ext-apps/examples/pdf-server
Repository files (latest commit first)
Filename Latest commit message Latest commit date
Olivier Chafik 281a26b021
pdf-server: robust path validation + folder/file root support (#497)
* pdf-server: support folders in cli + files in roots

* fix(pdf-server): use path.relative for robust ancestor dir matching

- Replace string prefix matching (startsWith) with path.relative-based
  isAncestorDir() which correctly handles trailing slashes, path
  normalization, and prevents both .. traversal and prefix attacks.
- Use path.resolve consistently when adding paths to allowedLocalFiles
  and allowedLocalDirs (main.ts was missing this).
- Use resolved path for exact file match check in validateUrl.
- Improve error message formatting for easier debugging.
- Add tests for trailing slashes, grandparent dirs, and isAncestorDir.

* chore(pdf-server): remove JSONL interaction logging

Remove the withLogging transport wrapper, logInteraction helper,
InteractionLogger type, and all log parameter threading that were
added for debugging.

* fix(pdf-server): support computer:// URL scheme for local files

Some clients (e.g. Claude Code) use computer:// instead of file://
for local file references. Handle both schemes in isFileUrl and
fileUrlToPath.

* fix(pdf-server): add debug logging for rejected files, ignore .jsonl logs

* fix(pdf-server): accept bare file paths in addition to file:// URLs

Clients like Claude Desktop may pass raw absolute paths (e.g.
/Users/.../file.pdf) instead of file:// URLs. Handle these in
validateUrl and readPdfRange.

* debug(pdf-server): add hex char diagnostics for path mismatch

* fix(pdf-server): resolve symlinks to handle sandbox path remapping

Use fs.realpathSync to resolve symlinks/bind mounts when comparing
file paths against allowed directories. This fixes the path namespace
mismatch where Claude Desktop sends container paths (e.g. /sessions/...)
while MCP roots use host paths (e.g. /Users/...).

Both the file path and directory paths are resolved through symlinks
before comparison, so either side can be a symlink.

Also stores realpath of roots in allowedLocalDirs/Files so matching
works in both directions.

Removes verbose hex diagnostics (no longer needed).

* fix(pdf-server): decode percent-encoded bare paths (e.g. %20 for spaces)

Clients may send bare file paths with percent-encoded characters
(e.g., Application%20Support). Apply decodeURIComponent to bare paths
before resolving, matching the behavior already used for file:// URLs.

* fix(pdf-server): add full diagnostics to client-facing error message

Include url, resolved path, realpath, allowedFiles, and per-directory
path.relative results in the error returned to the client, so we can
diagnose why isAncestorDir fails when paths look identical.

* debug(pdf-server): add hex dump to diagnose invisible char differences

path.relative returns 10 levels of .. despite paths looking identical,
meaning they differ at the byte level. Add hex dump of first 30 chars
of both paths to catch invisible Unicode or encoding differences.

* fix(pdf-server): use inode comparison for bind-mount path matching

The cowork VM remaps paths via bind mounts: the tool input uses
VM-internal paths (/sessions/...) while MCP roots use host paths
(/Users/...). Since path.relative can't match across bind mounts,
compare directory inodes instead (dev+ino from fs.statSync).

Walks up the file's parent directories checking each against allowed
dirs by inode, which works regardless of path namespace differences.

* fix(pdf-server): resolve VM-internal paths via directory basename matching

When the MCP server runs on the host but receives unrewritten VM paths
(e.g., /sessions/name/mnt/uploads/file.pdf), the tool call url argument
isn't rewritten by the cowork VM proxy because it doesn't know which
arguments are file paths.

Fix: when path validation fails, try to match the file by finding the
directory basename (e.g., 'uploads') in the VM path and looking for
the relative path suffix under each allowed directory on the host.

Also returns the resolved host path so readPdfRange reads the correct
file on the host filesystem.

* revert(pdf-server): remove resolveVmPath hack

The VM path mismatch (VM-internal paths not rewritten in tool call
arguments) should be fixed in the cowork VM proxy layer, not worked
around in the MCP server.

Removes:
- resolveVmPath() function
- resolvedPath field from validateUrl return type
- effectiveUrl remapping in tool handlers
- VM path resolution test

* nit
2026-02-24 18:23:57 +00:00
..
plugin Add MCPB packaging and Claude Code plugin for pdf-server (#491) 2026-02-24 00:51:43 +00:00
src fix(pdf-server): remove page-loading overlay (#493) 2026-02-23 21:25:25 +00:00
.gitignore pdf-server: robust path validation + folder/file root support (#497) 2026-02-24 18:23:57 +00:00
.mcpbignore pdf-server: robust path validation + folder/file root support (#497) 2026-02-24 18:23:57 +00:00
grid-cell.png examples: add PDF viewer w/ chunked data loading, full-screen, model context updates, private tool (#267) 2026-01-14 14:25:24 +00:00
icon.png Add MCPB packaging and Claude Code plugin for pdf-server (#491) 2026-02-24 00:51:43 +00:00
main.ts pdf-server: robust path validation + folder/file root support (#497) 2026-02-24 18:23:57 +00:00
manifest.json Add MCPB packaging and Claude Code plugin for pdf-server (#491) 2026-02-24 00:51:43 +00:00
mcp-app.html feat(pdf-server): lazy range-based loading + eager background preloading (#480) 2026-02-21 16:33:48 -08:00
package.json chore: bump ext-apps to 1.1.1 (#496) 2026-02-24 02:39:24 +00:00
pdf-icon.svg Adding a simple (bad) pdf icon for directory (#330) 2026-01-23 16:04:46 +00:00
README.md feat(app): throw helpful error when callServerTool is called with a string (#449) 2026-02-13 21:05:21 +00:00
screenshot.png examples: add PDF viewer w/ chunked data loading, full-screen, model context updates, private tool (#267) 2026-01-14 14:25:24 +00:00
server.test.ts pdf-server: robust path validation + folder/file root support (#497) 2026-02-24 18:23:57 +00:00
server.ts pdf-server: robust path validation + folder/file root support (#497) 2026-02-24 18:23:57 +00:00
tsconfig.json feat(pdf-server): lazy range-based loading + eager background preloading (#480) 2026-02-21 16:33:48 -08:00
tsconfig.server.json feat: compile example servers to JavaScript for npm consumption (#259) 2026-01-14 23:46:17 +00:00
vite.config.ts examples: add PDF viewer w/ chunked data loading, full-screen, model context updates, private tool (#267) 2026-01-14 14:25:24 +00:00

PDF Server

Screenshot

An interactive PDF viewer using PDF.js. Supports local files and remote URLs from academic sources (arxiv, biorxiv, zenodo, etc).

MCP Client Configuration

Add to your MCP client configuration (stdio transport):

{
  "mcpServers": {
    "pdf": {
      "command": "npx",
      "args": [
        "-y",
        "--silent",
        "--registry=https://registry.npmjs.org/",
        "@modelcontextprotocol/server-pdf",
        "--stdio"
      ]
    }
  }
}

Local Development

To test local modifications, use this configuration (replace ~/code/ext-apps with your clone path):

{
  "mcpServers": {
    "pdf": {
      "command": "bash",
      "args": [
        "-c",
        "cd ~/code/ext-apps/examples/pdf-server && npm run build >&2 && node dist/index.js --stdio"
      ]
    }
  }
}

What This Example Demonstrates

1. Chunked Data Through Size-Limited Tool Calls

On some host platforms, tool calls have size limits, so large PDFs cannot be sent in a single response. This example streams PDFs in chunks using HTTP Range requests:

Server side (server.ts):

// Returns chunks with pagination metadata
{
  (bytes, offset, byteCount, totalBytes, hasMore);
}

Client side (mcp-app.ts):

// Load in chunks with progress
while (hasMore) {
  const chunk = await app.callServerTool({
    name: "read_pdf_bytes",
    arguments: { url, offset },
  });
  chunks.push(base64ToBytes(chunk.bytes));
  offset += chunk.byteCount;
  hasMore = chunk.hasMore;
  updateProgress(offset, chunk.totalBytes);
}

2. Model Context Updates

The viewer keeps the model informed about what the user is seeing:

app.updateModelContext({
  content: [
    {
      type: "text",
      text: `PDF viewer | "${title}" | Current Page: ${page}/${total}\n\nPage content:\n${pageText}`,
    },
  ],
});

This enables the model to answer questions about the current page or selected text.

3. Display Modes: Fullscreen vs Inline

  • Inline mode: App requests height changes to fit content
  • Fullscreen mode: App fills the screen with internal scrolling
// Request fullscreen
app.requestDisplayMode({ mode: "fullscreen" });

// Listen for mode changes
app.ondisplaymodechange = (mode) => {
  if (mode === "fullscreen") enableScrolling();
  else disableScrolling();
};

The viewer demonstrates opening external links (e.g., to the original arxiv page):

titleEl.onclick = () => app.openLink(sourceUrl);

5. View Persistence

Page position is saved per-view using viewUUID and localStorage.

6. Dark Mode / Theming

The viewer syncs with the host's theme using CSS light-dark() and the SDK's theming APIs:

app.onhostcontextchanged = (ctx) => {
  if (ctx.theme) applyDocumentTheme(ctx.theme);
  if (ctx.styles?.variables) applyHostStyleVariables(ctx.styles.variables);
};

Usage

# Default: loads a sample arxiv paper
bun examples/pdf-server/main.ts

# Load local files (converted to file:// URLs)
bun examples/pdf-server/main.ts ./docs/paper.pdf /path/to/thesis.pdf

# Load from URLs
bun examples/pdf-server/main.ts https://arxiv.org/pdf/2401.00001.pdf

# Mix local and remote
bun examples/pdf-server/main.ts ./local.pdf https://arxiv.org/pdf/2401.00001.pdf

# stdio mode for MCP clients
bun examples/pdf-server/main.ts --stdio ./papers/

Allowed Sources

  • Local files: Must be passed as CLI arguments
  • Remote URLs: arxiv.org, biorxiv.org, medrxiv.org, chemrxiv.org, zenodo.org, osf.io, hal.science, ssrn.com, and more

Tools

Tool Visibility Purpose
list_pdfs Model List available local files and origins
display_pdf Model + UI Display interactive viewer
read_pdf_bytes App only Stream PDF data in chunks

Architecture

server.ts      # MCP server + tools
main.ts        # CLI entry point
src/
└── mcp-app.ts # Interactive viewer UI (PDF.js)

Key Patterns Shown

Pattern Implementation
App-only tools _meta: { ui: { visibility: ["app"] } }
Chunked responses hasMore + offset pagination
Model context app.updateModelContext()
Display modes app.requestDisplayMode()
External links app.openLink()
View persistence viewUUID + localStorage
Theming applyDocumentTheme() + CSS light-dark()

Dependencies

  • pdfjs-dist: PDF rendering (frontend only)
  • @modelcontextprotocol/ext-apps: MCP Apps SDK