@runhuman/mcp-server 1.0.0

package/.env.example

@@ -0,0 +1,12 @@
+# RunHuman API Configuration
+
+# API Base URL
+# For local development, use http://localhost:3000
+# For production, use your deployed API URL
+RUNHUMAN_API_URL=http://localhost:3000
+
+# API Key
+# Get this from the API dashboard at http://localhost:3000/app.html
+# Or use the default test key below for local development
+# Format: qa_live_xxxxxxxxxxxxxxxxxxxxx
+RUNHUMAN_API_KEY=qa_live_test_key_for_demo_purposes_only_12345

package/README.md

@@ -0,0 +1,206 @@
+# RunHuman MCP Server
+
+A Model Context Protocol (MCP) server that allows AI agents to interact with the RunHuman QA testing service.
+
+## Overview
+
+This MCP server provides tools for creating and managing human QA jobs through the RunHuman API. AI agents can use this server to:
+
+- Create new QA jobs with custom schemas
+- Check the status of running jobs
+- Retrieve completed job results
+
+## Installation
+
+### For Claude Desktop (Recommended)
+
+1. Get your API key at: https://qa-experiment.fly.dev/app.html
+
+2. Add to your Claude Desktop config (`~/Library/Application Support/Claude/claude_desktop_config.json` on Mac):
+
+```json
+{
+  "mcpServers": {
+    "runhuman": {
+      "command": "npx",
+      "args": ["-y", "@runhuman/mcp-server", "--api-key=qa_live_xxxxxxxxxxxxx"]
+    }
+  }
+}
+```
+
+3. Restart Claude Desktop
+
+That's it! The server will be automatically downloaded and run by Claude.
+
+### For Development
+
+From the monorepo root:
+
+```bash
+npm install
+npm run build --workspace=@runhuman/mcp-server
+
+# Run with API key
+node packages/mcp-server/dist/index.js --api-key=qa_live_xxxxx
+```
+
+### Available Tools
+
+#### `create_job`
+Create a new QA job with human testers.
+
+**Parameters:**
+- `url` (string): The URL to test
+- `description` (string): Instructions for the human tester describing what to test
+- `schema` (object): Expected result schema that the tester response will be extracted into
+
+#### `get_job_status`
+Get the current status of a QA job.
+
+**Parameters:**
+- `jobId` (string): The ID of the job to check
+
+#### `get_job_result`
+Get the results of a completed QA job.
+
+**Parameters:**
+- `jobId` (string): The ID of the completed job
+
+## Configuration
+
+The MCP server needs to be configured with your RunHuman API credentials.
+
+### 1. Get an API Key
+
+**Option A: Via Dashboard**
+1. Start the API server: `npm run dev --workspace=@runhuman/api`
+2. Open http://localhost:3000/app.html
+3. Go to "API Keys" tab
+4. Click "Create API Key"
+5. Copy the key (starts with `qa_live_`)
+
+**Option B: Use Default Test Key**
+- For local development, you can use: `qa_live_test_key_123`
+- This key exists in `packages/api/data/api-keys.json`
+
+### 2. Configure Environment Variables
+
+Create a `.env` file in the MCP server directory:
+
+```bash
+# For local development
+RUNHUMAN_API_URL=http://localhost:3000
+RUNHUMAN_API_KEY=qa_live_test_key_123
+
+# For production
+RUNHUMAN_API_URL=https://api.runhuman.com
+RUNHUMAN_API_KEY=qa_live_xxxxxxxxxxxxxxxxxxxxx
+```
+
+**Important:** Never commit `.env` files to git! They're already in `.gitignore`.
+
+### 3. Verify Configuration
+
+Test your API key works:
+
+```bash
+curl http://localhost:3000/api/jobs \
+  -H "Authorization: Bearer qa_live_test_key_123" \
+  -H "Content-Type: application/json" \
+  -d '{"url":"https://example.com","description":"test","outputSchema":{}}'
+```
+
+Should return a job ID if authentication works.
+
+For more details, see [docs/API-AUTHENTICATION.md](docs/API-AUTHENTICATION.md)
+
+## Testing
+
+The MCP server includes automated tests to verify it's working correctly:
+
+```bash
+# Build first
+npm run build --workspace=@runhuman/mcp-server
+
+# Run simple automated test
+npm run test --workspace=@runhuman/mcp-server
+
+# Or use the MCP Inspector (interactive testing)
+npm run test:inspector --workspace=@runhuman/mcp-server
+```
+
+The test script will:
+1. ✅ Initialize a connection to the MCP server
+2. ✅ List all available tools (create_job, get_job_status, get_job_result)
+3. ✅ Test calling the create_job tool
+
+### Expected Test Output
+
+```
+✅ Server initialized successfully
+✅ Tools listed: create_job, get_job_status, get_job_result
+✅ create_job tool called successfully
+```
+
+## Development
+
+```bash
+# Watch mode (auto-rebuild on changes)
+npm run dev --workspace=@runhuman/mcp-server
+
+# Build
+npm run build --workspace=@runhuman/mcp-server
+
+# Test after building
+npm run test --workspace=@runhuman/mcp-server
+```
+
+## Integration with Claude Desktop
+
+To use this MCP server with Claude Desktop, add it to your configuration:
+
+```json
+{
+  "mcpServers": {
+    "runhuman": {
+      "command": "node",
+      "args": ["/path/to/qa-experiment/packages/mcp-server/dist/index.js"]
+    }
+  }
+}
+```
+
+## Example Usage
+
+Once connected to an AI agent (like Claude), the agent can use these tools naturally:
+
+**User:** "Can someone test my checkout page at https://myapp.com/checkout?"
+
+**Agent uses create_job:**
+```
+✅ Job created successfully!
+Job ID: job_abc123
+Status: pending
+...
+```
+
+**Agent polls get_job_status until complete, then calls get_job_result:**
+```
+✅ Test completed!
+Results Summary:
+- Checkout Flow: ✅ Working
+- Payment Processing: ✅ Successful
+...
+```
+
+## Developer Documentation
+
+For developers working on this MCP server:
+- [docs/HOW-AGENTS-USE-MCP.md](docs/HOW-AGENTS-USE-MCP.md) - How AI agents discover and use MCP servers
+- [docs/TOOL-RESPONSE-BEST-PRACTICES.md](docs/TOOL-RESPONSE-BEST-PRACTICES.md) - Best practices for tool responses
+
+## Learn More
+
+- [Model Context Protocol Documentation](https://modelcontextprotocol.io/)
+- [RunHuman API Documentation](../api/README.md)

package/dist/index.d.ts

@@ -0,0 +1,14 @@
+#!/usr/bin/env node
+/**
+ * RunHuman MCP Server
+ *
+ * This MCP server provides tools for AI agents to interact with the RunHuman QA testing service.
+ * It allows agents to:
+ * - Create QA jobs
+ * - Check job status
+ * - Retrieve job results
+ *
+ * @see https://modelcontextprotocol.io/
+ */
+export {};
+//# sourceMappingURL=index.d.ts.map

package/dist/index.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":";AAEA;;;;;;;;;;GAUG"}

package/dist/index.js

@@ -0,0 +1,424 @@
+#!/usr/bin/env node
+/**
+ * RunHuman MCP Server
+ *
+ * This MCP server provides tools for AI agents to interact with the RunHuman QA testing service.
+ * It allows agents to:
+ * - Create QA jobs
+ * - Check job status
+ * - Retrieve job results
+ *
+ * @see https://modelcontextprotocol.io/
+ */
+import { Server } from '@modelcontextprotocol/sdk/server/index.js';
+import { StdioServerTransport } from '@modelcontextprotocol/sdk/server/stdio.js';
+import { CallToolRequestSchema, ListToolsRequestSchema, ListPromptsRequestSchema, } from '@modelcontextprotocol/sdk/types.js';
+import * as dotenv from 'dotenv';
+// Load environment variables (optional - for standalone testing)
+dotenv.config();
+// Configuration
+// Priority: CLI args > env vars > defaults
+// Usage: node dist/index.js --api-key=qa_live_xxx [--api-url=https://...]
+const args = process.argv.slice(2);
+const apiKeyArg = args.find(arg => arg.startsWith('--api-key='))?.split('=')[1];
+const apiUrlArg = args.find(arg => arg.startsWith('--api-url='))?.split('=')[1];
+const API_URL = apiUrlArg || process.env.RUNHUMAN_API_URL || 'https://qa-experiment.fly.dev';
+const API_KEY = apiKeyArg || process.env.RUNHUMAN_API_KEY;
+if (!API_KEY) {
+    console.error('❌ Error: API key is required');
+    console.error('');
+    console.error('For Claude Desktop, add to your config:');
+    console.error('{');
+    console.error('  "mcpServers": {');
+    console.error('    "runhuman": {');
+    console.error('      "command": "npx",');
+    console.error('      "args": ["-y", "@runhuman/mcp-server", "--api-key=qa_live_xxxxx"]');
+    console.error('    }');
+    console.error('  }');
+    console.error('}');
+    console.error('');
+    console.error('Get your API key at: https://qa-experiment.fly.dev/app.html');
+    process.exit(1);
+}
+console.error(`🔗 Connected to RunHuman API at: ${API_URL}`);
+console.error(`🔑 Using API key: ${API_KEY.substring(0, 12)}...`);
+/**
+ * Create and configure the MCP server
+ */
+const server = new Server({
+    name: 'runhuman-mcp-server',
+    version: '1.0.0',
+}, {
+    capabilities: {
+        tools: {},
+        prompts: {},
+    },
+});
+/**
+ * List available prompts (documentation for the agent)
+ */
+server.setRequestHandler(ListPromptsRequestSchema, async () => {
+    return {
+        prompts: [
+            {
+                name: 'explain_runhuman',
+                description: 'Get an explanation of how to use RunHuman for QA testing',
+            },
+        ],
+    };
+});
+/**
+ * List available tools
+ */
+server.setRequestHandler(ListToolsRequestSchema, async () => {
+    return {
+        tools: [
+            {
+                name: 'create_job',
+                description: `Create a new QA job with real human testers. This sends your test to a human who will manually test your application and describe what they find in natural language. The response is then extracted into structured data matching your schema using GPT-4o.
+
+Use this when you need human verification of:
+- UI/UX functionality that's hard to automate
+- Visual issues, accessibility problems
+- Complex user flows (login, checkout, forms)
+- Cross-browser compatibility
+- Real user experience feedback
+
+Returns a jobId that you can use with get_job_status and get_job_result.
+
+Example workflow:
+1. create_job → get jobId
+2. get_job_status → poll until status is "completed"
+3. get_job_result → retrieve structured results`,
+                inputSchema: {
+                    type: 'object',
+                    properties: {
+                        url: {
+                            type: 'string',
+                            description: 'The URL to test (must be publicly accessible). Example: "https://myapp.com/checkout"',
+                        },
+                        description: {
+                            type: 'string',
+                            description: 'Clear instructions for the human tester. Be specific about what to test and how. Example: "Test the checkout flow: Add a product to cart, proceed to checkout, fill in shipping info, and verify the order summary shows correct totals before submitting."',
+                        },
+                        schema: {
+                            type: 'object',
+                            description: 'JSON Schema defining the structure you want extracted from the tester\'s response. Example: { "type": "object", "properties": { "checkoutWorks": { "type": "boolean" }, "totalIsCorrect": { "type": "boolean" }, "issues": { "type": "array", "items": { "type": "string" } } } }',
+                        },
+                    },
+                    required: ['url', 'description', 'schema'],
+                },
+            },
+            {
+                name: 'get_job_status',
+                description: `Check the current status of a QA job. Jobs progress through states: pending → claimed → in_progress → completed (or failed/timeout).
+
+Use this to poll for completion before fetching results. Typical job completion time is 2-10 minutes depending on test complexity.
+
+Returns: { status: "pending" | "claimed" | "in_progress" | "completed" | "failed" | "timeout", message: "..." }`,
+                inputSchema: {
+                    type: 'object',
+                    properties: {
+                        jobId: {
+                            type: 'string',
+                            description: 'The job ID returned from create_job. Example: "550e8400-e29b-41d4-a716-446655440000"',
+                        },
+                    },
+                    required: ['jobId'],
+                },
+            },
+            {
+                name: 'get_job_result',
+                description: `Get the structured results of a completed QA job. Only call this after get_job_status shows status="completed".
+
+Returns the tester's response extracted into your specified schema, plus metadata about timing and the raw tester response.
+
+If the job isn't complete yet, returns an error. If extraction failed, includes the raw response so you can see what the tester said.`,
+                inputSchema: {
+                    type: 'object',
+                    properties: {
+                        jobId: {
+                            type: 'string',
+                            description: 'The job ID of a completed job. Example: "550e8400-e29b-41d4-a716-446655440000"',
+                        },
+                    },
+                    required: ['jobId'],
+                },
+            },
+        ],
+    };
+});
+/**
+ * Handle tool calls
+ */
+server.setRequestHandler(CallToolRequestSchema, async (request) => {
+    const { name, arguments: args } = request.params;
+    if (!args) {
+        throw new Error('Missing arguments');
+    }
+    switch (name) {
+        case 'create_job':
+            try {
+                // Call RunHuman API to create job
+                const response = await fetch(`${API_URL}/api/jobs`, {
+                    method: 'POST',
+                    headers: {
+                        'Authorization': `Bearer ${API_KEY}`,
+                        'Content-Type': 'application/json'
+                    },
+                    body: JSON.stringify({
+                        url: args.url,
+                        description: args.description,
+                        outputSchema: args.schema
+                    })
+                });
+                if (!response.ok) {
+                    const error = await response.json().catch(() => ({ error: response.statusText }));
+                    return {
+                        content: [{
+                                type: 'text',
+                                text: `❌ Failed to create job
+
+Error: ${error.error || error.message || response.statusText}
+Status: ${response.status}
+
+Please check:
+- Your RUNHUMAN_API_KEY is valid
+- The API server is running at ${API_URL}
+- Your API key has permission to create jobs`
+                            }],
+                        isError: true
+                    };
+                }
+                const data = await response.json();
+                return {
+                    content: [
+                        {
+                            type: 'text',
+                            text: `✅ Job created successfully!
+
+Job ID: ${data.jobId}
+Status: ${data.status}
+URL: ${args.url}
+
+Your test has been queued and will be picked up by a human tester shortly.
+
+Next steps:
+- Use get_job_status(jobId: "${data.jobId}") to check progress
+- Typical completion time: 2-10 minutes`,
+                        },
+                    ],
+                };
+            }
+            catch (error) {
+                return {
+                    content: [{
+                            type: 'text',
+                            text: `❌ Error creating job
+
+${error instanceof Error ? error.message : 'Unknown error'}
+
+Please check:
+- The API server is running at ${API_URL}
+- Your network connection
+- Your .env file configuration`
+                        }],
+                    isError: true
+                };
+            }
+        case 'get_job_status':
+            try {
+                const response = await fetch(`${API_URL}/api/jobs/${args.jobId}`, {
+                    headers: {
+                        'Authorization': `Bearer ${API_KEY}`
+                    }
+                });
+                if (!response.ok) {
+                    if (response.status === 404) {
+                        return {
+                            content: [{
+                                    type: 'text',
+                                    text: `❌ Job not found
+
+Job ID: ${args.jobId}
+
+The job does not exist or you don't have permission to access it.`
+                                }],
+                            isError: true
+                        };
+                    }
+                    return {
+                        content: [{
+                                type: 'text',
+                                text: `❌ Failed to get job status
+
+Status: ${response.status}
+Error: ${response.statusText}`
+                            }],
+                        isError: true
+                    };
+                }
+                const job = await response.json();
+                // Format timeline
+                const createdAt = new Date(job.createdAt);
+                const now = new Date();
+                const elapsed = Math.floor((now.getTime() - createdAt.getTime()) / 1000 / 60);
+                const statusEmoji = {
+                    pending: '⏳',
+                    claimed: '👤',
+                    in_progress: '🔄',
+                    completed: '✅',
+                    failed: '❌',
+                    timeout: '⏰'
+                };
+                const emoji = statusEmoji[job.status] || '📊';
+                let message = `${emoji} Job Status: ${job.status}
+
+Job ID: ${job.id}
+URL: ${job.url}
+
+Timeline:
+- Created: ${elapsed} minute${elapsed !== 1 ? 's' : ''} ago`;
+                if (job.claimedAt) {
+                    const claimedElapsed = Math.floor((now.getTime() - new Date(job.claimedAt).getTime()) / 1000 / 60);
+                    message += `\n- Claimed: ${claimedElapsed} minute${claimedElapsed !== 1 ? 's' : ''} ago`;
+                }
+                if (job.status === 'pending') {
+                    message += '\n\nWaiting for a tester to claim this job...';
+                }
+                else if (job.status === 'claimed' || job.status === 'in_progress') {
+                    message += '\n\nThe tester is working on your test. Estimated completion: 2-10 minutes';
+                }
+                else if (job.status === 'completed') {
+                    message += '\n\n✅ Job is complete! Use get_job_result to retrieve the results.';
+                }
+                else if (job.status === 'failed') {
+                    message += '\n\n❌ Job failed. Check the error with get_job_result.';
+                }
+                else if (job.status === 'timeout') {
+                    message += '\n\n⏰ Job timed out. The tester did not complete in time.';
+                }
+                return {
+                    content: [{
+                            type: 'text',
+                            text: message
+                        }]
+                };
+            }
+            catch (error) {
+                return {
+                    content: [{
+                            type: 'text',
+                            text: `❌ Error checking job status
+
+${error instanceof Error ? error.message : 'Unknown error'}`
+                        }],
+                    isError: true
+                };
+            }
+        case 'get_job_result':
+            try {
+                const response = await fetch(`${API_URL}/api/jobs/${args.jobId}`, {
+                    headers: {
+                        'Authorization': `Bearer ${API_KEY}`
+                    }
+                });
+                if (!response.ok) {
+                    if (response.status === 404) {
+                        return {
+                            content: [{
+                                    type: 'text',
+                                    text: `❌ Job not found
+
+Job ID: ${args.jobId}
+
+The job does not exist or you don't have permission to access it.`
+                                }],
+                            isError: true
+                        };
+                    }
+                    return {
+                        content: [{
+                                type: 'text',
+                                text: `❌ Failed to get job result
+
+Status: ${response.status}
+Error: ${response.statusText}`
+                            }],
+                        isError: true
+                    };
+                }
+                const job = await response.json();
+                if (job.status !== 'completed') {
+                    return {
+                        content: [{
+                                type: 'text',
+                                text: `⏳ Job not yet completed
+
+Job ID: ${job.id}
+Current status: ${job.status}
+
+${job.status === 'pending' ? 'Waiting for a tester to claim this job...' :
+                                    job.status === 'claimed' || job.status === 'in_progress' ? 'The tester is working on your test...' :
+                                        job.status === 'failed' ? '❌ Job failed. Error: ' + (job.error || 'Unknown error') :
+                                            job.status === 'timeout' ? '⏰ Job timed out.' :
+                                                'Use get_job_status to check current status.'}`
+                            }]
+                    };
+                }
+                // Job is completed, format results
+                let message = `✅ Test completed!
+
+Job ID: ${job.id}
+URL: ${job.url}
+
+**Tester Response:**
+"${job.testerResponse || 'No response recorded'}"
+
+**Extracted Data:**`;
+                const contents = [
+                    {
+                        type: 'text',
+                        text: message
+                    },
+                    {
+                        type: 'text',
+                        text: JSON.stringify(job.result || {}, null, 2)
+                    }
+                ];
+                if (job.error) {
+                    contents.push({
+                        type: 'text',
+                        text: `\n⚠️ Extraction Warnings:\n${job.error}`
+                    });
+                }
+                return { content: contents };
+            }
+            catch (error) {
+                return {
+                    content: [{
+                            type: 'text',
+                            text: `❌ Error getting job result
+
+${error instanceof Error ? error.message : 'Unknown error'}`
+                        }],
+                    isError: true
+                };
+            }
+        default:
+            throw new Error(`Unknown tool: ${name}`);
+    }
+});
+/**
+ * Start the server
+ */
+async function main() {
+    const transport = new StdioServerTransport();
+    await server.connect(transport);
+    console.error('RunHuman MCP server running on stdio');
+}
+main().catch((error) => {
+    console.error('Server error:', error);
+    process.exit(1);
+});
+//# sourceMappingURL=index.js.map

package/dist/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/index.ts"],"names":[],"mappings":";AAEA;;;;;;;;;;GAUG;AAEH,OAAO,EAAE,MAAM,EAAE,MAAM,2CAA2C,CAAC;AACnE,OAAO,EAAE,oBAAoB,EAAE,MAAM,2CAA2C,CAAC;AACjF,OAAO,EACL,qBAAqB,EACrB,sBAAsB,EACtB,wBAAwB,GACzB,MAAM,oCAAoC,CAAC;AAC5C,OAAO,KAAK,MAAM,MAAM,QAAQ,CAAC;AAEjC,iEAAiE;AACjE,MAAM,CAAC,MAAM,EAAE,CAAC;AAEhB,gBAAgB;AAChB,2CAA2C;AAC3C,0EAA0E;AAC1E,MAAM,IAAI,GAAG,OAAO,CAAC,IAAI,CAAC,KAAK,CAAC,CAAC,CAAC,CAAC;AACnC,MAAM,SAAS,GAAG,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,CAAC,UAAU,CAAC,YAAY,CAAC,CAAC,EAAE,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC;AAChF,MAAM,SAAS,GAAG,IAAI,CAAC,IAAI,CAAC,GAAG,CAAC,EAAE,CAAC,GAAG,CAAC,UAAU,CAAC,YAAY,CAAC,CAAC,EAAE,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAAC;AAEhF,MAAM,OAAO,GAAG,SAAS,IAAI,OAAO,CAAC,GAAG,CAAC,gBAAgB,IAAI,+BAA+B,CAAC;AAC7F,MAAM,OAAO,GAAG,SAAS,IAAI,OAAO,CAAC,GAAG,CAAC,gBAAgB,CAAC;AAE1D,IAAI,CAAC,OAAO,EAAE,CAAC;IACb,OAAO,CAAC,KAAK,CAAC,8BAA8B,CAAC,CAAC;IAC9C,OAAO,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC;IAClB,OAAO,CAAC,KAAK,CAAC,yCAAyC,CAAC,CAAC;IACzD,OAAO,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;IACnB,OAAO,CAAC,KAAK,CAAC,mBAAmB,CAAC,CAAC;IACnC,OAAO,CAAC,KAAK,CAAC,mBAAmB,CAAC,CAAC;IACnC,OAAO,CAAC,KAAK,CAAC,yBAAyB,CAAC,CAAC;IACzC,OAAO,CAAC,KAAK,CAAC,yEAAyE,CAAC,CAAC;IACzF,OAAO,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC;IACvB,OAAO,CAAC,KAAK,CAAC,KAAK,CAAC,CAAC;IACrB,OAAO,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;IACnB,OAAO,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC;IAClB,OAAO,CAAC,KAAK,CAAC,6DAA6D,CAAC,CAAC;IAC7E,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AAClB,CAAC;AAED,OAAO,CAAC,KAAK,CAAC,oCAAoC,OAAO,EAAE,CAAC,CAAC;AAC7D,OAAO,CAAC,KAAK,CAAC,qBAAqB,OAAO,CAAC,SAAS,CAAC,CAAC,EAAE,EAAE,CAAC,KAAK,CAAC,CAAC;AAElE;;GAEG;AACH,MAAM,MAAM,GAAG,IAAI,MAAM,CACvB;IACE,IAAI,EAAE,qBAAqB;IAC3B,OAAO,EAAE,OAAO;CACjB,EACD;IACE,YAAY,EAAE;QACZ,KAAK,EAAE,EAAE;QACT,OAAO,EAAE,EAAE;KACZ;CACF,CACF,CAAC;AAEF;;GAEG;AACH,MAAM,CAAC,iBAAiB,CAAC,wBAAwB,EAAE,KAAK,IAAI,EAAE;IAC5D,OAAO;QACL,OAAO,EAAE;YACP;gBACE,IAAI,EAAE,kBAAkB;gBACxB,WAAW,EAAE,0DAA0D;aACxE;SACF;KACF,CAAC;AACJ,CAAC,CAAC,CAAC;AAEH;;GAEG;AACH,MAAM,CAAC,iBAAiB,CAAC,sBAAsB,EAAE,KAAK,IAAI,EAAE;IAC1D,OAAO;QACL,KAAK,EAAE;YACL;gBACE,IAAI,EAAE,YAAY;gBAClB,WAAW,EAAE;;;;;;;;;;;;;;gDAc2B;gBACxC,WAAW,EAAE;oBACX,IAAI,EAAE,QAAQ;oBACd,UAAU,EAAE;wBACV,GAAG,EAAE;4BACH,IAAI,EAAE,QAAQ;4BACd,WAAW,EAAE,sFAAsF;yBACpG;wBACD,WAAW,EAAE;4BACX,IAAI,EAAE,QAAQ;4BACd,WAAW,EAAE,6PAA6P;yBAC3Q;wBACD,MAAM,EAAE;4BACN,IAAI,EAAE,QAAQ;4BACd,WAAW,EAAE,mRAAmR;yBACjS;qBACF;oBACD,QAAQ,EAAE,CAAC,KAAK,EAAE,aAAa,EAAE,QAAQ,CAAC;iBAC3C;aACF;YACD;gBACE,IAAI,EAAE,gBAAgB;gBACtB,WAAW,EAAE;;;;gHAI2F;gBACxG,WAAW,EAAE;oBACX,IAAI,EAAE,QAAQ;oBACd,UAAU,EAAE;wBACV,KAAK,EAAE;4BACL,IAAI,EAAE,QAAQ;4BACd,WAAW,EAAE,sFAAsF;yBACpG;qBACF;oBACD,QAAQ,EAAE,CAAC,OAAO,CAAC;iBACpB;aACF;YACD;gBACE,IAAI,EAAE,gBAAgB;gBACtB,WAAW,EAAE;;;;sIAIiH;gBAC9H,WAAW,EAAE;oBACX,IAAI,EAAE,QAAQ;oBACd,UAAU,EAAE;wBACV,KAAK,EAAE;4BACL,IAAI,EAAE,QAAQ;4BACd,WAAW,EAAE,gFAAgF;yBAC9F;qBACF;oBACD,QAAQ,EAAE,CAAC,OAAO,CAAC;iBACpB;aACF;SACF;KACF,CAAC;AACJ,CAAC,CAAC,CAAC;AAEH;;GAEG;AACH,MAAM,CAAC,iBAAiB,CAAC,qBAAqB,EAAE,KAAK,EAAE,OAAO,EAAE,EAAE;IAChE,MAAM,EAAE,IAAI,EAAE,SAAS,EAAE,IAAI,EAAE,GAAG,OAAO,CAAC,MAAM,CAAC;IAEjD,IAAI,CAAC,IAAI,EAAE,CAAC;QACV,MAAM,IAAI,KAAK,CAAC,mBAAmB,CAAC,CAAC;IACvC,CAAC;IAED,QAAQ,IAAI,EAAE,CAAC;QACb,KAAK,YAAY;YACf,IAAI,CAAC;gBACH,kCAAkC;gBAClC,MAAM,QAAQ,GAAG,MAAM,KAAK,CAAC,GAAG,OAAO,WAAW,EAAE;oBAClD,MAAM,EAAE,MAAM;oBACd,OAAO,EAAE;wBACP,eAAe,EAAE,UAAU,OAAO,EAAE;wBACpC,cAAc,EAAE,kBAAkB;qBACnC;oBACD,IAAI,EAAE,IAAI,CAAC,SAAS,CAAC;wBACnB,GAAG,EAAE,IAAI,CAAC,GAAG;wBACb,WAAW,EAAE,IAAI,CAAC,WAAW;wBAC7B,YAAY,EAAE,IAAI,CAAC,MAAM;qBAC1B,CAAC;iBACH,CAAC,CAAC;gBAEH,IAAI,CAAC,QAAQ,CAAC,EAAE,EAAE,CAAC;oBACjB,MAAM,KAAK,GAAG,MAAM,QAAQ,CAAC,IAAI,EAAE,CAAC,KAAK,CAAC,GAAG,EAAE,CAAC,CAAC,EAAE,KAAK,EAAE,QAAQ,CAAC,UAAU,EAAE,CAAC,CAAQ,CAAC;oBACzF,OAAO;wBACL,OAAO,EAAE,CAAC;gCACR,IAAI,EAAE,MAAM;gCACZ,IAAI,EAAE;;SAEX,KAAK,CAAC,KAAK,IAAI,KAAK,CAAC,OAAO,IAAI,QAAQ,CAAC,UAAU;UAClD,QAAQ,CAAC,MAAM;;;;iCAIQ,OAAO;6CACK;6BAChC,CAAC;wBACF,OAAO,EAAE,IAAI;qBACd,CAAC;gBACJ,CAAC;gBAED,MAAM,IAAI,GAAG,MAAM,QAAQ,CAAC,IAAI,EAAuC,CAAC;gBAExE,OAAO;oBACL,OAAO,EAAE;wBACP;4BACE,IAAI,EAAE,MAAM;4BACZ,IAAI,EAAE;;UAEV,IAAI,CAAC,KAAK;UACV,IAAI,CAAC,MAAM;OACd,IAAI,CAAC,GAAG;;;;;+BAKgB,IAAI,CAAC,KAAK;wCACD;yBAC3B;qBACF;iBACF,CAAC;YACJ,CAAC;YAAC,OAAO,KAAK,EAAE,CAAC;gBACf,OAAO;oBACL,OAAO,EAAE,CAAC;4BACR,IAAI,EAAE,MAAM;4BACZ,IAAI,EAAE;;EAEhB,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe;;;iCAGzB,OAAO;;+BAET;yBACpB,CAAC;oBACF,OAAO,EAAE,IAAI;iBACd,CAAC;YACJ,CAAC;QAEH,KAAK,gBAAgB;YACnB,IAAI,CAAC;gBACH,MAAM,QAAQ,GAAG,MAAM,KAAK,CAAC,GAAG,OAAO,aAAa,IAAI,CAAC,KAAK,EAAE,EAAE;oBAChE,OAAO,EAAE;wBACP,eAAe,EAAE,UAAU,OAAO,EAAE;qBACrC;iBACF,CAAC,CAAC;gBAEH,IAAI,CAAC,QAAQ,CAAC,EAAE,EAAE,CAAC;oBACjB,IAAI,QAAQ,CAAC,MAAM,KAAK,GAAG,EAAE,CAAC;wBAC5B,OAAO;4BACL,OAAO,EAAE,CAAC;oCACR,IAAI,EAAE,MAAM;oCACZ,IAAI,EAAE;;UAEZ,IAAI,CAAC,KAAK;;kEAE8C;iCACnD,CAAC;4BACF,OAAO,EAAE,IAAI;yBACd,CAAC;oBACJ,CAAC;oBAED,OAAO;wBACL,OAAO,EAAE,CAAC;gCACR,IAAI,EAAE,MAAM;gCACZ,IAAI,EAAE;;UAEV,QAAQ,CAAC,MAAM;SAChB,QAAQ,CAAC,UAAU,EAAE;6BACjB,CAAC;wBACF,OAAO,EAAE,IAAI;qBACd,CAAC;gBACJ,CAAC;gBAED,MAAM,GAAG,GAAG,MAAM,QAAQ,CAAC,IAAI,EAM9B,CAAC;gBAEF,kBAAkB;gBAClB,MAAM,SAAS,GAAG,IAAI,IAAI,CAAC,GAAG,CAAC,SAAS,CAAC,CAAC;gBAC1C,MAAM,GAAG,GAAG,IAAI,IAAI,EAAE,CAAC;gBACvB,MAAM,OAAO,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,OAAO,EAAE,GAAG,SAAS,CAAC,OAAO,EAAE,CAAC,GAAG,IAAI,GAAG,EAAE,CAAC,CAAC;gBAE9E,MAAM,WAAW,GAA2B;oBAC1C,OAAO,EAAE,GAAG;oBACZ,OAAO,EAAE,IAAI;oBACb,WAAW,EAAE,IAAI;oBACjB,SAAS,EAAE,GAAG;oBACd,MAAM,EAAE,GAAG;oBACX,OAAO,EAAE,GAAG;iBACb,CAAC;gBACF,MAAM,KAAK,GAAG,WAAW,CAAC,GAAG,CAAC,MAAM,CAAC,IAAI,IAAI,CAAC;gBAE9C,IAAI,OAAO,GAAG,GAAG,KAAK,gBAAgB,GAAG,CAAC,MAAM;;UAE9C,GAAG,CAAC,EAAE;OACT,GAAG,CAAC,GAAG;;;aAGD,OAAO,UAAU,OAAO,KAAK,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC;gBAErD,IAAI,GAAG,CAAC,SAAS,EAAE,CAAC;oBAClB,MAAM,cAAc,GAAG,IAAI,CAAC,KAAK,CAAC,CAAC,GAAG,CAAC,OAAO,EAAE,GAAG,IAAI,IAAI,CAAC,GAAG,CAAC,SAAS,CAAC,CAAC,OAAO,EAAE,CAAC,GAAG,IAAI,GAAG,EAAE,CAAC,CAAC;oBACnG,OAAO,IAAI,gBAAgB,cAAc,UAAU,cAAc,KAAK,CAAC,CAAC,CAAC,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,MAAM,CAAC;gBAC3F,CAAC;gBAED,IAAI,GAAG,CAAC,MAAM,KAAK,SAAS,EAAE,CAAC;oBAC7B,OAAO,IAAI,+CAA+C,CAAC;gBAC7D,CAAC;qBAAM,IAAI,GAAG,CAAC,MAAM,KAAK,SAAS,IAAI,GAAG,CAAC,MAAM,KAAK,aAAa,EAAE,CAAC;oBACpE,OAAO,IAAI,4EAA4E,CAAC;gBAC1F,CAAC;qBAAM,IAAI,GAAG,CAAC,MAAM,KAAK,WAAW,EAAE,CAAC;oBACtC,OAAO,IAAI,oEAAoE,CAAC;gBAClF,CAAC;qBAAM,IAAI,GAAG,CAAC,MAAM,KAAK,QAAQ,EAAE,CAAC;oBACnC,OAAO,IAAI,wDAAwD,CAAC;gBACtE,CAAC;qBAAM,IAAI,GAAG,CAAC,MAAM,KAAK,SAAS,EAAE,CAAC;oBACpC,OAAO,IAAI,2DAA2D,CAAC;gBACzE,CAAC;gBAED,OAAO;oBACL,OAAO,EAAE,CAAC;4BACR,IAAI,EAAE,MAAM;4BACZ,IAAI,EAAE,OAAO;yBACd,CAAC;iBACH,CAAC;YACJ,CAAC;YAAC,OAAO,KAAK,EAAE,CAAC;gBACf,OAAO;oBACL,OAAO,EAAE,CAAC;4BACR,IAAI,EAAE,MAAM;4BACZ,IAAI,EAAE;;EAEhB,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe,EAAE;yBACjD,CAAC;oBACF,OAAO,EAAE,IAAI;iBACd,CAAC;YACJ,CAAC;QAEH,KAAK,gBAAgB;YACnB,IAAI,CAAC;gBACH,MAAM,QAAQ,GAAG,MAAM,KAAK,CAAC,GAAG,OAAO,aAAa,IAAI,CAAC,KAAK,EAAE,EAAE;oBAChE,OAAO,EAAE;wBACP,eAAe,EAAE,UAAU,OAAO,EAAE;qBACrC;iBACF,CAAC,CAAC;gBAEH,IAAI,CAAC,QAAQ,CAAC,EAAE,EAAE,CAAC;oBACjB,IAAI,QAAQ,CAAC,MAAM,KAAK,GAAG,EAAE,CAAC;wBAC5B,OAAO;4BACL,OAAO,EAAE,CAAC;oCACR,IAAI,EAAE,MAAM;oCACZ,IAAI,EAAE;;UAEZ,IAAI,CAAC,KAAK;;kEAE8C;iCACnD,CAAC;4BACF,OAAO,EAAE,IAAI;yBACd,CAAC;oBACJ,CAAC;oBAED,OAAO;wBACL,OAAO,EAAE,CAAC;gCACR,IAAI,EAAE,MAAM;gCACZ,IAAI,EAAE;;UAEV,QAAQ,CAAC,MAAM;SAChB,QAAQ,CAAC,UAAU,EAAE;6BACjB,CAAC;wBACF,OAAO,EAAE,IAAI;qBACd,CAAC;gBACJ,CAAC;gBAED,MAAM,GAAG,GAAG,MAAM,QAAQ,CAAC,IAAI,EAO9B,CAAC;gBAEF,IAAI,GAAG,CAAC,MAAM,KAAK,WAAW,EAAE,CAAC;oBAC/B,OAAO;wBACL,OAAO,EAAE,CAAC;gCACR,IAAI,EAAE,MAAM;gCACZ,IAAI,EAAE;;UAEV,GAAG,CAAC,EAAE;kBACE,GAAG,CAAC,MAAM;;EAE1B,GAAG,CAAC,MAAM,KAAK,SAAS,CAAC,CAAC,CAAC,2CAA2C,CAAC,CAAC;oCACxE,GAAG,CAAC,MAAM,KAAK,SAAS,IAAI,GAAG,CAAC,MAAM,KAAK,aAAa,CAAC,CAAC,CAAC,uCAAuC,CAAC,CAAC;wCACpG,GAAG,CAAC,MAAM,KAAK,QAAQ,CAAC,CAAC,CAAC,uBAAuB,GAAG,CAAC,GAAG,CAAC,KAAK,IAAI,eAAe,CAAC,CAAC,CAAC;4CACpF,GAAG,CAAC,MAAM,KAAK,SAAS,CAAC,CAAC,CAAC,kBAAkB,CAAC,CAAC;gDAC/C,6CAA6C,EAAE;6BACpC,CAAC;qBACH,CAAC;gBACJ,CAAC;gBAED,mCAAmC;gBACnC,IAAI,OAAO,GAAG;;UAEZ,GAAG,CAAC,EAAE;OACT,GAAG,CAAC,GAAG;;;GAGX,GAAG,CAAC,cAAc,IAAI,sBAAsB;;oBAE3B,CAAC;gBAEb,MAAM,QAAQ,GAAG;oBACf;wBACE,IAAI,EAAE,MAAM;wBACZ,IAAI,EAAE,OAAO;qBACd;oBACD;wBACE,IAAI,EAAE,MAAM;wBACZ,IAAI,EAAE,IAAI,CAAC,SAAS,CAAC,GAAG,CAAC,MAAM,IAAI,EAAE,EAAE,IAAI,EAAE,CAAC,CAAC;qBAChD;iBACF,CAAC;gBAEF,IAAI,GAAG,CAAC,KAAK,EAAE,CAAC;oBACd,QAAQ,CAAC,IAAI,CAAC;wBACZ,IAAI,EAAE,MAAM;wBACZ,IAAI,EAAE,8BAA8B,GAAG,CAAC,KAAK,EAAE;qBAChD,CAAC,CAAC;gBACL,CAAC;gBAED,OAAO,EAAE,OAAO,EAAE,QAAQ,EAAE,CAAC;YAC/B,CAAC;YAAC,OAAO,KAAK,EAAE,CAAC;gBACf,OAAO;oBACL,OAAO,EAAE,CAAC;4BACR,IAAI,EAAE,MAAM;4BACZ,IAAI,EAAE;;EAEhB,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,eAAe,EAAE;yBACjD,CAAC;oBACF,OAAO,EAAE,IAAI;iBACd,CAAC;YACJ,CAAC;QAEH;YACE,MAAM,IAAI,KAAK,CAAC,iBAAiB,IAAI,EAAE,CAAC,CAAC;IAC7C,CAAC;AACH,CAAC,CAAC,CAAC;AAEH;;GAEG;AACH,KAAK,UAAU,IAAI;IACjB,MAAM,SAAS,GAAG,IAAI,oBAAoB,EAAE,CAAC;IAC7C,MAAM,MAAM,CAAC,OAAO,CAAC,SAAS,CAAC,CAAC;IAChC,OAAO,CAAC,KAAK,CAAC,sCAAsC,CAAC,CAAC;AACxD,CAAC;AAED,IAAI,EAAE,CAAC,KAAK,CAAC,CAAC,KAAK,EAAE,EAAE;IACrB,OAAO,CAAC,KAAK,CAAC,eAAe,EAAE,KAAK,CAAC,CAAC;IACtC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AAClB,CAAC,CAAC,CAAC"}

package/package.json

@@ -0,0 +1,59 @@
+{
+  "name": "@runhuman/mcp-server",
+  "version": "1.0.0",
+  "description": "Model Context Protocol (MCP) server for RunHuman - Human-powered QA testing for AI agents",
+  "main": "dist/index.js",
+  "type": "module",
+  "bin": {
+    "runhuman-mcp": "dist/index.js"
+  },
+  "files": [
+    "dist",
+    "README.md",
+    ".env.example"
+  ],
+  "scripts": {
+    "build": "tsc",
+    "dev": "tsx watch src/index.ts",
+    "start": "node dist/index.js",
+    "prepublishOnly": "npm run build",
+    "test": "node test-simple.cjs",
+    "test:all": "node test-all-tools.cjs",
+    "test:inspector": "npx @modelcontextprotocol/inspector node dist/index.js"
+  },
+  "keywords": [
+    "mcp",
+    "model-context-protocol",
+    "qa",
+    "testing",
+    "human-in-the-loop",
+    "ai-agent",
+    "claude",
+    "anthropic",
+    "qa-testing",
+    "manual-testing"
+  ],
+  "author": "RunHuman <hey@runhuman.com>",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/yueranyuan/qa-experiment.git",
+    "directory": "packages/mcp-server"
+  },
+  "homepage": "https://runhuman.com",
+  "bugs": {
+    "url": "https://github.com/yueranyuan/qa-experiment/issues"
+  },
+  "license": "ISC",
+  "engines": {
+    "node": ">=18.0.0"
+  },
+  "dependencies": {
+    "@modelcontextprotocol/sdk": "latest",
+    "dotenv": "^17.2.3"
+  },
+  "devDependencies": {
+    "@types/node": "^20.11.17",
+    "tsx": "^4.7.1",
+    "typescript": "^5.3.3"
+  }
+}