PDF MCP Server
Reads PDF files from local disk and returns their text and positional structure to an LLM host over stdio.
README
MCP Servers
A monorepo of Model Context Protocol servers. Each server under packages/ is an independently buildable, testable, and publishable MCP server that runs over stdio.
Packages
| Package | Description |
|---|---|
@jeius-mcp-servers/pdf |
Reads PDF files from local disk; returns text and positional structure to an LLM host over stdio. |
@jeius-mcp-servers/runner |
Internal runner (mcp-serve) that builds and runs any server in the workspace by name. Not a server itself. |
Quickstart
pnpm install
pnpm build
pnpm test
pnpm lint
Requires Node >=22 and pnpm (managed via corepack — the packageManager field in the root package.json pins the exact version).
Usage
Servers are run through the runner binary, mcp-serve, which the root delegates to with pnpm serve <name>.
Run a server (builds first, then runs over stdio):
pnpm serve pdf
Develop a server (watches src/, rebuilds, and respawns on a clean rebuild; keeps the last-good server running on a compile error):
pnpm serve pdf --dev
Skip the build precondition when you know the build is current (run-only; ignored by --dev):
pnpm serve pdf --no-build
Point an MCP host at a server by invoking the mcp-serve bin directly with the server name as the argument:
{
"mcpServers": {
"pdf": {
"command": "/absolute/path/to/node_modules/.bin/mcp-serve",
"args": ["pdf"]
}
}
}
A typo'd name prints the list of known servers to stderr and exits non-zero.
Repository layout
.
├── packages/
│ ├── pdf/ # @jeius-mcp-servers/pdf
│ └── runner/ # @jeius-mcp-servers/runner (the mcp-serve runner)
├── docs/
│ ├── adr/ # repo-wide Architecture Decision Records
│ └── agents/ # repo-wide agent conventions (issue tracker, domain docs)
├── AGENTS.md # operational guide for AI coding agents (monorepo entry)
├── turbo.json # Turborepo task pipelines
├── tsconfig.base.json # shared TypeScript strict base
├── biome.json # shared lint/format config
└── pnpm-workspace.yaml # workspace definition (packages/*)
Each package has its own AGENTS.md, CONTEXT.md, docs/ (PRD, architecture, tech-stack, plan, adr/), src/, and tests/.
Documentation
- Agent guide:
AGENTS.md - Decisions:
docs/adr/— repo-wide ADRs; package-specific ADRs live inpackages/<name>/docs/adr/ - Domain glossaries: each
packages/<name>/CONTEXT.md
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.