slopwatch_status
Retrieve current slop score and statistics to track AI system accountability by comparing promised versus delivered implementations.
Instructions
Get current slop score and statistics
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"random_string": "<random_string>"
},
"name": "slopwatch_status"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| random_string | Yes | Dummy parameter for no-parameter tools |
Implementation Reference
- src/mcp-server.js:304-317 (handler)The handleStatus method implements the core logic for the slopwatch_status tool, calculating accuracy from claims and verification results and returning a simple status message.
async handleStatus(args) { const totalClaims = this.claims.size; const verifiedClaims = this.verificationResults.filter(r => r.isVerified).length; const accuracy = totalClaims > 0 ? Math.round((verifiedClaims / totalClaims) * 100) : 100; return { content: [ { type: 'text', text: `Accuracy: ${accuracy}% (${verifiedClaims}/${totalClaims})` } ] }; } - src/index.ts:269-304 (handler)The getStatus function implements the slopwatch_status tool handler, providing detailed server status including recent verification history if requested.
async function getStatus(args: any, claims: Map<string, any>, verificationResults: any[]) { const { detailed = false } = args || {}; const totalClaims = claims.size; const verifiedClaims = verificationResults.filter(r => r.isVerified).length; const failedClaims = verificationResults.filter(r => !r.isVerified).length; const accuracy = totalClaims === 0 ? 100 : Math.round((verifiedClaims / totalClaims) * 100); let output = `š„ SlopWatch Server Status\n\n`; output += `š Total Claims: ${totalClaims}\n`; output += `ā Verified: ${verifiedClaims}\n`; output += `ā Failed: ${failedClaims}\n`; output += `šÆ AI Accuracy: ${accuracy}%\n\n`; if (detailed && verificationResults.length > 0) { output += `š Recent Verification History:\n`; verificationResults.slice(-5).forEach((result, i) => { const status = result.isVerified ? 'ā ' : 'ā'; output += ` ${status} "${result.claim}" (${result.confidence}%)\n`; }); } output += `\nš” How to use:\n`; output += `1. AI calls slopwatch_claim("what I'm implementing", ["file1.js"], "js")\n`; output += `2. AI makes the changes\n`; output += `3. AI calls slopwatch_verify(claimId)\n`; output += `4. Get instant lie detection results!\n`; return { content: [ { type: 'text', text: output } ] }; - src/mcp-server.js:66-79 (registration)Registration of the slopwatch_status tool in the ListTools response, defining name, description, and input schema.
{ name: 'slopwatch_status', description: 'Get current slop score and statistics', inputSchema: { type: 'object', properties: { random_string: { type: 'string', description: 'Dummy parameter for no-parameter tools' } }, required: ['random_string'] } }, - src/index.ts:88-100 (registration)Registration of the slopwatch_status tool in the ListTools response for the stateless server, including optional detailed parameter.
{ name: 'slopwatch_status', description: 'š Get current SlopWatch status and recent verification results', inputSchema: { type: 'object', properties: { detailed: { type: 'boolean', description: 'Show detailed verification history', } }, }, } - src/mcp-server.js:69-77 (schema)Input schema definition for slopwatch_status tool requiring a dummy random_string parameter.
inputSchema: { type: 'object', properties: { random_string: { type: 'string', description: 'Dummy parameter for no-parameter tools' } }, required: ['random_string']