# addiction-recovery-mcp -- Full Reference # addiction-recovery-mcp MCP server. ## Server - Name: addiction-recovery-mcp - Version: 1.0.0 - MCP Protocol: 2024-11-05 - Endpoint: https://addiction-recovery.forkjoin.ai/mcp - Discovery/docs quota: none - Paper: "Being Irreversible" by Taylor William Buley ## Tools ### temptation_boundary Compute distance to the relapse boundary using void boundary analysis. Given craving intensity and threshold, returns distance, crossed status, and safety margin. The boundary is sharp (Law 6) -- there is no gradual transition. Input schema: ```json { "type": "object", "properties": { "cravingIntensity": { "type": "number", "description": "Current craving intensity (0-100)" }, "threshold": { "type": "number", "description": "Relapse boundary threshold" } }, "required": [ "cravingIntensity", "threshold" ] } ``` ### relapse_risk Compute composite relapse risk using the God Formula. Sleep debt and stress increase risk; days sober decrease it. Returns weighted risk assessment where higher weight means lower risk. The sliver: recovery is always possible. Input schema: ```json { "type": "object", "properties": { "daysSober": { "type": "number", "description": "Number of days sober" }, "sleepDebtHours": { "type": "number", "description": "Hours of accumulated sleep debt" }, "stressLevel": { "type": "number", "description": "Current stress level (0-100)" }, "totalObservations": { "type": "number", "description": "Total observation rounds for normalization" } }, "required": [ "daysSober", "sleepDebtHours", "stressLevel", "totalObservations" ] } ``` ### recovery_convergence Check if recovery trajectory is converging (cravings decreasing over time). Computes ratio of consecutive craving levels. If ratio consistently < 1, the trajectory is converging. Returns rate and estimated days to baseline. Input schema: ```json { "type": "object", "properties": { "sobrietyDays": { "type": "array", "items": { "type": "number" }, "description": "Array of day numbers (e.g., [1, 7, 14, 30])" }, "cravingLevels": { "type": "array", "items": { "type": "number" }, "description": "Craving intensity at each day (e.g., [90, 70, 50, 30])" } }, "required": [ "sobrietyDays", "cravingLevels" ] } ``` ### emotional_trigger_map Map emotional triggers that increase relapse risk. Returns trigger ranking by intensity and coping strategies per trigger. The emotions are the territory -- mapping them reduces their power. Input schema: ```json { "type": "object", "properties": { "triggers": { "type": "array", "items": { "type": "object", "properties": { "situation": { "type": "string" }, "emotion": { "type": "string" }, "intensity": { "type": "number" } }, "required": [ "situation", "emotion", "intensity" ] }, "description": "Array of trigger situations with associated emotions and intensities" } }, "required": [ "triggers" ] } ``` ### sobriety_walk Model the recovery journey as void walking. Applies the God Formula to life decisions. The sliver: every path retains minimum weight -- recovery is always possible. Returns the complement distribution over decisions. Input schema: ```json { "type": "object", "properties": { "decisions": { "type": "array", "items": { "type": "object", "properties": { "name": { "type": "string" }, "rejections": { "type": "number" } }, "required": [ "name", "rejections" ] }, "description": "Life decisions with rejection counts" }, "totalRounds": { "type": "number", "description": "Total rounds of decision-making" } }, "required": [ "decisions", "totalRounds" ] } ``` ## Discovery Endpoints - /llms.txt -- This file - /llms-full.txt -- Full reference (you are here) - /skills -- Skill definitions - /agents.json -- Agent manifest - /.well-known/mcp.json -- MCP discovery - /.well-known/agent-card.json -- Agent card - /.well-known/openapi.json -- OpenAPI spec - /.well-known/security.txt -- Security contact ## Integration Connect via any MCP-compatible client (Claude, ChatGPT, Cursor, etc.) POST https://addiction-recovery.forkjoin.ai/mcp with JSON-RPC 2.0 body. ## Parent Part of the ForkJoin MCP server family at https://forkjoin.ai Superserver: https://mcp.forkjoin.ai