Kitbag MCP — A Modular Utility MCP Server
Connect Kitbag to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Kitbag MCP — A Modular Utility MCP Server. The kitbag mcp server is what makes that connection.
To prevent your AI agents from getting overwhelmed by tool options, enable only what you need:
The server ships on npm as kitbag-mcp, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
pdf.convert_to_text — Extract raw text from a PDF documentpdf.convert_to_markdown — Parse PDF and format it into clean Markdownpdf.extract_images — Extract raw image assets embedded inside a PDFpdf.extract_tables — Extract structured table data from PDF pagespdf.merge — Merge multiple PDF files together in orderpdf.split — Split specific page ranges from a PDFweb.to_markdown — Scrape a webpage, clean clutter, and convert to Markdownweb.extract_metadata — Extract title, description, OG tags, and JSON-LD dataweb.extract_links — Scrape a webpage and list internal and external linksweb.rss_parser — Parse an RSS or Atom feed XML URL into JSONweb.sitemap_generator — Fetch and parse a sitemap.xml URL, extracting all URLsweb.dns_lookup — Perform DNS resolution (A, AAAA, MX, TXT, etc.)Configuration is passed through the environment: KITBAG_ENABLED_MODULES. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Kitbag's toolset — pdf.convert_to_text, pdf.convert_to_markdown, pdf.extract_images and 11 more — is a fair guide to whether it matches your workflow. It is maintained by royalblood; worth a glance at recent repository activity before you build anything load-bearing on it.
We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.
| Tool | What it does |
|---|---|
| pdf.convert_to_text | Extract raw text from a PDF document. |
| pdf.convert_to_markdown | Parse PDF and format it into clean Markdown. |
| pdf.extract_images | Extract raw image assets embedded inside a PDF. |
| pdf.extract_tables | Extract structured table data from PDF pages. |
| pdf.merge | Merge multiple PDF files together in order. |
| pdf.split | Split specific page ranges from a PDF. |
| web.to_markdown | Scrape a webpage, clean clutter, and convert to Markdown. |
| web.extract_metadata | Extract title, description, OG tags, and JSON-LD data. |
| web.extract_links | Scrape a webpage and list internal and external links. |
| web.rss_parser | Parse an RSS or Atom feed XML URL into JSON. |
| web.sitemap_generator | Fetch and parse a sitemap.xml URL, extracting all URLs. |
| web.dns_lookup | Perform DNS resolution (A, AAAA, MX, TXT, etc.). |
| web.youtube_transcript | Extract text transcripts and captions with timestamps. |
| image.ocr | Extract text from an image locally using Tesseract OCR. |
{
"mcpServers": {
"kitbag": {
"command": "npx",
"args": ["-y", "kitbag-mcp"],
"env": {
"KITBAG_ENABLED_MODULES": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| KITBAG_ENABLED_MODULES | Configuration value read at startup. | Optional |
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.