How do I use mcp-docs-helper?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-docs-helper show me the template for a basic server" 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-docs-helper

by CHIRANTH-24

Overview Schema Source Related Servers Discussions Admin

TypeScript

Local

MCP Documentation Helper

An AI-powered developer tool that provides LLMs with instant access to MCP protocol specifications and TypeScript SDK documentation.

Overview

MCP Documentation Helper is a Model Context Protocol (MCP) server that exposes comprehensive MCP documentation as structured resources. It enables AI assistants like Claude to provide accurate, context-aware guidance when building custom MCP servers.

Features

📚 Complete Documentation Access - Full MCP protocol specification and TypeScript SDK docs
🔍 Context-Aware Search - Intelligent search with relevance scoring and focused results
📋 Code Templates - Ready-to-use implementation patterns for common MCP use cases
🎯 Categorized Resources - Quick access to tools, resources, prompts, transports, and examples
🤖 AI-Optimized - Designed specifically for LLM-assisted development workflows

Related MCP server: MCP Documentation Server

Prerequisites

Node.js 18+ or Bun
An MCP client (Claude Desktop, Cursor, or any MCP-compatible client)

Installation

1. Clone the Repository

git clone https://github.com/yourusername/mcp-documentation-helper.git
cd mcp-documentation-helper

2. Install Dependencies

Using npm:

npm install

Using Bun:

bun install

That's it! The repository includes all necessary MCP documentation files in the data directory.

Usage

Running Locally

Using npm:

npm run dev

Using Bun:

bun run dev

Using Node directly (after building):

npm run build
npm run start

Connecting to Claude Desktop

Open your Claude Desktop configuration file:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json
- Linux: ~/.config/Claude/claude_desktop_config.json
Add the MCP server configuration:

For npm/Node:

{
  "mcpServers": {
    "mcp-docs": {
      "command": "node",
      "args": [
        "/absolute/path/to/mcp-documentation-helper/build/index.js"
      ]
    }
  }
}

For Bun:

{
  "mcpServers": {
    "mcp-docs": {
      "command": "bun",
      "args": [
        "index.ts"
      ],
      "cwd": "/absolute/path/to/mcp-documentation-helper"
    }
  }
}

Replace /absolute/path/to/mcp-documentation-helper with your actual project path
Restart Claude Desktop

Connecting to Cursor

Open Cursor Settings → MCP Servers
Click "Add MCP Server"
Configure the server:

For npm/Node:

{
  "name": "mcp-docs",
  "command": "node",
  "args": [
    "/absolute/path/to/mcp-documentation-helper/build/index.js"
  ]
}

For Bun:

{
  "name": "mcp-docs",
  "command": "bun",
  "args": [
    "index.ts"
  ],
  "cwd": "/absolute/path/to/mcp-documentation-helper"
}

Save and restart Cursor

Using with VS Code (via MCP extension)

Install the MCP extension for VS Code
Add to your workspace settings (.vscode/settings.json):

{
  "mcp.servers": {
    "mcp-docs": {
      "command": "node",
      "args": [
        "/absolute/path/to/mcp-documentation-helper/build/index.js"
      ]
    }
  }
}

Available Resources

Once connected, the following resources are available:

Resource URI	Description
`mcp://docs/complete`	Full MCP protocol and SDK documentation
`mcp://docs/quick-start`	Getting started guide
`mcp://docs/tools`	Tool implementation reference
`mcp://docs/resources`	Resource implementation reference
`mcp://docs/prompts`	Prompt implementation reference
`mcp://docs/transport`	Transport setup (stdio, HTTP, SSE)
`mcp://docs/examples`	Working code examples

Available Tools

search-mcp-docs

Search across all MCP documentation with context-aware results.

Parameters:

query (string): What you want to learn or implement
focus (optional): all, implementation, concepts, examples, or troubleshooting

get-implementation-template

Get code templates for common MCP patterns.

Available Templates:

basic-server - Basic MCP server structure
tool-with-validation - Tool with Zod validation
resource-static - Static resource
resource-dynamic - Dynamic resource with parameters
prompt-simple - Simple prompt template
stdio-server - stdio transport setup
http-server - HTTP transport setup
error-handling - Error handling patterns

Available Prompts

build-server

Start building a new MCP server with guided assistance.

debug-server

Get help debugging an MCP server issue.

Example Usage

Once connected to Claude Desktop or Cursor, you can:

You: "I want to build an MCP server that connects to a PostgreSQL database"

Claude: *Uses mcp-docs resources to provide accurate implementation guidance*

You: "How do I implement a dynamic resource with parameters?"

Claude: *Searches documentation and provides relevant examples*

You: "Show me how to set up an HTTP transport"

Claude: *Retrieves transport documentation and code templates*

Development

Project Structure

mcp-documentation-helper/
├── data/                      # Documentation files
│   ├── llms-full.txt         # MCP protocol documentation
│   └── typescript-sdk-readme.md  # TypeScript SDK docs
├── index.ts                   # Main server implementation
├── package.json              # Dependencies and scripts
└── tsconfig.json             # TypeScript configuration

Scripts

npm run dev - Run in development mode with tsx
npm run build - Build TypeScript to JavaScript
npm run start - Run the built server
bun run dev - Run with Bun (if using Bun)

How It Works

Documentation Parsing: The server parses MCP protocol and SDK documentation into structured sections
Resource Exposure: Documentation is exposed through MCP resources with semantic URIs
Intelligent Search: Built-in search tool provides context-aware results with relevance scoring
Code Templates: Pre-built templates help jumpstart common implementation patterns
AI Integration: LLMs can access documentation through standard MCP protocols

Troubleshooting

Server Not Showing Up in Claude Desktop

Check that the path in the config is absolute, not relative
Verify the data directory contains both required files
Restart Claude Desktop completely
Check Claude Desktop logs for errors

Documentation Files Not Found

The repository includes all necessary documentation files. If you encounter this error:

Ensure you cloned the full repository with all files
Check that the data directory exists with both files:

ls data/
# Should show:
# llms-full.txt
# typescript-sdk-readme.md

Build Errors (Node/npm)

Make sure you've run the build command before starting:

npm run build
npm run start

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

Acknowledgments

Built with the Model Context Protocol SDK
Documentation sourced from modelcontextprotocol.io
Inspired by the Building MCP with LLMs guide

Links

Made with ❤️ for the MCP community

Available Tools

2 tools

get-implementation-templateGet Implementation TemplateC

Get code templates for common MCP patterns

ParametersJSON Schema

Name	Required	Description	Default
`pattern`	Yes	The implementation pattern you need

Output Schema

ParametersJSON Schema

Name	Required	Description
`template`	Yes
`description`	Yes
`relatedDocs`	Yes

TDQS

C2.9/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description should disclose behavioral traits; it only says 'Get code templates,' missing details on safety, idempotency, or possible side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise (one sentence), but could be slightly more informative without losing brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity, the description is minimally acceptable but lacks behavioral and usage context, making it incomplete for decision-making.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with enum descriptions, so the description adds no extra meaning; baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves code templates for MCP patterns, distinguishing it from the sibling 'search-mcp-docs' which searches documentation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, nor any prerequisites or context for invoking it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search-mcp-docsSearch MCP DocumentationB

Search MCP documentation with context-aware results for building servers

ParametersJSON Schema

Name	Required	Description	Default
`focus`	No	Focus area for search results
`query`	Yes	What you want to learn or implement (e.g., "how to create tools", "stdio transport setup")

Output Schema

ParametersJSON Schema

Name	Required	Description
`results`	Yes
`summary`	Yes
`relatedTopics`	Yes

TDQS

B3.1/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden for behavioral traits. It only mentions 'context-aware results' which is vague, and omits details such as read-only nature, rate limits, or authentication requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that is front-loaded with the core purpose. Every word is necessary, and it avoids unnecessary elaboration.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with two parameters and an output schema, the description provides the essential purpose but lacks details on result format, pagination, or error conditions. It is adequate but not fully informative.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the parameters are already documented. The description adds no additional meaning beyond the schema, meeting the baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose (Search MCP documentation) with a specific modifier (context-aware results for building servers). It distinguishes from the sibling tool 'get-implementation-template' implicitly, but lacks explicit differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, nor are there any conditions or exclusions. The description simply states what the tool does without usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

2 tool updatesv1.0.0Jul 28, 2026
- First observedget-implementation-template
- First observedsearch-mcp-docs

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

B3.3/5.0

Scored 2026-07-28 05:35 across 2 tools

Disambiguation5/5

The two tools have clearly distinct purposes: one searches documentation, the other retrieves code templates. There is no overlap or ambiguity.

Naming Consistency5/5

Both tools follow the consistent verb_noun pattern with underscores, making naming predictable and clear.

Tool Count3/5

With only two tools, the server feels minimal for a documentation helper. While the tools are useful, the scope is narrow and may require additional tools for comprehensive coverage.

Completeness3/5

The server covers search and template retrieval but lacks other expected documentation features such as browsing categories, listing versions, or retrieving full guides. This leaves notable gaps.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Remote MCP A
com.remote-mcp.mcp
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
Developer Tools Search Agent Orchestration
13
mcp
dev.augments
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
Developer Tools Documentation Access
2128
gread A
io.github.NitroRCr
An MCP server that gives your AI access to the source code and docs of all public github repos
Version Control Code Analysis Documentation Access
5361
Cortex C
io.cortex.mcp
The Cortex MCP server provides read-only access to real-time engineering context from the Cortex developer portal, allowing AI coding assistants to answer natural language questions about your organization's catalog (microservices, libraries, domains, teams, infrastructure), scorecards (engineering standards and best practices), initiatives (goals and deadlines), and Engineering Intelligence metrics. It includes tools for querying documentation, tracking personal entities, and accessing AI-assisted insights across the entire Cortex ecosystem.
Developer Tools Monitoring Observability
312

Related MCP Servers

Library Docs MCP Server
Documentation Access RAG Systems Search
vikramdse
F
license
B
quality
D
maintenance
An MCP server that fetches real-time documentation for popular libraries like Langchain, Llama-Index, MCP, and OpenAI, allowing LLMs to access updated library information beyond their knowledge cut-off dates.
Updated a year ago (2025-03-26 14:17 UTC)
1
3
-
MCP Documentation Server
Documentation Access Developer Tools App Automation
esakrissa
F
license
Not graded
quality
D
maintenance
A customized MCP server that enables integration between LLM applications and documentation sources, providing AI-assisted access to LangGraph and Model Context Protocol documentation.
Updated a year ago (2025-06-15 10:09 UTC)
-
MCP-Typescribe
Developer Tools Code Analysis Documentation Access
yWorks
A
license
Not graded
quality
D
maintenance
An MCP server that enables LLMs to understand and work with TypeScript APIs they haven't been trained on by providing structured access to TypeScript type definitions and documentation.
Updated a year ago (2025-10-17 07:07 UTC)
11 npm
46
MIT
MCP Specification Server
MCPJam
A
license
B
quality
C
maintenance
Provides complete access to Model Context Protocol documentation through an MCP server, allowing LLMs to query specific sections like 'Tools', 'Resources', and 'Authorization' to retrieve comprehensive protocol specifications.
Updated a year ago (2025-07-15 05:32 UTC)
1
25 npm
9
MIT

MCP Documentation Helper

Overview

Features

Prerequisites

Installation

1. Clone the Repository

2. Install Dependencies

Usage

Running Locally

Connecting to Claude Desktop

Connecting to Cursor

Using with VS Code (via MCP extension)

Available Resources

Available Tools

search-mcp-docs

get-implementation-template

Available Prompts

build-server

debug-server

Example Usage

Development

Project Structure

Scripts

How It Works

Troubleshooting

Server Not Showing Up in Claude Desktop

Documentation Files Not Found

Build Errors (Node/npm)

Contributing

Acknowledgments

Links

Available Tools

Output Schema

TDQS

Output Schema

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

Library Docs MCP Server

MCP Documentation Server

MCP-Typescribe

MCP Specification Server