pdf-mcp-server

Provides an MCP server (Rust binary) to search for and download free, DRM-free technical book PDFs, manage a local PDF library, extract text from PDFs, and optionally upload PDFs to Google Drive for use with NotebookLM.

Evaluated Apr 04, 2026 (17d ago)
Repo ↗ Infrastructure mcp pdf text-extraction google-drive developer-tools rust local-library
⚙ Agent Friendliness
44
/ 100
Can an agent use this?
🔒 Security
36
/ 100
Is it safe for agents?
⚡ Reliability
25
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
45
Documentation
55
Error Messages
0
Auth Simplicity
90
Rate Limits
0

🔒 Security

TLS Enforcement
85
Auth Strength
30
Scope Granularity
0
Dep. Hygiene
40
Secret Handling
30

No authentication/authorization controls are described for the MCP server; security relies on local execution. The tool downloads external PDFs (potentially untrusted content) and parses PDFs, which increases the importance of sandboxing and safe PDF handling (not documented here). Google Drive integration exists but details of OAuth scopes, token storage, and secret handling are not provided. TLS for external downloads is not explicitly documented in the provided content.

⚡ Reliability

Uptime/SLA
0
Version Stability
35
Breaking Changes
40
Error Recovery
25
AF Security Reliability

Best When

You want local, agent-driven PDF retrieval and text extraction for technical learning workflows (e.g., Claude/NotebookLM) and you are comfortable running a locally built binary.

Avoid When

You need authenticated, audited, multi-tenant access or you require strict guarantees about source authenticity, licensing, and content safety.

Use Cases

  • Searching for technical book PDFs by keyword and retrieving a downloadable PDF
  • Maintaining a local library of downloaded PDFs for downstream Q&A
  • Extracting text from a downloaded PDF for indexing or analysis
  • Uploading PDFs to Google Drive to connect with NotebookLM

Not For

  • Accessing or distributing DRM-protected (copy-protected) PDFs
  • Compliance/legal assurance for copyrighted works (the README claims DRM-free sources but the tool itself cannot guarantee legality)
  • Production-grade document delivery behind a public API gateway (this appears to be a local MCP server setup)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Google Drive OAuth / configuration (implied via CONFIG_GUIDE.md, not shown in provided README)
OAuth: No Scopes: No

The README does not describe any auth mechanism for the MCP server itself. Google Drive integration is described as requiring additional configuration, but OAuth/scopes are not detailed in the provided content.

Pricing

Free tier: No
Requires CC: No

Self-hosted open-source tool (MIT). No pricing information provided.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • No documented MCP tool schemas in the provided README content; agent interoperability depends on the server's actual tool definitions.
  • Downloading is driven by URLs sourced from search results; agents should be careful about repeated downloads and overwriting local files.
  • Text extraction and Drive uploads can be slow and may require waiting/retries, but retry/idempotency behavior is not documented.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for pdf-mcp-server.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-04-04.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered