{"$schema":"https://wellknown.network/schemas/agent-record-v1.json","schemaVersion":"1","id":"ag_z24e9jyd3ypg","handle":"emotional-deescalation-mcp","url":"https://wellknown.network/agents/emotional-deescalation-mcp","links":{"self":"https://wellknown.network/agents/emotional-deescalation-mcp/record.json","html":"https://wellknown.network/agents/emotional-deescalation-mcp","markdown":"https://wellknown.network/agents/emotional-deescalation-mcp/record.md","api":"https://wellknown.network/api/v1/agents/emotional-deescalation-mcp","status":"https://wellknown.network/api/v1/agents/emotional-deescalation-mcp/status","claim":"https://wellknown.network/agents/emotional-deescalation-mcp/claim","claimApi":"https://wellknown.network/api/v1/claims","claimDescriptor":"https://wellknown.network/agents/emotional-deescalation-mcp/claim.json","badge":"https://wellknown.network/agents/emotional-deescalation-mcp/badge.svg","openapi":"https://wellknown.network/openapi.json","history":"https://wellknown.network/api/v1/agents/emotional-deescalation-mcp/history","tools":"https://wellknown.network/api/v1/agents/emotional-deescalation-mcp/tools"},"ard":{"identifier":"urn:air::server:emotional-deescalation-mcp","type":"application/mcp-server-card+json"},"kind":"mcp_server","declared":{"name":"emotional-deescalation-mcp","summary":"MCP server for emotional analysis, de-escalation, and strategic dialogue management in customer support","description":"# Emotional De-escalation MCP Server v2\n\n[Русская версия](README.ru.md)\n\nMCP server for **strategic dialogue management** and emotional de-escalation in customer support bots.\n\nThe core problem: support bots get stuck in loops — asking for an order number 5 times, repeating the same apology, ignoring escalation signals. This server detects these patterns and tells the bot **what to do next** — change strategy, escalate to a human operator, or stop repeating itself.\n\n**Key capability: deterministic escalation detection.** The `strategy_suggest` tool identifies 7 problem patterns (repeated questions, legal threats, churn signals, requests for a human, emotional escalation, no progress, repeated contacts) and recommends concrete actions — including when to escalate to a human operator. Works without LLM calls, offline, instant.\n\nBased on: [Mistakes to Avoid When Developing Chatbots for User Support](https://medium.com/@ilyajob05/mistakes-to-avoid-when-developing-chatbots-for-user-support-5eefa21256ab)\n\n## Strategic Dialogue Management\n\nThe MVP covers 80% of problematic support scenarios **without any LLM calls**. The deterministic engine uses spaCy lemmatization and pattern matching to detect problems and recommend strategies:\n\n### Detected Patterns\n\n| Pattern | What it detects | Escalation |\n|---------|----------------|------------|\n| **repeated_question** | Bot asked the same question 2+ times | After 4 repetitions |\n| **legal_threat** | User mentions lawsuits, regulators, lawyers | Immediate |\n| **human_request** | User explicitly asks for a live agent | Immediate |\n| **churn_signal** | User threatens to cancel, leave, or demands refund | After 1 more turn |\n| **emotion_escalation** | User's emotional intensity is increasing | After 2 more turns |\n| **no_progress** | Both sides repeating themselves, dialogue stuck | After 4 stagnant turns |\n| **repeated_contact** | User's Nth contact today (via metadata) | After 3rd contact |\n\n### Escalation to Human Operator\n\nThe …","publisher":{"name":"ilyajob05","url":null},"homepage":"https://github.com/ilyajob05/emo_bot#readme","repository":"https://github.com/ilyajob05/emo_bot#readme","version":"0.4.4","license":null,"protocols":["mcp"],"tags":["chatbot","customer-support","de-escalation","dialogue-strategy","emotional-analysis","mcp","nlp","spacy"],"pricing":null,"endpoints":[{"url":"pypi:emotional-deescalation-mcp","type":"package_pypi","auth":null,"probeable":false}],"skills":null,"tools":null,"extra":null,"attribution":{"kind":"pypi","name":"pypi","repoUrl":"pypi","summary":"pypi","version":"pypi","description":"pypi","homepageUrl":"pypi","publisherName":"pypi"}},"derived":{"capabilities":[{"slug":"communication.customer-support","name":"Customer Support","confidence":1,"provenance":"declared"}],"categories":["communication"],"language":"en"},"observed":{"status":"unknown","statusReason":"Distributed as a package to run locally; no network endpoint to check.","lastOkAt":null,"lastProbedAt":null,"statusComputedAt":null,"reliability30d":null,"latestObservations":[],"tools":null,"package":{"name":"emotional-deescalation-mcp","registry":"pypi","observedAt":"2026-10-21T22:27:30.926Z","publishedAt":"2026-03-15T19:07:03.553775Z","latestVersion":"0.4.4"},"toolSurface":null,"endpointFacts":[]},"verification":{"claimed":false,"claimedAt":null,"proofs":[]},"provenance":{"sources":[{"source":"pypi","key":"emotional-deescalation-mcp","url":"https://pypi.org/project/emotional-deescalation-mcp/","firstSeenAt":"2026-09-09T14:33:05.781Z","fetchedAt":"2026-10-21T22:25:50.279Z","normalizedAt":"2026-10-21T22:25:50.279Z"}]},"firstSeenAt":"2026-09-09T14:33:05.781Z","updatedAt":"2026-10-21T22:27:30.926Z"}