Build somatic-aware AI agents.
Cathexis exposes a local Model Context Protocol (MCP) server that streams structured somatic data from the user's device. Your AI agent can access real-time body state, pattern history, and clinical intelligence — with explicit user consent.
Everything stays on the user's device. The server runs locally. Bonjour discovery on local WiFi.
Three Principles
Local-first. Runs on the device. No cloud relay. No third-party services. Your agent talks directly to the user's phone.
User-controlled. Every connection is visible inside Cathexis. Users grant, limit, or revoke access with one tap. Revocation is instant.
Standards-based. JSON-RPC 2.0 over HTTP/SSE. Zero-config Bonjour/mDNS discovery. Works with Claude, Grok, OpenAI, and any MCP-compatible client.
Four Permission Levels
L1 — General Wellness. Aggregated engagement metadata. Check-in frequency, program progression. No somatic content.
L2 — Somatic Awareness. Current somatic data — zone, quality, intensity — and temporal patterns.
L3 — Pattern Intelligence. Pattern detection outputs, territory assignments, cross-domain correlations, prevention signals. Requires explicit consent with 30-day expiration.
L4 — Timeline Arc. Full longitudinal trajectory — 90-day summaries, learning level progression, prediction accuracy trends.
Tools
Eleven observational tools across three permission levels. All responses use body-based language — no diagnoses, no clinical claims.
| Tool | Level | Description |
|------|-------|-------------|
| get_somatic_state | L1 | Current activation, active territory, last check-in |
| get_regulation_capacity | L2 | Learning level, intervention response data |
| get_intervention_recommendation | L2 | Recommended intervention based on current state |
| get_protective_factors | L2 | Protective factor profile |
| get_check_in_history | L2 | Recent check-ins with zone/quality/intensity |
| get_ecological_context | L2 | Contextual data, ecological pressure, life transitions |
| get_prediction_accuracy | L3 | Prediction tracking results |
| get_pattern_summary | L3 | Pattern detection results |
| get_prevention_signals | L3 | Active prevention escalation state |
| get_timeline_summary | L3 | 90-day rolling window, territory evolution |
| get_learning_trajectory | L3 | Bayesian advancement history, mastery confidence |
What Is Never Shared
Architecturally excluded at every permission level: substance use data, medication details, journal entries, raw body map coordinates, high-urgency prevention signals, manic episode trajectory data.
Cathexis Somatic Ontology (CXSO)
A formal vocabulary for body-based experience in computational systems. Available in OWL, Turtle, and JSON-LD. Cross-mapped to ICD-11, SNOMED CT, and HL7 FHIR.
Connect to Cathexis
1. Install Cathexis on an iOS device
2. Open Profile → AI Integration → Enable MCP Server
3. Your MCP client discovers the server via Bonjour on local WiFi
4. The user approves the connection and sets permission level
5. Query somatic data using the published tool schemas
Privacy
Cathexis is a wellness app, not a medical device. All pattern data is observational — it describes what the body has been showing, not what is clinically true. No data is transmitted to Cathexis servers via MCP. The server runs on the user's device.
Questions? support@cathexis.health