required. If false, optional fields are marked as optional

No output schema declared.

No examples provided.

list_tools ~25

List all tools available in the Agent Toolbelt API catalog, including descriptions and pricing.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

mock_api_response ~110

Generate realistic mock API responses from a JSON Schema. Supports nested objects, arrays, string formats (email, uuid, date-time, url), field-name heuristics, enums, and min/max constraints. Set seed for reproducible output. Returns 1–100 records.

NameTypeReqDescription
countintegerNumber of mock records to generate (1–100)
schemaobjectyesJSON Schema object describing the shape of the mock data
seedintegerOptional seed for reproducible output

No output schema declared.

No examples provided.

normalize_address ~82

Normalize a US mailing address to USPS standard format. Expands abbreviations (st→ST, ave→AVE), standardizes directionals, converts state names to codes. Returns parsed components and a confidence score (high/medium/low).

NameTypeReqDescription
addressstringyesThe US address to normalize
includeComponentsbooleanInclude parsed address components in response

No output schema declared.

No examples provided.

optimize_prompt ~132

Analyze and improve an LLM prompt. Scores clarity, specificity, structure, and completeness. Returns an optimized rewrite with a summary of what changed and why. Powered by Claude.

NameTypeReqDescription
modestring'both' returns analysis + improved prompt; 'analyze' scores only; 'improve' rewrites only
modelstringTarget model (e.g. 'gpt-4o', 'claude-3-5-sonnet')
promptstringyesThe LLM prompt to analyze and/or improve
taskstringWhat this prompt is trying to accomplish

No output schema declared.

No examples provided.

pack_context_window ~139

Pack content chunks into a token budget for an LLM context window. Selects the best subset of chunks that fits within the token limit using priority, greedy, or balanced strategies. Use when you have more content than fits in the context window.

NameTypeReqDescription
chunksarrayyesContent chunks to pack
modelstringTarget model for tokenization
reserveForOutputintegerTokens to reserve for output
separatorstringText between chunks
strategystringPacking strategy
systemPromptstringSystem prompt to reserve tokens for
tokenBudgetintegeryesMaximum tokens allowed

No output schema declared.

No examples provided.

strip_image_metadata ~137

Strip EXIF, GPS, IPTC, XMP, and ICC metadata from an image for privacy. Use before uploading or sharing images to remove sensitive embedded data like GPS coordinates, camera model, timestamps, and editing history. Accepts base64-encoded JPEG, PNG, WebP, or TIFF. Returns cleaned base64 image with a removal report.

NameTypeReqDescription
formatstringOutput format ('preserve' keeps original)
imagestringyesBase64-encoded image (JPEG, PNG, WebP, TIFF). No data URI prefix.
qualityintegerQuality for lossy formats (1-100)

No output schema declared.

No examples provided.