Mcp
Okrs MCP
Model Context Protocol reference for okrs.do - Objectives and Key Results (Objectives and Key Results (OKR) management
Okrs MCP
Objectives and Key Results (Objectives and Key Results (OKR) management
Overview
The Model Context Protocol (MCP) provides AI models with direct access to okrs.do through a standardized interface.
Installation
pnpm add @modelcontextprotocol/sdkConfiguration
Add to your MCP server configuration:
{
"mcpServers": {
"okrs": {
"command": "npx",
"args": ["-y", "@dotdo/mcp-server"],
"env": {
"DO_API_KEY": "your-api-key"
}
}
}
}Tools
okrs/invoke
Main tool for okrs.do operations.
{
"name": "okrs/invoke",
"description": "Objectives and Key Results (Objectives and Key Results (OKR) management",
"inputSchema": {
"type": "object",
"properties": {
"operation": {
"type": "string",
"description": "Operation to perform"
},
"parameters": {
"type": "object",
"description": "Operation parameters"
}
},
"required": ["operation"]
}
}Usage in AI Models
Claude Desktop
// ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"okrs": {
"command": "npx",
"args": ["-y", "@dotdo/mcp-server", "--tool=okrs"],
"env": {
"DO_API_KEY": "undefined"
}
}
}
}OpenAI GPTs
# Custom GPT configuration
tools:
- type: mcp
server: okrs
operations:
- invoke
- query
- executeCustom Integration
import { Client } from '@modelcontextprotocol/sdk/client/index.js'
import { StdioClientTransport } from '@modelcontextprotocol/sdk/client/stdio.js'
const transport = new StdioClientTransport({
command: 'npx',
args: ['-y', '@dotdo/mcp-server', '--tool=okrs'],
})
const client = new Client(
{
name: 'okrs-client',
version: '1.0.0',
},
{
capabilities: {},
}
)
await client.connect(transport)
// Call tool
const result = await client.callTool({
name: 'okrs/invoke',
arguments: {
operation: 'okrs',
parameters: {},
},
})Tool Definitions
Available Tools
{
"tools": [
{
"name": "okrs/invoke",
"description": "Invoke okrs.do",
"inputSchema": {
/* ... */
}
},
{
"name": "okrs/query",
"description": "Query okrs.do resources",
"inputSchema": {
/* ... */
}
},
{
"name": "okrs/status",
"description": "Check okrs.do status",
"inputSchema": {
/* ... */
}
}
]
}Resources
Available Resources
{
"resources": [
{
"uri": "okrs://config",
"name": "Okrs Configuration",
"mimeType": "application/json"
},
{
"uri": "okrs://docs",
"name": "Okrs Documentation",
"mimeType": "text/markdown"
}
]
}Prompts
Pre-configured Prompts
{
"prompts": [
{
"name": "okrs-quick-start",
"description": "Quick start guide for okrs.do",
"arguments": []
},
{
"name": "okrs-best-practices",
"description": "Best practices for okrs.do",
"arguments": []
}
]
}Examples
Basic Usage
// AI model calls tool via MCP
mcp call okrs/manageWith Parameters
// Call with parameters
await mcp.callTool('okrs/invoke', {
operation: 'process',
parameters: {
// Operation-specific parameters
},
options: {
timeout: 30000,
},
})Error Handling
try {
const result = await mcp.callTool('okrs/invoke', {
operation: 'process',
})
return result
} catch (error) {
if (error.code === 'TOOL_NOT_FOUND') {
console.error('Okrs tool not available')
} else {
throw error
}
}AI Integration Patterns
Agentic Workflows
// AI agent uses okrs.do in workflow
const workflow = {
steps: [
{
tool: 'okrs/invoke',
operation: 'analyze',
input: 'user-data',
},
{
tool: 'okrs/process',
operation: 'transform',
input: 'analysis-result',
},
],
}Chain of Thought
AI models can reason about okrs.do operations:
User: "I need to process this data"
AI: "I'll use the okrs tool to:
1. Validate the data format
2. Process it through okrs.do
3. Return the results
Let me start..."
[Calls: mcp call okrs/manage]Server Implementation
Custom MCP Server
import { Server } from '@modelcontextprotocol/sdk/server/index.js'
import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js'
const server = new Server(
{
name: 'okrs-server',
version: '1.0.0',
},
{
capabilities: {
tools: {},
resources: {},
prompts: {},
},
}
)
// Register tool
server.setRequestHandler('tools/call', async (request) => {
if (request.params.name === 'okrs/invoke') {
// Handle okrs.do operation
return {
content: [
{
type: 'text',
text: JSON.stringify(result),
},
],
}
}
})
const transport = new StdioServerTransport()
await server.connect(transport)Best Practices
- Tool Design - Keep tools focused and single-purpose
- Error Messages - Provide clear, actionable errors
- Documentation - Include examples in tool descriptions
- Rate Limiting - Implement appropriate limits
- Security - Validate all inputs from AI models
- Monitoring - Track tool usage and errors