MCP.Market

Bigapi MCP server

by bigapi.dev·dev.bigapi/mcp·v0.8.2

The output layer for AI agents: turn what an agent produced into a finished file.

B75/100grade B
What users say
No reviews yet
Be the first
Safety scan
B75/100

full report

Adoption
Growing

0 stars103 downloads/wk

Reviews

Write one

Nobody has reviewed Bigapi yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Bigapi tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.10 · 2026-10-02 · same rubric, same numbers if you re-run it

no findings
  • Code scan3 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 14 days ago15/15
  • Maintainer identitynamespace and repository owner differ3/10
Overall 75/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Bigapi compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
75/100
higher than 45% of 4,460 AI and agents servers
Downloads a week
103
more than 65% of 1,538 AI and agents servers with a package

Release history: 3 versions in the registry since 2026-09-15, latest 2026-09-19, typically one every 3 days.

Install Bigapi in Claude Code, Cursor or VS Code

Runs npx -y @bigapi/mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add mcp -- npx -y @bigapi/mcp
Add to Cursor

What the publisher says

From the Bigapi repository's README, as published. We do not edit it. Read it on GitHub

@bigapi/mcp

MCP server for bigapi.dev – the output layer for AI agents.

Your agent produced something. bigapi turns it into a finished file – and reads files back in. Merge, redact, OCR, convert, sign, validate: the operations an LLM cannot do itself, over plain HTTPS, with one key, nothing to install server-side.

$0.01 per operation. 100 free. Free operations and balance never expire. Failed calls are free. Servers in Germany, GDPR, files deleted after delivery. Every operation ships with a published proof that it does what it promises.

Also listed in the official MCP Registry as dev.bigapi/mcp.

Lean by default

The server starts lean: it lists five tools, so your context stays free.

All 40+ operations are available from the first second through runoperation; the dedicated tools are a convenience, not a requirement. Want the full list right away? Set BIGAPITOOLS=all in the server environment.

Why: every tool definition costs context in your client, and a model choosing between five descriptions picks better than one scanning forty-six.

What you can run

All 40+ operations go through runoperation (or their own tool after enabletools). Ask find_tool in plain words instead of memorising this list:

  • PDF basics — merge, split, rotate, compress, page info, outline, compare, linearize
  • PDF content — to Markdown, to images, extract tables, extract attachments (ZUGFeRD / Factur-X invoice XML)
  • PDF safety — redact (rasterise and rebuild, text provably gone), sanitize (JavaScript, actions, embedded files), password on/off, verify signature
  • PDF archival — PDF/A-2b with embedded fonts and an output intent, checked with veraPDF
  • Documents — Office and e-books to PDF or Markdown (DOCX, XLSX, PPTX, ODT, EPUB), Markdown to Word, .eml to PDF
  • Web and rendering — HTML/Markdown/URL to PDF or PNG, full-page screenshots with device presets, HTML or URL to clean Markdown, Handlebars templates, charts, QR codes
  • Images — resize, crop, convert (WebP/AVIF/…), compress, strip metadata, watermark, image info
  • AI transparency — C2PA Content Credentials sign and verify, visible "AI-generated" label with EXIF marking (EU AI Act Art. 50)
  • Text for RAG — token-based chunking, heading-aware, with overlap
  • Account — free key, balance, usage, monthly cap, pricing

Install

Requires Node 18+. No API key needed up front – the agent can call get_access itself.

Claude Desktop

claudedesktopconfig.json (Settings → Developer → Edit Config):

{
  "mcpServers": {
    "bigapi": {
      "command": "npx",
      "args": ["-y", "@bigapi/mcp"]
    }
  }
}

Restart Claude Desktop. Then: "Get bigapi access and render this text as a PDF on my Desktop."

Cursor / Windsurf / Cline

Same block in the respective MCP settings (.cursor/mcp.json, ~/.codeium/windsurf/mcp_config.json, Cline → MCP Servers → Configure).

With an existing key

"bigapi": { "command": "npx", "args": ["-y", "@bigapi/mcp"], "env": { "BIGAPI_KEY": "bigapi_..." } }

How files work

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Bigapi: common questions

Is Bigapi MCP server safe?
Mostly: it is graded B (75/100). Read the Bigapi safety report
How do I install Bigapi?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Bigapi need an API key?
Yes. The registry entry asks for BIGAPI_KEY.
Is Bigapi maintained?
The last commit was 46 days ago (2026-09-19). The latest release is v0.8.2.
What can I use instead of Bigapi?
Servers from other publishers that do the same job: agent-device MCP server, Basic Memory MCP server and Agent Recall MCP server.
How does Bigapi compare with other AI and agents MCP servers?
safety score 75/100 (higher than 45% of 4,460 AI and agents servers); downloads a week 103 (more than 65% of 1,538 AI and agents servers with a package). Full comparison.

Alternatives to Bigapi

Same job from other publishers: the closest match first, then the best rated.

  • agent-device
    Open source device layer for AI agents: control mobile, web, TV, and desktop apps over MCP
    A
  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • Agent Recall
    Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.
    A
  • llmtrim
    MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.
    A
  • Openflowkit
    Architecture diagrams for your agent: draw on the live OpenFlowKit canvas or edit diagram files.
    A