AgentIndex icon
AgentIndex
pdf-mcp logo
pdf-mcp
★ 155
vs
codegraph logo
codegraph
★ 99

pdf-mcp vs codegraph

pdf-mcp: pdf-mcp is a Model Context Protocol (MCP) server that enables AI agents to read, search, and extract content from PDF files. It uses PyMuPDF for PDF parsing, SQLite for persistent caching, and supports hybrid search combining BM25 keyword and semantic embeddings, OCR for scanned documents, and structured extraction of tables and images.; codegraph: Codegraph provides AI coding assistants with an always-current, function-level dependency graph of an entire codebase, built locally and open source. This allows AI to understand code structure instantly, reducing token waste and improving accuracy for complex tasks like refactoring and debugging.

01

TL;DR

pdf-mcp logo
pdf-mcpVision / Multimodal · ★ 155

Efficiently read and analyze large PDF documents without exceeding context limits

Read pdf-mcp full review →
codegraph logo
codegraphVision / Multimodal · ★ 99

Improve AI agent's understanding of codebase structure, eliminating repeated re-orientation.

Read codegraph full review →
02

Side-by-Side Comparison

Field
pdf-mcp logopdf-mcp
codegraph logocodegraph
Category
Vision / Multimodal
Vision / Multimodal
Stars
★ 155
★ 99
License
MIT
Apache-2.0
Install Command
pip install pdf-mcp
npm install -g @optave/codegraph
Updated
1w ago
2d ago
Open Source
Yes
Yes
Website
↗ Visit
↗ Visit
GitHub
↗ GitHub
↗ GitHub
Tags
agentic-ai, ai, claude
AI Coding Assistant, Code Analysis, Dependency Graph
03

Features

pdf-mcp logopdf-mcp
01Hybrid search (BM25 keyword + semantic embeddings) with Reciprocal Rank Fusion
02Paginated reading to avoid context overflow
03OCR support for scanned and image-based PDFs via Tesseract
04Structured extraction of tables, images, and table of contents
05Persistent SQLite cache with automatic invalidation
codegraph logocodegraph
01Sub-second incremental rebuilds for an always-fresh dependency graph.
02Function-level code analysis, tracing calls and dependencies within and across files.
03Built for AI agents with a 19-tool Model Context Protocol (MCP) server for direct querying.
04Git diff impact analysis to show affected functions and callers from staged or unstaged changes.
05Embeddings-powered local semantic search for natural language queries.
04

Use Cases

pdf-mcp logopdf-mcp
↳Efficiently read and analyze large PDF documents without exceeding context limits
↳Search for specific content or concepts within PDFs using natural language
↳Extract structured data such as tables and images from PDFs
codegraph logocodegraph
↳Improve AI agent's understanding of codebase structure, eliminating repeated re-orientation.
↳Perform impact analysis before code changes, preventing silent bugs and dependency breakage.
↳Identify dead code and classify architectural roles (e.g., entry, core, utility) of symbols.
↳Facilitate semantic search for functions by natural language intent rather than exact names.
↳Detect and visualize circular dependencies at file or function levels to improve code quality.
FAQ

FAQ

What is the difference between pdf-mcp and codegraph?
Both pdf-mcp and codegraph are in the Vision / Multimodal category. pdf-mcp has 155 stars, while codegraph has 99 stars.
Which is better, pdf-mcp or codegraph?
The best choice depends on your use case. Choose pdf-mcp if Efficiently read and analyze large PDF documents without exceeding context limits, and codegraph if Improve AI agent's understanding of codebase structure, eliminating repeated re-orientation..
Is pdf-mcp free or open source?
Yes, pdf-mcp is open source on GitHub (MIT).
Is codegraph free or open source?
Yes, codegraph is open source on GitHub (Apache-2.0).
Cloud Infrastructure
Ad

Deploy on DigitalOcean

Host your MCP servers, Docker containers, and AI agents with $200 free credit over 60 days.

Claim $200 Free Credit
→

Related

Alternatives to pdf-mcp →Alternatives to codegraph →pdf-mcp details →codegraph details →