How do I use Kitbag MCP?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Kitbag MCP extract text from report.pdf" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

Kitbag MCP

by syedtaj7

Overview Schema Source Related Servers Discussions Admin

TypeScript

Kitbag MCP is a single, open-source Model Context Protocol server that bundles a curated library of 50+ high-value utility tools — document converters, OCR processors, web scrapers, data formatters, and AI developer utilities — all in one place.
Instead of installing, configuring, and paying to host a dozen single-purpose MCP servers, install Kitbag MCP once and selectively enable only the modules you need. It runs entirely on your machine: zero hosting costs, no API keys, no server setup.

📖 Table of Contents

Related MCP server: IteraTools MCP

🚀 Quick Start (Zero Config)

Run instantly using npx (Node.js required):

npx kitbag-mcp

Expose Specific Modules (Saves LLM Context Tokens)

To prevent your AI agents from getting overwhelmed by tool options, enable only what you need:

# Enable PDF and Web scraping modules only
npx kitbag-mcp --enabled-modules pdf,web

⚙️ Supported Clients Setup

1. Claude Desktop

Add this entry to your claude_desktop_config.json:

{
  "mcpServers": {
    "kitbag-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "kitbag-mcp",
        "--enabled-modules",
        "pdf,web,image,data,utility,ai"
      ]
    }
  }
}

2. Cursor

Go to Settings → Beta Features → MCP.
Click + Add New MCP Server.
Configure:
- Name: Kitbag MCP
- Type: stdio
- Command: npx -y kitbag-mcp --enabled-modules pdf,web,data,utility

3. Windsurf

Add this entry to your mcp_config.json:

{
  "mcpServers": {
    "kitbag-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "kitbag-mcp"
      ],
      "env": {
        "KITBAG_ENABLED_MODULES": "pdf,web,data,utility"
      }
    }
  }
}

🎛️ Configuration Flags & Environment Variables

Kitbag MCP can be configured through CLI flags, environment variables, or a JSON config file — whichever fits your workflow.

Configuration Source	Example Usage
CLI Flags	`--enabled-modules pdf,web` or `--enabled-tools utility.qr_generate`
Env Variables	`KITBAG_ENABLED_MODULES=pdf,web` or `KITBAG_ENABLED_TOOLS=utility.qr_generate`
JSON Config	A `kitbag-config.json` file in the current working directory, or via `--config /path/to/config.json`

kitbag-config.json schema:

{
  "enabledModules": ["pdf", "web", "image", "data", "utility", "ai", "developer"],
  "enabledTools": [],
  "defaultTimeoutMs": 30000,
  "maxPayloadSizeBytes": 52428800
}

🗺️ Tool Category Index

Category	Prefix	Tools	Focus
📄 PDF	`pdf.*`	6	Parsing, conversion, merging, splitting
🌐 Web	`web.*`	7	Scraping, feeds, sitemaps, DNS
📸 Image & OCR	`image.*`	5	Resizing, compression, OCR, EXIF
📊 Data	`data.*`	8	CSV / JSON / XML / YAML conversion
💻 Developer	`developer.*`	11	Formatting, linting, diffing, decoding
🛠️ Utility	`utility.*`	12	Crypto, QR, networking, archives
🧠 AI	`ai.*`	1	Text chunking for LLM ingestion

📚 Complete Tool Directory

📄 PDF Tools (`pdf.*`)

High-performance local PDF parsers and manipulators.

Tool Name	Description	Example Agent Prompt
`pdf.convert_to_text`	Extract raw text from a PDF document.	"Extract the text from reports/invoice.pdf"
`pdf.convert_to_markdown`	Parse PDF and format it into clean Markdown.	"Convert layout of guide.pdf to markdown"
`pdf.extract_images`	Extract raw image assets embedded inside a PDF.	"Extract all images from slide_deck.pdf"
`pdf.extract_tables`	Extract structured table data from PDF pages.	"Pull out all tables from financial_report.pdf"
`pdf.merge`	Merge multiple PDF files together in order.	"Merge doc1.pdf and doc2.pdf into a single file"
`pdf.split`	Split specific page ranges from a PDF.	"Give me page 1 to 3 from main_guide.pdf"

🌐 Web Scraping & Networking (`web.*`)

Interact with raw web documents and query networking systems.

Tool Name	Description	Example Agent Prompt
`web.to_markdown`	Scrape a webpage, clean clutter, and convert to Markdown.	"Convert the article at https://example.com/blog to markdown"
`web.extract_metadata`	Extract title, description, OG tags, and JSON-LD data.	"Get metadata for URL https://news.ycombinator.com"
`web.extract_links`	Scrape a webpage and list internal and external links.	"Find all external links on the Wikipedia page for AI"
`web.rss_parser`	Parse an RSS or Atom feed XML URL into JSON.	"Get the latest feed items from https://github.blog/feed/"
`web.sitemap_generator`	Fetch and parse a sitemap.xml URL, extracting all URLs.	"Fetch all URLs in the sitemap for google.com"
`web.dns_lookup`	Perform DNS resolution (A, AAAA, MX, TXT, etc.).	"Do an MX record lookup for domain gmail.com"
`web.youtube_transcript`	Extract text transcripts and captions with timestamps.	"Get the transcript for https://www.youtube.com/watch?v=dQw4w9"

📸 Image & OCR Tools (`image.*`)

Manipulate images and extract text locally.

Tool Name	Description	Example Agent Prompt
`image.ocr`	Extract text from an image locally using Tesseract OCR.	"Extract text from screenshot.png"
`image.resize`	Resize an image's dimensions (width and height).	"Resize avatar.png to be 200x200 pixels"
`image.compress`	Compress image file size with custom quality.	"Compress banner.jpg to 80% quality"
`image.convert_format`	Convert images between formats (PNG, JPEG, WebP, etc.).	"Convert logo.png to webp format"
`image.exif_metadata`	Extract EXIF camera and location metadata from image files.	"Show me the GPS coordinates and camera model of photo.jpg"

📊 Data Transformation (`data.*`)

Fast, offline conversion between standard data formats.

Tool Name	Description	Example Agent Prompt
`data.csv_to_json`	Convert CSV file or raw text to JSON.	"Parse users.csv and return it as JSON"
`data.json_to_csv`	Convert JSON array of objects to CSV output.	"Convert this array of users to a CSV table"
`data.xml_to_json`	Convert XML documents to structured JSON objects.	"Convert this configuration XML text to JSON"
`data.json_to_xml`	Convert JSON objects to clean XML output.	"Export this JSON object into XML tag format"
`data.yaml_to_json`	Convert YAML documents to JSON.	"Convert Kubernetes config yaml to JSON"
`data.json_to_yaml`	Convert JSON objects to clean YAML format.	"Format this database JSON block as YAML"
`data.deduplicate`	Deduplicate arrays of JSON objects by a specific key.	"Remove duplicates from this list of user objects by ID"
`data.diff_arrays`	Compare two JSON arrays and list differences.	"Compare array A and B and show me additions and removals"

💻 Developer Utilities (`developer.*`)

Standard formats, validation, and layout tools for developers.

Tool Name	Description	Example Agent Prompt
`developer.json_formatter`	Format and prettify JSON strings with custom indentation.	"Prettify this JSON string using 4 spaces indent"
`developer.jwt_decoder`	Decode JWT tokens to read payload/header claims.	"Decode this JWT token: eyJhbGciOiJI..."
`developer.sql_formatter`	Format SQL strings for multiple database dialects.	"Format this messy select query for PostgreSQL"
`developer.mermaid_generate`	Create Mermaid diagrams (flowcharts, sequence, etc.).	"Generate a flowchart diagram representing this user flow"
`developer.openapi_parser`	Parse and format OpenAPI/Swagger specification files.	"List the endpoints and request schemas of this openapi.yaml"
`developer.regex_tester`	Test regular expression matches on text.	"Test if this email regex matches test@example.com"
`developer.cron_parser`	Parse Cron expressions and list upcoming execution times.	"Tell me when the cron job '0 9 * 1-5' runs next"*
`developer.diff_files`	Show line differences between text files.	"Show me the diff between fileA.txt and fileB.txt"
`developer.diff_json`	Show differences between JSON schemas.	"Highlight structural changes between config1.json and config2.json"
`developer.code_detector`	Detect programming language and syntax structure.	"What programming language is this code written in?"
`developer.markdown_lint`	Lint and validate formatting in Markdown files.	"Find styling errors or trailing spaces in index.md"

🛠️ Utility Tools (`utility.*`)

System, network, and cryptography helper functions.

Tool Name	Description	Example Agent Prompt
`utility.qr_generate`	Generate a QR code as a file or base64 Data URL.	"Create a QR code pointing to https://github.com"
`utility.qr_read`	Read and decode a QR code from a file or stream.	"What does the QR code inside code.png say?"
`utility.base64_encode`	Convert strings/files to base64 format.	"Base64 encode the string 'Hello World'"
`utility.base64_decode`	Decode base64 strings back to text.	"Decode 'SGVsbG8gV29ybGQ='"
`utility.uuid_generate`	Generate secure UUIDs (v4/v1) or secure passwords.	"Generate a secure password of length 16"
`utility.file_hash`	Compute md5, sha1, or sha256 hashes of text/data.	"Calculate the sha256 hash of this string"
`utility.email_validate`	Validate syntax and verify MX records of emails.	"Check if support@github.com has valid MX records"
`utility.ssl_check`	Query certificate expiration date and info for any domain.	"Check when the SSL certificate for google.com expires"
`utility.unit_convert`	Convert values between physical or data units.	"Convert 1024 megabytes to gigabytes"
`utility.url_parser`	Break down URLs into protocol, domain, params, etc.	"Parse this search query URL into its components"
`utility.zip_create`	Compress files or folders into a single ZIP archive.	"Compress source/ and assets/ into workspace.zip"
`utility.zip_extract`	Extract a ZIP archive to a destination folder.	"Extract files from archive.zip into build_dir/"

🧠 AI Chunker (`ai.*`)

Segment large text structures dynamically for ingestion.

Tool Name	Description	Example Agent Prompt
`ai.text_chunker`	Chunk long text using paragraph/sentence/word strategies.	"Chunk this text document into 500-char sizes with a 50-char overlap"

🏗️ How It Works

flowchart LR
    A[AI Agent / Client] -->|MCP Protocol| B(Kitbag MCP Server)
    B --> C{Enabled Modules}
    C --> D[📄 pdf.*]
    C --> E[🌐 web.*]
    C --> F[📸 image.*]
    C --> G[📊 data.*]
    C --> H[💻 developer.*]
    C --> I[🛠️ utility.*]
    C --> J[🧠 ai.*]
    D & E & F & G & H & I & J --> K[Local Execution<br/>No External API Calls]
    K --> A

Kitbag MCP runs as a single local process. Your AI client talks to it over the standard MCP protocol, and only the modules you enable are exposed as tools — keeping token usage low and your workflow fast and private.

🛠️ Local Development & Contributions

Every tool is fully self-contained. Adding a new tool is as simple as creating a folder inside src/tools/<category>/<tool_name>/.

Contribution Requirements

File	Purpose
`tool.ts`	The main execution code, exporting a `ToolDefinition`.
`README.md`	Direct tool documentation and parameter descriptions.
`example.json`	Sample inputs and expected outputs.
`tests.ts`	Self-contained unit tests using mocks where necessary to run instantly.

Command Guide

# Build compiler output
npm run build

# Run all 50 module tests
npm test

# Run real-life execution checks (makes live API and DNS requests)
npx tsx src/tests/run_real_life.ts

⚖️ License

Distributed under the MIT License. See LICENSE for more information. Fully open-source and free to adapt for personal or commercial use.

⭐ If Kitbag MCP saves you time, consider starring the repo! ⭐

Available Tools

51 tools

ai_text_chunkerB

Split large text into smaller semantic chunks for LLM context optimization or vector databases (RAG).

Inputs: text (required), strategy, chunkSize, chunkOverlap.

data_csv_to_jsonB

Convert a CSV file or CSV string data to a JSON array.

Inputs: columns, csvData, filePath, delimiter.

data_deduplicateB

Remove duplicate entries from a JSON array of objects or strings.

Inputs: arrayData (required), key.

data_diff_arraysA

Compare two JSON arrays of objects and return the differences (added, deleted, modified, unchanged).

Inputs: arrayA (required), arrayB (required), key.

data_json_to_csvB

Convert a JSON array of objects to a CSV string.

Inputs: filePath, jsonData, delimiter.

data_json_to_xmlB

Convert a JSON object to an XML text string.

Inputs: jsonData (required), rootName.

data_json_to_yamlA

Convert a JSON object or string to a YAML text string.

Inputs: jsonData (required).

data_xml_to_jsonA

Convert an XML string to a structured JSON object.

Inputs: xml (required).

data_yaml_to_jsonB

Convert a YAML string to a structured JSON object.

Inputs: yaml (required).

developer_code_detectorB

Detect the programming language of a raw code snippet using heuristic analyzers.

Inputs: code (required).

developer_cron_parserA

Parse a cron expression to validate it, explain its scheduling, and list its next execution dates.

Inputs: expression (required), iterations.

developer_diff_filesA

Compare two text contents (or files) and generate a Git-style line-by-line diff.

Inputs: contentA (required), contentB (required), headerA, headerB.

developer_diff_jsonB

Perform a structural, nested properties diff comparison between two JSON objects.

Inputs: jsonA (required), jsonB (required).

developer_json_formatterA

Validate, format (pretty-print), or minify JSON strings.

Inputs: json (required), indent, minify.

developer_jwt_decoderA

Decode the header and payload of a JSON Web Token (JWT) without verification, displaying timestamps in human-readable formats.

Inputs: token (required).

developer_markdown_lintB

Lint Markdown text for common format, structural, and style violations.

Inputs: markdown (required).

developer_mermaid_generateA

Format and construct a syntax-valid Mermaid diagram markup.

Inputs: type (required), elements (required), title.

developer_openapi_parserA

Parse and validate an OpenAPI (Swagger) 3.0 / 3.1 specification, returning endpoints summary.

Inputs: spec (required).

developer_regex_testerA

Test a regular expression against a string and return details about matches and capture groups.

Inputs: text (required), regex (required), flags.

developer_sql_formatterB

Format SQL queries to improve readability. Supports dialects like sql, mysql, postgresql, sqlite, plsql.

Inputs: sql (required), dialect.

image_compressC

Compress image quality to reduce file size.

Inputs: quality (required), fileData, filePath, outputPath.

image_convert_formatC

Convert an image to a different file format (supports png, jpeg, bmp).

Inputs: format (required), fileData, filePath, outputPath.

image_exif_metadataA

Extract EXIF metadata tags (e.g. camera, GPS, capture date) from JPEG images.

Inputs: fileData, filePath.

image_ocrA

Extract text from an image (PNG, JPEG, etc.) using Tesseract OCR. Supports local file path or base64 data.

Inputs: fileData, filePath, language.

image_resizeB

Resize an image to specific width and height dimensions.

Inputs: width (required), height, fileData, filePath, +1 more.

pdf_convert_to_markdownB

Extract text from a PDF file and apply heuristics to format it into Markdown.

Inputs: fileData, filePath.

pdf_convert_to_textA

Extract raw text from a PDF file using pdf-parse (supports local file path or base64 data).

Inputs: fileData, filePath.

pdf_extract_imagesB

Extract embedded JPEG images from a PDF file.

Inputs: fileData, filePath.

pdf_extract_tablesB

Extract structures resembling data tables from a PDF text stream and format them in Markdown.

Inputs: fileData, filePath.

pdf_mergeB

Merge multiple PDF files into a single PDF document.

Inputs: files (required), outputPath.

pdf_splitB

Split a PDF file into separate pages or custom page ranges.

Inputs: pages, fileData, filePath.

utility_base64_decodeB

Decode a Base64 encoded string back to its original plain text or save to a file.

Inputs: base64 (required), outputPath.

utility_base64_encodeB

Encode a text string or a local file to Base64 format.

Inputs: text, filePath.

utility_email_validateA

Validate email format and check if the domain has configured mail exchange (MX) DNS records.

Inputs: email (required), checkMx.

utility_file_hashA

Calculate the cryptographic hash (SHA-256, MD5, SHA-1) of a file or text string.

Inputs: text, filePath, algorithm.

utility_qr_generateA

Generate a QR code for a given text or URL, returning a base64 Data URL or saving to a file.

Inputs: text (required), outputPath.

utility_qr_readB

Decode a QR code from an image file or base64 image data.

Inputs: fileData, filePath.

utility_random_numberA

Generate a cryptographically secure random integer within a specified range [min, max].

Inputs: max, min.

utility_ssl_checkA

Retrieve SSL certificate details (expiration, issuer, subject) for a given domain/host.

Inputs: host (required), port.

utility_unit_convertB

Convert values between physical or data units (length, mass, temperature, data storage).

Inputs: to (required), from (required), type (required), value (required).

utility_url_parserA

Parse a URL string into its component parts (protocol, hostname, port, pathname, search params, hash).

Inputs: url (required).

utility_uuid_generateA

Generate a cryptographically secure UUID (v4/v1) or a secure random password.

Inputs: type, length.

utility_zip_createC

Compress files or folders into a single ZIP archive.

Inputs: files (required), outputPath (required).

utility_zip_extractB

Extract a ZIP archive to a destination folder.

Inputs: zipPath (required), outputPath (required).

web_dns_lookupA

Perform DNS resolution for a domain (A, AAAA, MX, TXT, CNAME, NS, SOA).

Inputs: domain (required), rrtype.

web_extract_linksA

Scrape a webpage and extract all links with their anchor text, categorizing them as internal or external.

Inputs: url (required), ignoreAnchorOnly.

web_extract_metadataB

Extract metadata, OpenGraph tags, Twitter cards, and JSON-LD structured data from a web page.

Inputs: url (required).

web_rss_parserA

Parse an RSS or Atom feed XML URL and return feed items in a structured JSON array.

Inputs: url (required).

web_sitemap_generatorA

Fetch and parse a sitemap.xml URL, extracting all listed URLs.

Inputs: url (required).

web_to_markdownA

Fetch a web page, clean up clutter (scripts, styles, footer, navigation), and convert the main body to Markdown.

Inputs: url (required).

web_youtube_transcriptA

Extract text transcripts and captions with timestamps from a YouTube video URL.

Inputs: url (required), languageCode.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A3.5/5.0

Scored 2026-07-29 00:20 across 51 tools

Disambiguation5/5

Each tool targets a distinct operation, with clear category prefixes and unique action-noun combinations. No two tools appear to do the same thing.

Naming Consistency4/5

Tools follow a consistent category_operation pattern, but the operation style varies (e.g., verb_noun, noun_to_noun, noun_noun). This minor inconsistency does not hinder understanding.

Tool Count3/5

With 51 tools, the set is large but justified by the broad utility scope of a 'kitbag'. However, the count is on the high side, potentially overwhelming for an agent.

Completeness5/5

The toolkit covers a wide range of common tasks: data conversion, image processing, PDF handling, web scraping, developer utilities, and more. No obvious gaps for a general-purpose utility server.

Maintenance

ActivityNo data

ResponsivenessOutdated data

Resources

Related MCP Connectors

BenchlineA
io.github.fabwaseem
Open-source developer, PDF, image, SEO and security tools over a stateless HTTP MCP server. No key.
Developer Tools Image & Video Processing Security
1
https://benchline.fabwaseem.com/mcp
OneSimpleAPI
com.onesimpleapi
Screenshots, PDFs, image editing, QR codes, email validation and more through one hosted MCP server.
Image & Video Processing Browser Automation
1
https://onesimpleapi.com/mcp
Novada MCP
io.github.NovadaLabs
One MCP server for all web data. Scrape, search, crawl, and AI research in one install.
Browser Automation Web Scraping Search
13
https://mcp.novada.com/mcp
Tinplate Edge AI Safety, Security & EU ComplianceB
dev.tinplate
Zero-log MCP server with 49 tools for AI guardrails, secret scanning, MCP linting & EU compliance.
491
https://api.tinplate.dev/mcp

Related MCP Servers

doc-ops-mcp
Documentation Access Content Management Systems
Tele-AI
A
license
B
quality
D
maintenance
A universal MCP server for document processing, conversion, and automation. Handle PDF, DOCX, HTML, Markdown, and more through a unified API and toolset.
Updated 6 days ago (2026-11-09 09:08 UTC)
13
18 npm
140
MIT
IteraTools MCP
Web Scraping Image & Video Processing Text-to-Speech
fredpsantos33
A
license
B
quality
D
maintenance
Production-ready MCP server with 40+ tools — QR codes, PDFs, text processing, TTS, web scraping, image generation and more. Built for AI agents.
Updated 8 months ago (2026-03-06 22:16 UTC)
25
61 npm
MIT
mcp-services
san-npm
A
license
Not graded
quality
D
maintenance
Multi-tool MCP server for AI agents with 29 tools across web scraping, SEO analysis, screenshot and PDF generation, domain intelligence, content extraction, multi-chain EVM blockchain queries, and security toolkit. Free tier available with no auth required.
Updated 8 months ago (2026-03-10 20:07 UTC)
50 npm
1
MIT
onion-mcp-serverofficial
AI & Machine Learning Code Analysis Web Scraping
onion-ai
A
license
A
quality
D
maintenance
A feature-rich MCP server offering 30 tools across AI, code, text, data, web, and system categories, enabling tasks like chat, translation, code review, web scraping, and text processing.
Updated 6 months ago (2026-05-15 08:04 UTC)
30
MIT

📖 Table of Contents

🚀 Quick Start (Zero Config)

Expose Specific Modules (Saves LLM Context Tokens)

⚙️ Supported Clients Setup

1. Claude Desktop

2. Cursor

3. Windsurf

🎛️ Configuration Flags & Environment Variables

🗺️ Tool Category Index

📚 Complete Tool Directory

📄 PDF Tools (pdf.*)

🌐 Web Scraping & Networking (web.*)

📸 Image & OCR Tools (image.*)

📊 Data Transformation (data.*)

💻 Developer Utilities (developer.*)

🛠️ Utility Tools (utility.*)

🧠 AI Chunker (ai.*)

🏗️ How It Works

🛠️ Local Development & Contributions

Contribution Requirements

Command Guide

⚖️ License

Available Tools

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

doc-ops-mcp

IteraTools MCP

mcp-services

onion-mcp-serverofficial

📄 PDF Tools (`pdf.*`)

🌐 Web Scraping & Networking (`web.*`)

📸 Image & OCR Tools (`image.*`)

📊 Data Transformation (`data.*`)

💻 Developer Utilities (`developer.*`)

🛠️ Utility Tools (`utility.*`)

🧠 AI Chunker (`ai.*`)