PDF Reader MCP
Reads and searches PDFs with OCR, table extraction, document structure, page citations, and focused visual evidence tools.
What it provides
Connect an existing HTTPS deployment, with a scoped token where the service requires one. Heavy jobs stay on that service instead of using bot memory.
Connection requirements
Self-host PDF Reader MCP in HTTP mode with MCP_TRANSPORT=http and MCP_API_KEY set, then publish /mcp through an authenticated TLS reverse proxy. Keep X-API-Key selected and paste the same MCP_API_KEY below. Use URL sources for PDFs; local paths refer to the PDF Reader server, not the bot. Restrict filesystem access with MCP_PDF_ALLOWED_DIRS or --allow-dir.
- Protocol
- Streamable HTTP MCP
- Endpoint
https://pdf-reader.example.com/mcp- Authentication
- x-api-key
mcp call read_pdf {"sources":[{"url":"https://example.com/report.pdf"}]}mcp call search_pdf {"sources":[{"url":"https://example.com/report.pdf"}],"query":"revenue"}Where to add it
Open Dashboard Tools, select a running OpenClaw or Hermes instance, then use the card’s Install or Connect action. External services may require an HTTPS endpoint and credentials; the dashboard shows those fields before anything is saved.