Click on "Deploy 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 Server Boilerplate show me how to add a new tool to my 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.
A starter template for building MCP (Model Context Protocol) servers. This boilerplate provides a clean foundation for creating your own MCP server that can integrate with Claude, Cursor, or other MCP-compatible AI assistants.
This boilerplate helps you quickly start building:
Custom tools for AI assistants
Resource providers for dynamic content
Prompt templates for common operations
Integration points for external APIs and services
Related MCP server: MCP Server Boilerplate
Simple "hello-world" tool example
TypeScript support with proper type definitions
Easy installation scripts for different MCP clients
Clean project structure ready for customization
This MCP server template provides:
A basic server setup using the MCP SDK
Example tool implementation
Build and installation scripts
TypeScript configuration for development
The included example demonstrates how to create a simple tool that takes a name parameter and returns a greeting.
# Clone the boilerplate
git clone <your-repo-url>
cd mcp-server-boilerplate
# Install dependencies
pnpm install
# Build the project
pnpm run build
# Start the server
pnpm startThis boilerplate includes convenient installation scripts for different MCP clients:
# For Claude Desktop
pnpm run install-desktop
# For Cursor
pnpm run install-cursor
# For Claude Code
pnpm run install-code
# Generic installation
pnpm run install-serverThese scripts will build the project and automatically update the appropriate configuration files.
The installation script will automatically add the configuration, but you can also manually add it to your claude_desktop_config.json file:
{
"mcpServers": {
"your-server-name": {
"command": "node",
"args": ["/path/to/your/dist/index.js"]
}
}
}Then restart Claude Desktop to connect to the server.
Tools are functions that the AI assistant can call. Here's the basic structure:
server.tool(
"tool-name",
"Description of what the tool does",
{
// Zod schema for parameters
param1: z.string().describe("Description of parameter"),
param2: z.number().optional().describe("Optional parameter"),
},
async ({ param1, param2 }) => {
// Your tool logic here
return {
content: [
{
type: "text",
text: "Your response",
},
],
};
}
);Resources provide dynamic content that the AI can access:
server.resource(
"resource://example/{id}",
"Description of the resource",
async (uri) => {
// Extract parameters from URI
const id = uri.path.split("/").pop();
return {
contents: [
{
uri,
mimeType: "text/plain",
text: `Content for ${id}`,
},
],
};
}
);Prompts are reusable templates:
server.prompt(
"prompt-name",
"Description of the prompt",
{
// Parameters for the prompt
topic: z.string().describe("The topic to discuss"),
},
async ({ topic }) => {
return {
description: `A prompt about ${topic}`,
messages: [
{
role: "user",
content: {
type: "text",
text: `Please help me with ${topic}`,
},
},
],
};
}
);├── src/
│ └── index.ts # Main server implementation
├── scripts/ # Installation and utility scripts
├── dist/ # Compiled JavaScript (generated)
├── package.json # Project configuration
├── tsconfig.json # TypeScript configuration
└── README.md # This fileMake changes to src/index.ts
Run pnpm run build to compile
Test your server with pnpm start
Use the installation scripts to update your MCP client configuration
Update package.json with your project details
Customize the server name and tools in src/index.ts
Add your own tools, resources, and prompts
Integrate with external APIs or databases as needed
MIT
Extract specific data using paths, filters, patterns, or slices from JSON files. Always use this tool when you need to retrieve particular values, filter arrays/objects by conditions, search for patterns, or slice data. Ideal for targeted data extraction, data transformation, and focused analysis of specific JSON elements.
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Path to the JSON file | |
| path | No | Dot notation path to target | |
| filter | No | JS condition to filter results (e.g., 'item.age > 18') | |
| pattern | No | Regex pattern to search for | |
| search_type | No | What to search when using pattern | |
| start | No | Array slice start index | |
| end | No | Array slice end index | |
| keys | No | Specific object keys to extract | |
| default_value | No | Fallback if path not found |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure. It describes what the tool does (extract data using various methods) and mentions use cases (data transformation, focused analysis), but doesn't address important behavioral aspects like error handling, performance characteristics, memory usage with large files, or what happens when multiple extraction methods are combined. It provides basic operational context but lacks depth on behavioral traits.
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?
The description is appropriately sized with three sentences that each serve distinct purposes: stating the core functionality, providing usage guidelines, and describing ideal use cases. It's front-loaded with the main purpose and avoids redundancy. While efficient, it could be slightly more structured with clearer separation between mandatory and optional parameter usage.
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?
For a tool with 9 parameters, no annotations, and no output schema, the description provides adequate but incomplete context. It covers the 'what' and 'when' well but lacks details on 'how' the extraction works, error conditions, return formats, or performance considerations. The description compensates somewhat for the lack of annotations by specifying use cases, but doesn't fully address the complexity of a multi-parameter extraction tool.
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?
Schema description coverage is 100%, so the schema already documents all 9 parameters thoroughly. The description mentions the extraction methods (paths, filters, patterns, slices) which correspond to parameters, but doesn't add meaningful semantic context beyond what's in the schema descriptions. It doesn't explain how parameters interact or provide usage examples. Baseline 3 is appropriate when schema does the heavy lifting.
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?
The description clearly states the tool's purpose as extracting specific data from JSON files using multiple methods (paths, filters, patterns, slices). It distinguishes from the sibling 'json_read' by emphasizing targeted extraction rather than general reading. The verb 'extract' with the resource 'JSON files' is specific and actionable.
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?
The description provides explicit guidance on when to use this tool: 'Always use this tool when you need to retrieve particular values, filter arrays/objects by conditions, search for patterns, or slice data.' It also distinguishes from the sibling 'json_read' by specifying this is for 'targeted data extraction' rather than general reading. The 'Ideal for' section further clarifies appropriate contexts.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Read and analyze JSON. Always use this tool to explore JSON structure, understand data schema, or get high-level overviews of large JSON. Use this for initial data exploration or when you need to understand the shape and types of data before extracting specific values.
| Name | Required | Description | Default |
|---|---|---|---|
| file_path | Yes | Path to the JSON file | |
| path | No | Dot notation to specific location | |
| max_depth | No | Limit traversal depth | |
| max_keys | No | Maximum number of keys to show per object (default: show all keys) | |
| sample_arrays | No | Show only first N array items | |
| keys_only | No | Return only the key structure | |
| include_types | No | Add type information | |
| include_stats | No | Add file size and structure statistics |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively communicates that this is a read/analysis tool (not destructive), provides context about its exploratory nature, and hints at capabilities like handling large JSON files and providing overviews. However, it doesn't mention potential limitations like file size constraints or performance characteristics.
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?
The description is perfectly structured with two sentences that each earn their place. The first sentence establishes the core purpose, while the second provides specific usage guidelines. There's zero wasted language and it's appropriately sized for the tool's complexity.
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?
Given the tool's moderate complexity (8 parameters, no output schema, no annotations), the description provides excellent guidance on when and why to use it. However, without annotations or output schema, it could benefit from more explicit information about what the tool returns (e.g., formatted analysis vs. raw data) and any behavioral constraints.
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?
The schema description coverage is 100%, so the schema already documents all 8 parameters thoroughly. The description doesn't add any parameter-specific information beyond what's in the schema, maintaining the baseline score of 3 for high schema coverage.
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?
The description clearly states the tool's purpose with specific verbs ('read and analyze JSON') and resources ('JSON structure', 'data schema', 'large JSON'). It distinguishes from the sibling tool json_extract by emphasizing exploration and understanding rather than extraction.
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?
The description explicitly states when to use this tool ('Always use this tool to explore JSON structure', 'for initial data exploration', 'when you need to understand the shape and types of data before extracting specific values') and implies when not to use it (when you need to extract specific values, suggesting json_extract as an alternative).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v1.0.0json_extractjson_readScored across 2 tools
The two tools have clearly distinct purposes with no overlap. json_extract is for targeted data extraction and transformation, while json_read is for initial exploration and schema understanding. The descriptions explicitly guide when to use each tool, eliminating any ambiguity.
Both tools follow a consistent verb_noun pattern with 'json_' prefix and descriptive actions (extract, read). The naming is perfectly uniform and predictable across the tool set.
With only 2 tools, the server feels too thin for a general-purpose JSON handling domain. While the tools are well-defined, a complete JSON manipulation surface would typically include additional operations like validation, transformation, or writing capabilities. The count is insufficient for comprehensive JSON workflows.
There are significant gaps in the JSON manipulation surface. The server only provides read/extract capabilities with no tools for creating, updating, validating, or writing JSON data. This creates dead ends for agents needing to modify or generate JSON, making it incomplete for common JSON-related tasks.
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
A simple Typescript MCP server built using the official MCP Typescript SDK and smithery/cli. This…
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
