by talljack
Content Manager offers powerful knowledge base software for managing markdown docs with advanced search, analytics, and
An MCP server that manages and searches through markdown files using fuzzy search, frontmatter parsing, and HTML rendering. It provides content analysis and navigation tools for documentation and knowledge base systems.
Content Manager is a community-built MCP server published by talljack that provides AI assistants with tools and capabilities via the Model Context Protocol. Content Manager offers powerful knowledge base software for managing markdown docs with advanced search, analytics, and It is categorized under productivity.
You can install Content Manager in your AI client of choice. Use the install panel on this page to get one-click setup for Cursor, Claude Desktop, VS Code, and other MCP-compatible clients. This server runs locally on your machine via the stdio transport.
MIT
Content Manager is released under the MIT license. This is a permissive open-source license, meaning you can freely use, modify, and distribute the software.
Add new capabilities to Claude beyond text generation
Example
Access external data sources, execute code, interact with tools and services
Transform Claude from chatbot to action-taking agent
Provide Claude with access to relevant context and data
Example
Load project documentation, access knowledge bases, query databases
Get more accurate, context-aware responses
Automate multi-step workflows combining AI and external tools
Example
Research → Summarize → Create document → Send notification
Complete complex tasks end-to-end without manual steps
Share your MCP server with the developer community
Content Manager is among the better-indexed MCP projects we tried; the explainx.ai summary tracks the official description.
According to our notes, Content Manager benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
Useful MCP listing: Content Manager is the kind of server we cite when onboarding engineers to host + tool permissions.
Content Manager has been reliable for tool-calling workflows; the MCP profile page is a good permalink for internal docs.
We wired Content Manager into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
Strong directory entry: Content Manager surfaces stars and publisher context so we could sanity-check maintenance before adopting.
We evaluated Content Manager against two servers with overlapping tools; this profile had the clearer scope statement.
We wired Content Manager into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
According to our notes, Content Manager benefits from clear Model Context Protocol framing — fewer ambiguous “AI plugin” claims.
We wired Content Manager into a staging workspace; the listing’s GitHub and npm pointers saved time versus hunting across READMEs.
showing 1-10 of 75
A comprehensive TypeScript-based Model Context Protocol (MCP) server for content management, including Markdown processing, document generation, and intelligent note searching.
# Install globally
npm install -g content-manager-mcp
# Or use directly with npx
npx -y content-manager-mcp
# Clone and install dependencies
git clone <repository-url>
cd content-manager-mcp
pnpm install
# Build the project
pnpm build
# Run in development mode
pnpm dev
The server runs via stdio and implements the MCP protocol:
# If installed globally
content-manager-mcp
# Using npx (no installation required)
npx -y content-manager-mcp
node dist/index.js
Add to your Claude Desktop configuration:
{
"mcpServers": {
"content-manager": {
"command": "npx",
"args": ["-y", "content-manager-mcp"]
}
}
}
Configure MCP server:
npx["-y", "content-manager-mcp"]Add to your Codex MCP servers configuration:
{
"mcpServers": {
"content-manager": {
"command": "npx",
"args": ["-y", "content-manager-mcp"]
}
}
}
Add MCP server using Claude Code CLI:
# Add content-manager-mcp server to Claude Code
claude mcp add content-manager -- npx -y content-manager-mcp
# Or if you prefer to install globally first
npm install -g content-manager-mcp
claude mcp add content-manager -- content-manager-mcp
Install the MCP extension and configure:
settings.json):{
"mcp.servers": {
"content-manager": {
"command": "npx",
"args": ["-y", "content-manager-mcp"]
}
}
}
Configure MCP server in Cursor settings:
content-managernpx["-y", "content-manager-mcp"]Or add to Cursor's settings.json:
{
"mcp.servers": {
"content-manager": {
"command": "npx",
"args": ["-y", "content-manager-mcp"]
}
}
}
render_markdownConverts Markdown content to HTML with optional features:
{
content: string, // Markdown content to render
generateToc?: boolean, // Generate table of contents (default: true)
sanitizeHtml?: boolean, // Sanitize output HTML (default: true)
enableCodeHighlight?: boolean // Enable syntax highlighting (default: true)
}
search_notesIntelligent search through content files:
{
query: string, // Search query
directory?: string, // Directory to search (default: cwd)
includeContent?: boolean, // Include file content in results (default: true)
maxResults?: number, // Maximum results to return (default: 10)
fuzzy?: boolean // Use fuzzy search (default: true)
}
search_by_tagsFind files by frontmatter tags:
{
tags: string[], // Array of tags to search for
directory?: string // Directory to search (default: cwd)
}
search_by_date_rangeFind files by modification date:
{
startDate: string, // ISO date string (YYYY-MM-DD)
endDate: string, // ISO date string (YYYY-MM-DD)
directory?: string // Directory to search (default: cwd)
}
generate_table_of_contentsExtract and format headings as a table of contents:
{
content: string // Markdown content to analyze
}
extract_headingsGet structured heading information:
{
content: string // Markdown content to analyze
}
extract_frontmatterParse YAML frontmatter from Markdown:
{
content: string // Markdown content with frontmatter
}
get_directory_statsAnalyze directory content statistics:
{
directory?: string // Directory to analyze (default: cwd)
}
find_content_filesDiscover files with specific extensions:
{
directory?: string, // Directory to search (default: cwd)
extensions?: string[] // File extensions (default: ['.md', '.markdown', '.txt', '.mdx'])
}
read_content_fileRead and parse a single content file:
{
filePath: string // Path to file to read
}
pnpm dev - Development mode with watchpnpm build - Build for productionpnpm start - Run built serverpnpm lint - Check code stylepnpm lint:fix - Fix code style issuespnpm type-check - TypeScript type checkingpnpm clean - Clean build artifactsThis project leverages Zod for runtime validation combined with TypeScript for compile-time safety. All tool arguments are validated at runtime, ensuring robust error handling and type safety.
The server recognizes YAML frontmatter in Markdown files:
---
title: My Document
tags: [typescript, mcp, documentation]
author: Your Name
date: 2024-01-15
---
# Document Content
Your markdown content here...
query: "typescript mcp" (finds related content)query: "exact phrase", fuzzy: falsetags: ["typescript", "documentation"]startDate: "2024-01-01", endDate: "2024-12-31"This package is published to NPM as @yugangcao/content-manager-mcp. To publish a new version:
# Build the project
pnpm build
# Update version (patch/minor/major)
npm version patch
# Publish to NPM
npm publish
For detailed publishing instructions, see PUBLISH_TO_NPM.md.
git checkout -b feature-namepnpm type-checkMIT License - see LICENSE file for details.
Built with ❤️ using TypeScript, Zod, and the latest modern tooling for robust content management.
Prerequisites
Time Estimate
15-60 minutes depending on server complexity
Steps
Troubleshooting
✓ Do
✗ Don't
💡 Pro Tips
Architecture
Model Context Protocol standardizes how AI hosts (Claude, Cursor) communicate with external tools and data sources through server implementations.
Protocols
Compatibility
✓ Use when
Use when you need Claude to access external data, execute actions, or integrate with tools. Best for extending AI capabilities beyond conversation.
✗ Avoid when
Avoid when native integrations exist (use official APIs directly), for real-time critical systems, or when security/compliance requires zero external dependencies.