MCP Document Server
Uses Express.js as the web server foundation for serving markdown documents and handling MCP communication
Manages markdown documents locally, providing functionality to list available documents and read their contents with proper formatting
Relies on npm for dependency management, installation and running server commands
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Document Serverlist all available documents"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Server for Document Management
A local development server that provides a simple interface for managing and accessing markdown documents using the Model Context Protocol (MCP).
Features
Serve markdown documents from a local directory
List available documents
Read document contents
Simple and fast local development setup
Support for both direct MCP and SSE communication
Related MCP server: Markdown MCP Server
Project Structure
.
├── documents/ # Directory containing markdown files
├── tools/ # Tool definitions
├── resources/ # Resource templates
├── utils/ # Utility functions
└── server.js # Main server fileSetup
Install dependencies:
npm installCreate a
documentsdirectory in the project root and add your markdown files:
mkdir documentsStart the server:
npm startIn a separate terminal, run the inspector:
npm run inspectUsage
The server provides the following functionality:
List Documents:
Access available markdown files through the inspector
Files are listed with their names (without .md extension)
Read Documents:
Click on any document in the inspector to view its contents
Documents are served with proper markdown formatting
File Management:
Add new markdown files to the
documentsdirectoryFiles are automatically detected and made available
Only
.mdfiles are supported
Development
The server uses:
Express.js for the web server
Model Context Protocol (MCP) for communication
SSE (Server-Sent Events) for real-time updates
Direct MCP communication for simple requests
Error Handling
The server includes:
Automatic port conflict resolution
Graceful error handling for file operations
Connection management for SSE
Proper cleanup of resources
Notes
This is a local development server, not intended for production use
No security measures are implemented as it's meant for local use only
File operations are optimized for quick access and response
lv.
Available Tools
2 toolsaddD
| Name | Required | Description | Default |
|---|---|---|---|
| a | Yes | ||
| b | Yes |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
test_docs_pathD
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
TDQS
The two tools 'add' and 'test_docs_path' have no descriptions, making their purposes unclear. 'add' is extremely vague and could refer to many operations, while 'test_docs_path' suggests a testing function, but without descriptions, it's impossible to determine if they overlap or serve distinct roles. The lack of clarity creates significant ambiguity.
The tool names show inconsistency: 'add' uses a simple verb with no noun, while 'test_docs_path' uses a snake_case pattern with a verb-noun structure. This mixing of conventions (simple verb vs. descriptive snake_case) makes the naming unpredictable and chaotic, lacking a coherent pattern across the set.
With only 2 tools and no descriptions, it's difficult to assess the server's purpose, but based on the server name 'MCP Document Server', this count feels too thin for a document management domain. A document server typically requires more operations (e.g., create, read, update, delete, search), making 2 tools insufficient and poorly scoped.
Inferred from the server name, a document server should cover basic CRUD operations and document lifecycle management. With only vague tools like 'add' and 'test_docs_path', there are severe gaps—no clear ways to retrieve, update, delete, or search documents. This surface is highly incomplete and will likely cause agent failures in handling document-related tasks.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Document-to-Markdown MCP server — convert PDF, Office and HTML into LLM-ready Markdown.
Publish and share access-controlled Markdown documents from any MCP-enabled AI tool.
Markdown-based note-taking with a hosted MCP server. Your notes serve you and your AI.
Read-only MCP server for the OrchestKit docs: full-text search + Markdown fetch. No auth.
Related MCP Servers
- AlicenseCqualityDmaintenanceMCP protocol server for managing multi-project Markdown documents, supporting project isolation and LLM tool integration.29254MIT
- FlicenseNot gradedqualityDmaintenanceAn MCP (Model Context Protocol) server for efficiently managing Markdown documents in Cursor AI IDE, supporting CRUD operations, search, and metadata management.
- AlicenseAqualityDmaintenanceA Model Context Protocol (MCP) server that provides a local-first RAG engine for your markdown documents. It uses a file-based Milvus vector database to index your notes, enabling LLMs to perform semantic search and retrieve relevant content from your local files.359Apache 2.0
- AlicenseAqualityDmaintenanceMCP server for managing product documentation as markdown files. Supports creating, reading, updating, deleting, and searching docs with optional semantic search.714MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/motiondesignlv/MCP_server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server