PDFSAFE
PDF MCP server with image rendering capabilities. Useful for automatically searching datasheets, manuals, etc...
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
An MCP server for reading, rendering, and searching PDF files. Built with PyMuPDF and PyMuPDF4LLM.
Designed for use with LLMs that need to read datasheets and other PDFs containing diagrams, tables, and technical content.
Tools
All requests are stateless and take the PDF filename as a parameter.
Setup
Add the following to your .mcp.json:
{
"mcpServers": {
"pdf-mcp": {
"command": "uvx",
"args": ["--from", "git+https://github.com/I-CAN-hack/pdf-mcp.git", "pdf-mcp"]
}
}
}Or for codex run codex mcp add pdf-mcp -- uvx --from git+https://github.com/I-CAN-hack/pdf-mcp.git pdf-mcp.
This will automatically install and run the server using uvx.
Development
# Install dependencies uv sync # Generate test PDFs uv run python assets/generate.py # Run tests uv run pytest tests/ -v # Run the server locally uv run pdf-mcp
9ce7a55fc0c8OBSERVED · 2026-10-08Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control.
claude mcp add pdf-mcp -- uvx pdf-mcp
{
"mcpServers": {
"pdf-mcp": {
"command": "uvx",
"args": [
"pdf-mcp"
]
}
}
}Exposed tools (5)
5 read · 0 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
get_page_image | read | Render a single PDF page as a PNG image. |
get_page_text | read | Extract text content from one or more PDF pages. |
get_pdf_info | read | Get metadata and basic info about a PDF file. |
get_table_of_contents | read | Get the table of contents (bookmarks/outline) from a PDF. |
search_text | read | Search for text in a PDF file (case-insensitive). |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | WARN |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
page1.insert_text((72, 110), "The resistance of R1 is 10kΩ at 25°C.", fontsize=11)
Gates applied: no_behavioural_pass.
9ce7a55fc0c8full audit observations/trust-audit/mcp-server/i-can-hack__pdf-2.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 9ce7a55fc0c8 | SAFE | B | 89 | first audit |
Questions
What is the PDF MCP server?
PDF MCP server with image rendering capabilities. Useful for automatically searching datasheets, manuals, etc...
What tools does PDF expose?
5 in total: 5 read-only, 0 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is PDF safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does PDF need?
No credential environment variables were found in its source, so it appears to need none.
How current is this page?
The grade is for one exact copy of the source (9ce7a55fc0c8), read on 2026-10-08. The repository is watched and re-audited when it changes.