zsp/skills
1
0
Fork 0
mirror of https://github.com/anthropics/skills.git synced 2026-04-14 05:43:36 +08:00
Code Issues Packages Projects Releases Wiki Activity

Update example skills and rename 'artifacts-builder' (#112)

Browse Source 
* Export updated examples

* Rename 'artifacts-builder' to 'web-artifacts-builder'
This commit is contained in:
Keith Lazuka
2025-11-17 16:34:29 -05:00
committed by GitHub
parent e5c60158df
commit 0f77e501e6
20 changed files with 1051 additions and 2287 deletions
Download Patch File Download Diff File Expand all files Collapse all files

862
mcp-builder/reference/mcp_best_practices.md
View File

@@ -1,10 +1,4 @@
# MCP Server Development Best Practices and Guidelines
## Overview
This document compiles essential best practices and guidelines for building Model Context Protocol (MCP) servers. It covers naming conventions, tool design, response formats, pagination, error handling, security, and compliance requirements.
---
# MCP Server Best Practices
## Quick Reference
@@ -27,106 +21,77 @@ This document compiles essential best practices and guidelines for building Mode
- Return `has_more`, `next_offset`, `total_count`
- Default to 20-50 items
### Character Limits
- Set CHARACTER_LIMIT constant (typically 25,000)
- Truncate gracefully with clear messages
- Provide guidance on filtering
### Transport
- **Streamable HTTP**: For remote servers, multi-client scenarios
- **stdio**: For local integrations, command-line tools
- Avoid SSE (deprecated in favor of streamable HTTP)
---
## Table of Contents
1. Server Naming Conventions
2. Tool Naming and Design
3. Response Format Guidelines
4. Pagination Best Practices
5. Character Limits and Truncation
6. Tool Development Best Practices
7. Transport Best Practices
8. Testing Requirements
9. OAuth and Security Best Practices
10. Resource Management Best Practices
11. Prompt Management Best Practices
12. Error Handling Standards
13. Documentation Requirements
14. Compliance and Monitoring
## Server Naming Conventions
---
## 1. Server Naming Conventions
Follow these standardized naming patterns for MCP servers:
Follow these standardized naming patterns:
**Python**: Use format `{service}_mcp` (lowercase with underscores)
- Examples: `slack_mcp`, `github_mcp`, `jira_mcp`, `stripe_mcp`
- Examples: `slack_mcp`, `github_mcp`, `jira_mcp`
**Node/TypeScript**: Use format `{service}-mcp-server` (lowercase with hyphens)
- Examples: `slack-mcp-server`, `github-mcp-server`, `jira-mcp-server`
The name should be:
- General (not tied to specific features)
- Descriptive of the service/API being integrated
- Easy to infer from the task description
- Without version numbers or dates
The name should be general, descriptive of the service being integrated, easy to infer from the task description, and without version numbers.
---
## 2. Tool Naming and Design
## Tool Naming and Design
### Tool Naming Best Practices
### Tool Naming
1. **Use snake_case**: `search_users`, `create_project`, `get_channel_info`
2. **Include service prefix**: Anticipate that your MCP server may be used alongside other MCP servers
- Use `slack_send_message` instead of just `send_message`
- Use `github_create_issue` instead of just `create_issue`
- Use `asana_list_tasks` instead of just `list_tasks`
3. **Be action-oriented**: Start with verbs (get, list, search, create, etc.)
4. **Be specific**: Avoid generic names that could conflict with other servers
5. **Maintain consistency**: Use consistent naming patterns within your server
### Tool Design Guidelines
### Tool Design
- Tool descriptions must narrowly and unambiguously describe functionality
- Descriptions must precisely match actual functionality
- Should not create confusion with other MCP servers
- Should provide tool annotations (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- Provide tool annotations (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- Keep tool operations focused and atomic
---
## 3. Response Format Guidelines
## Response Formats
All tools that return data should support multiple formats for flexibility:
All tools that return data should support multiple formats:
### JSON Format (`response_format="json"`)
- Machine-readable structured data
- Include all available fields and metadata
- Consistent field names and types
- Suitable for programmatic processing
- Use for when LLMs need to process data further
- Use for programmatic processing
### Markdown Format (`response_format="markdown"`, typically default)
- Human-readable formatted text
- Use headers, lists, and formatting for clarity
- Convert timestamps to human-readable format (e.g., "2024-01-15 10:30:00 UTC" instead of epoch)
- Show display names with IDs in parentheses (e.g., "@john.doe (U123456)")
- Omit verbose metadata (e.g., show only one profile image URL, not all sizes)
- Group related information logically
- Use for when presenting information to users
- Convert timestamps to human-readable format
- Show display names with IDs in parentheses
- Omit verbose metadata
---
## 4. Pagination Best Practices
## Pagination
For tools that list resources:
- **Always respect the `limit` parameter**: Never load all results when a limit is specified
- **Always respect the `limit` parameter**
- **Implement pagination**: Use `offset` or cursor-based pagination
- **Return pagination metadata**: Include `has_more`, `next_offset`/`next_cursor`, `total_count`
- **Never load all results into memory**: Especially important for large datasets
- **Default to reasonable limits**: 20-50 items is typical
- **Include clear pagination info in responses**: Make it easy for LLMs to request more data
Example pagination response structure:
Example pagination response:
```json
{
"total": 150,
@@ -140,776 +105,145 @@ Example pagination response structure:
---
## 5. Character Limits and Truncation
## Transport Options
To prevent overwhelming responses with too much data:
### Streamable HTTP
- **Define CHARACTER_LIMIT constant**: Typically 25,000 characters at module level
- **Check response size before returning**: Measure the final response length
- **Truncate gracefully with clear indicators**: Let the LLM know data was truncated
- **Provide guidance on filtering**: Suggest how to use parameters to reduce results
- **Include truncation metadata**: Show what was truncated and how to get more
Example truncation handling:
```python
CHARACTER_LIMIT = 25000
if len(result) > CHARACTER_LIMIT:
truncated_data = data[:max(1, len(data) // 2)]
response["truncated"] = True
response["truncation_message"] = (
f"Response truncated from {len(data)} to {len(truncated_data)} items. "
f"Use 'offset' parameter or add filters to see more results."
)
```
---
## 6. Transport Options
MCP servers support multiple transport mechanisms for different deployment scenarios:
### Stdio Transport
**Best for**: Command-line tools, local integrations, subprocess execution
**Best for**: Remote servers, web services, multi-client scenarios
**Characteristics**:
- Standard input/output stream communication
- Simple setup, no network configuration needed
- Runs as a subprocess of the client
- Ideal for desktop applications and CLI tools
**Use when**:
- Building tools for local development environments
- Integrating with desktop applications (e.g., Claude Desktop)
- Creating command-line utilities
- Single-user, single-session scenarios
### HTTP Transport
**Best for**: Web services, remote access, multi-client scenarios
**Characteristics**:
- Request-response pattern over HTTP
- Bidirectional communication over HTTP
- Supports multiple simultaneous clients
- Can be deployed as a web service
- Requires network configuration and security considerations
- Enables server-to-client notifications
**Use when**:
- Serving multiple clients simultaneously
- Deploying as a cloud service
- Integration with web applications
- Need for load balancing or scaling
### Server-Sent Events (SSE) Transport
### stdio
**Best for**: Real-time updates, push notifications, streaming data
**Best for**: Local integrations, command-line tools
**Characteristics**:
- One-way server-to-client streaming over HTTP
- Enables real-time updates without polling
- Long-lived connections for continuous data flow
- Built on standard HTTP infrastructure
- Standard input/output stream communication
- Simple setup, no network configuration needed
- Runs as a subprocess of the client
**Use when**:
- Clients need real-time data updates
- Implementing push notifications
- Streaming logs or monitoring data
- Progressive result delivery for long operations
- Building tools for local development environments
- Integrating with desktop applications
- Single-user, single-session scenarios
### Transport Selection Criteria
**Note**: stdio servers should NOT log to stdout (use stderr for logging)
| Criterion | Stdio | HTTP | SSE |
|-----------|-------|------|-----|
| **Deployment** | Local | Remote | Remote |
| **Clients** | Single | Multiple | Multiple |
| **Communication** | Bidirectional | Request-Response | Server-Push |
| **Complexity** | Low | Medium | Medium-High |
| **Real-time** | No | No | Yes |
### Transport Selection
| Criterion | stdio | Streamable HTTP |
|-----------|-------|-----------------|
| **Deployment** | Local | Remote |
| **Clients** | Single | Multiple |
| **Complexity** | Low | Medium |
| **Real-time** | No | Yes |
---
## 7. Tool Development Best Practices
### General Guidelines
1. Tool names should be descriptive and action-oriented
2. Use parameter validation with detailed JSON schemas
3. Include examples in tool descriptions
4. Implement proper error handling and validation
5. Use progress reporting for long operations
6. Keep tool operations focused and atomic
7. Document expected return value structures
8. Implement proper timeouts
9. Consider rate limiting for resource-intensive operations
10. Log tool usage for debugging and monitoring
### Security Considerations for Tools
#### Input Validation
- Validate all parameters against schema
- Sanitize file paths and system commands
- Validate URLs and external identifiers
- Check parameter sizes and ranges
- Prevent command injection
#### Access Control
- Implement authentication where needed
- Use appropriate authorization checks
- Audit tool usage
- Rate limit requests
- Monitor for abuse
#### Error Handling
- Don't expose internal errors to clients
- Log security-relevant errors
- Handle timeouts appropriately
- Clean up resources after errors
- Validate return values
### Tool Annotations
- Provide readOnlyHint and destructiveHint annotations
- Remember annotations are hints, not security guarantees
- Clients should not make security-critical decisions based solely on annotations
---
## 8. Transport Best Practices
### General Transport Guidelines
1. Handle connection lifecycle properly
2. Implement proper error handling
3. Use appropriate timeout values
4. Implement connection state management
5. Clean up resources on disconnection
### Security Best Practices for Transport
- Follow security considerations for DNS rebinding attacks
- Implement proper authentication mechanisms
- Validate message formats
- Handle malformed messages gracefully
### Stdio Transport Specific
- Local MCP servers should NOT log to stdout (interferes with protocol)
- Use stderr for logging messages
- Handle standard I/O streams properly
---
## 9. Testing Requirements
A comprehensive testing strategy should cover:
### Functional Testing
- Verify correct execution with valid/invalid inputs
### Integration Testing
- Test interaction with external systems
### Security Testing
- Validate auth, input sanitization, rate limiting
### Performance Testing
- Check behavior under load, timeouts
### Error Handling
- Ensure proper error reporting and cleanup
---
## 10. OAuth and Security Best Practices
## Security Best Practices
### Authentication and Authorization
MCP servers that connect to external services should implement proper authentication:
**OAuth 2.1 Implementation:**
**OAuth 2.1**:
- Use secure OAuth 2.1 with certificates from recognized authorities
- Validate access tokens before processing requests
- Only accept tokens specifically intended for your server
- Reject tokens without proper audience claims
- Never pass through tokens received from MCP clients
**API Key Management:**
**API Keys**:
- Store API keys in environment variables, never in code
- Validate keys on server startup
- Provide clear error messages when authentication fails
- Use secure transmission for sensitive credentials
### Input Validation and Security
### Input Validation
**Always validate inputs:**
- Sanitize file paths to prevent directory traversal
- Validate URLs and external identifiers
- Check parameter sizes and ranges
- Prevent command injection in system calls
- Use schema validation (Pydantic/Zod) for all inputs
**Error handling security:**
### Error Handling
- Don't expose internal errors to clients
- Log security-relevant errors server-side
- Provide helpful but not revealing error messages
- Clean up resources after errors
### Privacy and Data Protection
### DNS Rebinding Protection
**Data collection principles:**
- Only collect data strictly necessary for functionality
- Don't collect extraneous conversation data
- Don't collect PII unless explicitly required for the tool's purpose
- Provide clear information about what data is accessed
**Data transmission:**
- Don't send data to servers outside your organization without disclosure
- Use secure transmission (HTTPS) for all network communication
- Validate certificates for external services
For streamable HTTP servers running locally:
- Enable DNS rebinding protection
- Validate the `Origin` header on all incoming connections
- Bind to `127.0.0.1` rather than `0.0.0.0`
---
## 11. Resource Management Best Practices
## Tool Annotations
1. Only suggest necessary resources
2. Use clear, descriptive names for roots
3. Handle resource boundaries properly
4. Respect client control over resources
5. Use model-controlled primitives (tools) for automatic data exposure
Provide annotations to help clients understand tool behavior:
| Annotation | Type | Default | Description |
|-----------|------|---------|-------------|
| `readOnlyHint` | boolean | false | Tool does not modify its environment |
| `destructiveHint` | boolean | true | Tool may perform destructive updates |
| `idempotentHint` | boolean | false | Repeated calls with same args have no additional effect |
| `openWorldHint` | boolean | true | Tool interacts with external entities |
**Important**: Annotations are hints, not security guarantees. Clients should not make security-critical decisions based solely on annotations.
---
## 12. Prompt Management Best Practices
- Clients should show users proposed prompts
- Users should be able to modify or reject prompts
- Clients should show users completions
- Users should be able to modify or reject completions
- Consider costs when using sampling
---
## 13. Error Handling Standards
## Error Handling
- Use standard JSON-RPC error codes
- Report tool errors within result objects (not protocol-level)
- Provide helpful, specific error messages
- Report tool errors within result objects (not protocol-level errors)
- Provide helpful, specific error messages with suggested next steps
- Don't expose internal implementation details
- Clean up resources properly on errors
Example error handling:
```typescript
try {
const result = performOperation();
return { content: [{ type: "text", text: result }] };
} catch (error) {
return {
isError: true,
content: [{
type: "text",
text: `Error: ${error.message}. Try using filter='active_only' to reduce results.`
}]
};
}
```
---
## 14. Documentation Requirements
## Testing Requirements
Comprehensive testing should cover:
- **Functional testing**: Verify correct execution with valid/invalid inputs
- **Integration testing**: Test interaction with external systems
- **Security testing**: Validate auth, input sanitization, rate limiting
- **Performance testing**: Check behavior under load, timeouts
- **Error handling**: Ensure proper error reporting and cleanup
---
## Documentation Requirements
- Provide clear documentation of all tools and capabilities
- Include working examples (at least 3 per major feature)
- Document security considerations
- Specify required permissions and access levels
- Document rate limits and performance characteristics
---
## 15. Compliance and Monitoring
- Implement logging for debugging and monitoring
- Track tool usage patterns
- Monitor for potential abuse
- Maintain audit trails for security-relevant operations
- Be prepared for ongoing compliance reviews
---
## Summary
These best practices represent the comprehensive guidelines for building secure, efficient, and compliant MCP servers that work well within the ecosystem. Developers should follow these guidelines to ensure their MCP servers meet the standards for inclusion in the MCP directory and provide a safe, reliable experience for users.
----------
# Tools
> Enable LLMs to perform actions through your server
Tools are a powerful primitive in the Model Context Protocol (MCP) that enable servers to expose executable functionality to clients. Through tools, LLMs can interact with external systems, perform computations, and take actions in the real world.
<Note>
Tools are designed to be **model-controlled**, meaning that tools are exposed from servers to clients with the intention of the AI model being able to automatically invoke them (with a human in the loop to grant approval).
</Note>
## Overview
Tools in MCP allow servers to expose executable functions that can be invoked by clients and used by LLMs to perform actions. Key aspects of tools include:
* **Discovery**: Clients can obtain a list of available tools by sending a `tools/list` request
* **Invocation**: Tools are called using the `tools/call` request, where servers perform the requested operation and return results
* **Flexibility**: Tools can range from simple calculations to complex API interactions
Like [resources](/docs/concepts/resources), tools are identified by unique names and can include descriptions to guide their usage. However, unlike resources, tools represent dynamic operations that can modify state or interact with external systems.
## Tool definition structure
Each tool is defined with the following structure:
```typescript
{
name: string; // Unique identifier for the tool
description?: string; // Human-readable description
inputSchema: { // JSON Schema for the tool's parameters
type: "object",
properties: { ... } // Tool-specific parameters
},
annotations?: { // Optional hints about tool behavior
title?: string; // Human-readable title for the tool
readOnlyHint?: boolean; // If true, the tool does not modify its environment
destructiveHint?: boolean; // If true, the tool may perform destructive updates
idempotentHint?: boolean; // If true, repeated calls with same args have no additional effect
openWorldHint?: boolean; // If true, tool interacts with external entities
}
}
```
## Implementing tools
Here's an example of implementing a basic tool in an MCP server:
<Tabs>
<Tab title="TypeScript">
```typescript
const server = new Server({
name: "example-server",
version: "1.0.0"
}, {
capabilities: {
tools: {}
}
});
// Define available tools
server.setRequestHandler(ListToolsRequestSchema, async () => {
return {
tools: [{
name: "calculate_sum",
description: "Add two numbers together",
inputSchema: {
type: "object",
properties: {
a: { type: "number" },
b: { type: "number" }
},
required: ["a", "b"]
}
}]
};
});
// Handle tool execution
server.setRequestHandler(CallToolRequestSchema, async (request) => {
if (request.params.name === "calculate_sum") {
const { a, b } = request.params.arguments;
return {
content: [
{
type: "text",
text: String(a + b)
}
]
};
}
throw new Error("Tool not found");
});
```
</Tab>
<Tab title="Python">
```python
app = Server("example-server")
@app.list_tools()
async def list_tools() -> list[types.Tool]:
return [
types.Tool(
name="calculate_sum",
description="Add two numbers together",
inputSchema={
"type": "object",
"properties": {
"a": {"type": "number"},
"b": {"type": "number"}
},
"required": ["a", "b"]
}
)
]
@app.call_tool()
async def call_tool(
name: str,
arguments: dict
) -> list[types.TextContent | types.ImageContent | types.EmbeddedResource]:
if name == "calculate_sum":
a = arguments["a"]
b = arguments["b"]
result = a + b
return [types.TextContent(type="text", text=str(result))]
raise ValueError(f"Tool not found: {name}")
```
</Tab>
</Tabs>
## Example tool patterns
Here are some examples of types of tools that a server could provide:
### System operations
Tools that interact with the local system:
```typescript
{
name: "execute_command",
description: "Run a shell command",
inputSchema: {
type: "object",
properties: {
command: { type: "string" },
args: { type: "array", items: { type: "string" } }
}
}
}
```
### API integrations
Tools that wrap external APIs:
```typescript
{
name: "github_create_issue",
description: "Create a GitHub issue",
inputSchema: {
type: "object",
properties: {
title: { type: "string" },
body: { type: "string" },
labels: { type: "array", items: { type: "string" } }
}
}
}
```
### Data processing
Tools that transform or analyze data:
```typescript
{
name: "analyze_csv",
description: "Analyze a CSV file",
inputSchema: {
type: "object",
properties: {
filepath: { type: "string" },
operations: {
type: "array",
items: {
enum: ["sum", "average", "count"]
}
}
}
}
}
```
## Best practices
When implementing tools:
1. Provide clear, descriptive names and descriptions
2. Use detailed JSON Schema definitions for parameters
3. Include examples in tool descriptions to demonstrate how the model should use them
4. Implement proper error handling and validation
5. Use progress reporting for long operations
6. Keep tool operations focused and atomic
7. Document expected return value structures
8. Implement proper timeouts
9. Consider rate limiting for resource-intensive operations
10. Log tool usage for debugging and monitoring
### Tool name conflicts
MCP client applications and MCP server proxies may encounter tool name conflicts when building their own tool lists. For example, two connected MCP servers `web1` and `web2` may both expose a tool named `search_web`.
Applications may disambiguiate tools with one of the following strategies (among others; not an exhaustive list):
* Concatenating a unique, user-defined server name with the tool name, e.g. `web1___search_web` and `web2___search_web`. This strategy may be preferable when unique server names are already provided by the user in a configuration file.
* Generating a random prefix for the tool name, e.g. `jrwxs___search_web` and `6cq52___search_web`. This strategy may be preferable in server proxies where user-defined unique names are not available.
* Using the server URI as a prefix for the tool name, e.g. `web1.example.com:search_web` and `web2.example.com:search_web`. This strategy may be suitable when working with remote MCP servers.
Note that the server-provided name from the initialization flow is not guaranteed to be unique and is not generally suitable for disambiguation purposes.
## Security considerations
When exposing tools:
### Input validation
* Validate all parameters against the schema
* Sanitize file paths and system commands
* Validate URLs and external identifiers
* Check parameter sizes and ranges
* Prevent command injection
### Access control
* Implement authentication where needed
* Use appropriate authorization checks
* Audit tool usage
* Rate limit requests
* Monitor for abuse
### Error handling
* Don't expose internal errors to clients
* Log security-relevant errors
* Handle timeouts appropriately
* Clean up resources after errors
* Validate return values
## Tool discovery and updates
MCP supports dynamic tool discovery:
1. Clients can list available tools at any time
2. Servers can notify clients when tools change using `notifications/tools/list_changed`
3. Tools can be added or removed during runtime
4. Tool definitions can be updated (though this should be done carefully)
## Error handling
Tool errors should be reported within the result object, not as MCP protocol-level errors. This allows the LLM to see and potentially handle the error. When a tool encounters an error:
1. Set `isError` to `true` in the result
2. Include error details in the `content` array
Here's an example of proper error handling for tools:
<Tabs>
<Tab title="TypeScript">
```typescript
try {
// Tool operation
const result = performOperation();
return {
content: [
{
type: "text",
text: `Operation successful: ${result}`
}
]
};
} catch (error) {
return {
isError: true,
content: [
{
type: "text",
text: `Error: ${error.message}`
}
]
};
}
```
</Tab>
<Tab title="Python">
```python
try:
# Tool operation
result = perform_operation()
return types.CallToolResult(
content=[
types.TextContent(
type="text",
text=f"Operation successful: {result}"
)
]
)
except Exception as error:
return types.CallToolResult(
isError=True,
content=[
types.TextContent(
type="text",
text=f"Error: {str(error)}"
)
]
)
```
</Tab>
</Tabs>
This approach allows the LLM to see that an error occurred and potentially take corrective action or request human intervention.
## Tool annotations
Tool annotations provide additional metadata about a tool's behavior, helping clients understand how to present and manage tools. These annotations are hints that describe the nature and impact of a tool, but should not be relied upon for security decisions.
### Purpose of tool annotations
Tool annotations serve several key purposes:
1. Provide UX-specific information without affecting model context
2. Help clients categorize and present tools appropriately
3. Convey information about a tool's potential side effects
4. Assist in developing intuitive interfaces for tool approval
### Available tool annotations
The MCP specification defines the following annotations for tools:
| Annotation | Type | Default | Description |
| ----------------- | ------- | ------- | ------------------------------------------------------------------------------------------------------------------------------------ |
| `title` | string | - | A human-readable title for the tool, useful for UI display |
| `readOnlyHint` | boolean | false | If true, indicates the tool does not modify its environment |
| `destructiveHint` | boolean | true | If true, the tool may perform destructive updates (only meaningful when `readOnlyHint` is false) |
| `idempotentHint` | boolean | false | If true, calling the tool repeatedly with the same arguments has no additional effect (only meaningful when `readOnlyHint` is false) |
| `openWorldHint` | boolean | true | If true, the tool may interact with an "open world" of external entities |
### Example usage
Here's how to define tools with annotations for different scenarios:
```typescript
// A read-only search tool
{
name: "web_search",
description: "Search the web for information",
inputSchema: {
type: "object",
properties: {
query: { type: "string" }
},
required: ["query"]
},
annotations: {
title: "Web Search",
readOnlyHint: true,
openWorldHint: true
}
}
// A destructive file deletion tool
{
name: "delete_file",
description: "Delete a file from the filesystem",
inputSchema: {
type: "object",
properties: {
path: { type: "string" }
},
required: ["path"]
},
annotations: {
title: "Delete File",
readOnlyHint: false,
destructiveHint: true,
idempotentHint: true,
openWorldHint: false
}
}
// A non-destructive database record creation tool
{
name: "create_record",
description: "Create a new record in the database",
inputSchema: {
type: "object",
properties: {
table: { type: "string" },
data: { type: "object" }
},
required: ["table", "data"]
},
annotations: {
title: "Create Database Record",
readOnlyHint: false,
destructiveHint: false,
idempotentHint: false,
openWorldHint: false
}
}
```
### Integrating annotations in server implementation
<Tabs>
<Tab title="TypeScript">
```typescript
server.setRequestHandler(ListToolsRequestSchema, async () => {
return {
tools: [{
name: "calculate_sum",
description: "Add two numbers together",
inputSchema: {
type: "object",
properties: {
a: { type: "number" },
b: { type: "number" }
},
required: ["a", "b"]
},
annotations: {
title: "Calculate Sum",
readOnlyHint: true,
openWorldHint: false
}
}]
};
});
```
</Tab>
<Tab title="Python">
```python
from mcp.server.fastmcp import FastMCP
mcp = FastMCP("example-server")
@mcp.tool(
annotations={
"title": "Calculate Sum",
"readOnlyHint": True,
"openWorldHint": False
}
)
async def calculate_sum(a: float, b: float) -> str:
"""Add two numbers together.
Args:
a: First number to add
b: Second number to add
"""
result = a + b
return str(result)
```
</Tab>
</Tabs>
### Best practices for tool annotations
1. **Be accurate about side effects**: Clearly indicate whether a tool modifies its environment and whether those modifications are destructive.
2. **Use descriptive titles**: Provide human-friendly titles that clearly describe the tool's purpose.
3. **Indicate idempotency properly**: Mark tools as idempotent only if repeated calls with the same arguments truly have no additional effect.
4. **Set appropriate open/closed world hints**: Indicate whether a tool interacts with a closed system (like a database) or an open system (like the web).
5. **Remember annotations are hints**: All properties in ToolAnnotations are hints and not guaranteed to provide a faithful description of tool behavior. Clients should never make security-critical decisions based solely on annotations.
## Testing tools
A comprehensive testing strategy for MCP tools should cover:
* **Functional testing**: Verify tools execute correctly with valid inputs and handle invalid inputs appropriately
* **Integration testing**: Test tool interaction with external systems using both real and mocked dependencies
* **Security testing**: Validate authentication, authorization, input sanitization, and rate limiting
* **Performance testing**: Check behavior under load, timeout handling, and resource cleanup
* **Error handling**: Ensure tools properly report errors through the MCP protocol and clean up resources

198
mcp-builder/reference/node_mcp_server.md
View File

@@ -11,9 +11,10 @@ This document provides Node/TypeScript-specific best practices and examples for
### Key Imports
```typescript
import { McpServer } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StreamableHTTPServerTransport } from "@modelcontextprotocol/sdk/server/streamableHttp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import express from "express";
import { z } from "zod";
import axios, { AxiosError } from "axios";
```
### Server Initialization
@@ -26,9 +27,22 @@ const server = new McpServer({
### Tool Registration Pattern
```typescript
server.registerTool("tool_name", {...config}, async (params) => {
// Implementation
});
server.registerTool(
"tool_name",
{
title: "Tool Display Name",
description: "What the tool does",
inputSchema: { param: z.string() },
outputSchema: { result: z.string() }
},
async ({ param }) => {
const output = { result: `Processed: ${param}` };
return {
content: [{ type: "text", text: JSON.stringify(output) }],
structuredContent: output // Modern pattern for structured data
};
}
);
```
---
@@ -41,6 +55,11 @@ The official MCP TypeScript SDK provides:
- Zod schema integration for runtime input validation
- Type-safe tool handler implementations
**IMPORTANT - Use Modern APIs Only:**
- **DO use**: `server.registerTool()`, `server.registerResource()`, `server.registerPrompt()`
- **DO NOT use**: Old deprecated APIs such as `server.tool()`, `server.setRequestHandler(ListToolsRequestSchema, ...)`, or manual handler registration
- The `register*` methods provide better type safety, automatic schema handling, and are the recommended approach
See the MCP SDK documentation in the references for complete details.
## Server Naming Convention
@@ -204,55 +223,43 @@ Error Handling:
};
}
// Format response based on requested format
let result: string;
// Prepare structured output
const output = {
total,
count: users.length,
offset: params.offset,
users: users.map((user: any) => ({
id: user.id,
name: user.name,
email: user.email,
...(user.team ? { team: user.team } : {}),
active: user.active ?? true
})),
has_more: total > params.offset + users.length,
...(total > params.offset + users.length ? {
next_offset: params.offset + users.length
} : {})
};
// Format text representation based on requested format
let textContent: string;
if (params.response_format === ResponseFormat.MARKDOWN) {
// Human-readable markdown format
const lines: string[] = [`# User Search Results: '${params.query}'`, ""];
lines.push(`Found ${total} users (showing ${users.length})`);
lines.push("");
const lines = [`# User Search Results: '${params.query}'`, "",
`Found ${total} users (showing ${users.length})`, ""];
for (const user of users) {
lines.push(`## ${user.name} (${user.id})`);
lines.push(`- **Email**: ${user.email}`);
if (user.team) {
lines.push(`- **Team**: ${user.team}`);
}
if (user.team) lines.push(`- **Team**: ${user.team}`);
lines.push("");
}
result = lines.join("\n");
textContent = lines.join("\n");
} else {
// Machine-readable JSON format
const response: any = {
total,
count: users.length,
offset: params.offset,
users: users.map((user: any) => ({
id: user.id,
name: user.name,
email: user.email,
...(user.team ? { team: user.team } : {}),
active: user.active ?? true
}))
};
// Add pagination info if there are more results
if (total > params.offset + users.length) {
response.has_more = true;
response.next_offset = params.offset + users.length;
}
result = JSON.stringify(response, null, 2);
textContent = JSON.stringify(output, null, 2);
}
return {
content: [{
type: "text",
text: result
}]
content: [{ type: "text", text: textContent }],
structuredContent: output // Modern pattern for structured data
};
} catch (error) {
return {
@@ -695,27 +702,57 @@ server.registerTool(
);
// Main function
async function main() {
// Verify environment variables if needed
// For stdio (local):
async function runStdio() {
if (!process.env.EXAMPLE_API_KEY) {
console.error("ERROR: EXAMPLE_API_KEY environment variable is required");
process.exit(1);
}
// Create transport
const transport = new StdioServerTransport();
// Connect server to transport
await server.connect(transport);
console.error("Example MCP server running via stdio");
console.error("MCP server running via stdio");
}
// Run the server
main().catch((error) => {
console.error("Server error:", error);
process.exit(1);
});
// For streamable HTTP (remote):
async function runHTTP() {
if (!process.env.EXAMPLE_API_KEY) {
console.error("ERROR: EXAMPLE_API_KEY environment variable is required");
process.exit(1);
}
const app = express();
app.use(express.json());
app.post('/mcp', async (req, res) => {
const transport = new StreamableHTTPServerTransport({
sessionIdGenerator: undefined,
enableJsonResponse: true
});
res.on('close', () => transport.close());
await server.connect(transport);
await transport.handleRequest(req, res, req.body);
});
const port = parseInt(process.env.PORT || '3000');
app.listen(port, () => {
console.error(`MCP server running on http://localhost:${port}/mcp`);
});
}
// Choose transport based on environment
const transport = process.env.TRANSPORT || 'stdio';
if (transport === 'http') {
runHTTP().catch(error => {
console.error("Server error:", error);
process.exit(1);
});
} else {
runStdio().catch(error => {
console.error("Server error:", error);
process.exit(1);
});
}
```
---
@@ -777,30 +814,47 @@ server.registerResourceList(async () => {
- **Resources**: When data is relatively static or template-based
- **Tools**: When operations have side effects or complex workflows
### Multiple Transport Options
### Transport Options
The TypeScript SDK supports different transport mechanisms:
The TypeScript SDK supports two main transport mechanisms:
#### Streamable HTTP (Recommended for Remote Servers)
```typescript
import { StreamableHTTPServerTransport } from "@modelcontextprotocol/sdk/server/streamableHttp.js";
import express from "express";
const app = express();
app.use(express.json());
app.post('/mcp', async (req, res) => {
// Create new transport for each request (stateless, prevents request ID collisions)
const transport = new StreamableHTTPServerTransport({
sessionIdGenerator: undefined,
enableJsonResponse: true
});
res.on('close', () => transport.close());
await server.connect(transport);
await transport.handleRequest(req, res, req.body);
});
app.listen(3000);
```
#### stdio (For Local Integrations)
```typescript
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";
import { SSEServerTransport } from "@modelcontextprotocol/sdk/server/sse.js";
// Stdio transport (default - for CLI tools)
const stdioTransport = new StdioServerTransport();
await server.connect(stdioTransport);
// SSE transport (for real-time web updates)
const sseTransport = new SSEServerTransport("/message", response);
await server.connect(sseTransport);
// HTTP transport (for web services)
// Configure based on your HTTP framework integration
const transport = new StdioServerTransport();
await server.connect(transport);
```
**Transport selection guide:**
- **Stdio**: Command-line tools, subprocess integration, local development
- **HTTP**: Web services, remote access, multiple simultaneous clients
- **SSE**: Real-time updates, server-push notifications, web dashboards
**Transport selection:**
- **Streamable HTTP**: Web services, remote access, multiple clients
- **stdio**: Command-line tools, local development, subprocess integration
### Notification Support
@@ -889,7 +943,7 @@ Before finalizing your Node/TypeScript MCP server implementation, ensure:
### Advanced Features (where applicable)
- [ ] Resources registered for appropriate data endpoints
- [ ] Appropriate transport configured (stdio, HTTP, SSE)
- [ ] Appropriate transport configured (stdio or streamable HTTP)
- [ ] Notifications implemented for dynamic server capabilities
- [ ] Type-safe with SDK interfaces

47
mcp-builder/reference/python_mcp_server.md
View File

@@ -204,32 +204,6 @@ async def list_items(params: ListInput) -> str:
return json.dumps(response, indent=2)
```
## Character Limits and Truncation
Add a CHARACTER_LIMIT constant to prevent overwhelming responses:
```python
# At module level
CHARACTER_LIMIT = 25000 # Maximum response size in characters
async def search_tool(params: SearchInput) -> str:
result = generate_response(data)
# Check character limit and truncate if needed
if len(result) > CHARACTER_LIMIT:
# Truncate data and add notice
truncated_data = data[:max(1, len(data) // 2)]
response["data"] = truncated_data
response["truncated"] = True
response["truncation_message"] = (
f"Response truncated from {len(data)} to {len(truncated_data)} items. "
f"Use 'offset' parameter or add filters to see more results."
)
result = json.dumps(response, indent=2)
return result
```
## Error Handling
Provide clear, actionable error messages:
@@ -377,7 +351,6 @@ mcp = FastMCP("example_mcp")
# Constants
API_BASE_URL = "https://api.example.com/v1"
CHARACTER_LIMIT = 25000 # Maximum response size in characters
# Enums
class ResponseFormat(str, Enum):
@@ -643,28 +616,23 @@ async def query_data(query: str, ctx: Context) -> str:
return format_results(results)
```
### Multiple Transport Options
### Transport Options
FastMCP supports different transport mechanisms:
FastMCP supports two main transport mechanisms:
```python
# Default: Stdio transport (for CLI tools)
# stdio transport (for local tools) - default
if __name__ == "__main__":
mcp.run()
# HTTP transport (for web services)
# Streamable HTTP transport (for remote servers)
if __name__ == "__main__":
mcp.run(transport="streamable_http", port=8000)
# SSE transport (for real-time updates)
if __name__ == "__main__":
mcp.run(transport="sse", port=8000)
```
**Transport selection:**
- **Stdio**: Command-line tools, subprocess integration
- **HTTP**: Web services, remote access, multiple clients
- **SSE**: Real-time updates, push notifications
- **stdio**: Command-line tools, local integrations, subprocess execution
- **Streamable HTTP**: Web services, remote access, multiple clients
---
@@ -733,12 +701,11 @@ Before finalizing your Python MCP server implementation, ensure:
- [ ] Resources registered for appropriate data endpoints
- [ ] Lifespan management implemented for persistent connections
- [ ] Structured output types used (TypedDict, Pydantic models)
- [ ] Appropriate transport configured (stdio, HTTP, SSE)
- [ ] Appropriate transport configured (stdio or streamable HTTP)
### Code Quality
- [ ] File includes proper imports including Pydantic imports
- [ ] Pagination is properly implemented where applicable
- [ ] Large responses check CHARACTER_LIMIT and truncate with clear messages
- [ ] Filtering options are provided for potentially large result sets
- [ ] All async functions are properly defined with `async def`
- [ ] HTTP client usage follows async patterns with proper context managers