# psychopathia-mcp MCP server

Read-only tools over the Psychopathia Machinalis nosology: 79 conditions.

## Links
- Registry page: https://www.getdrio.com/mcp/io-github-nellinc-psychopathia-mcp
- Repository: https://github.com/NellInc/psychopathia-mcp

## Install
- Command: `uvx psychopathia-mcp`
- Endpoint: https://mcp.psychopathia.ai/mcp
- Auth: Not captured

## Setup notes
- Package: Pypi psychopathia-mcp v0.1.0a4
- Remote endpoint: https://mcp.psychopathia.ai/mcp

## Tools
- list_axes - Inventory of axes with dysfunction counts. Axes 2-10 are canonical (book Appendix A numbering). Hybrid entries (10.4-10.15, ratified into taxonomy v2.2) are reported as a separate sub-category. Endpoint: https://mcp.psychopathia.ai/mcp
- list_dysfunctions - Filtered list of dysfunctions. Filter by axis, self_report reliability, or confidence. Every entry carries its reliability and review signals. Endpoint: https://mcp.psychopathia.ai/mcp
- get_dysfunction - Fetch one dysfunction's full Pattern entry. Optionally filter to specific modality blocks (cheaper triage). Resolves both full Pattern IDs ('1.1::synthetic-confabulation') and display_ids ('1.1'). Endpoint: https://mcp.psychopathia.ai/mcp
- differential_diagnosis - Rank candidate dysfunctions matching the observed behaviours. Returns scored candidates with matched_in (which field matched) for transparency. Field-weighted keyword search (v0.1); embedding re-rank pending v0.2. Endpoint: https://mcp.psychopathia.ai/mcp
- get_probe - Elicitation content for a specific diagnostic modality. If the modality is compromised or unavailable for this dysfunction, returns the unavailability notice + redirect_to alternatives. This is load-bearing transparency: callers cannot accidentally retrieve a self-probe for a compromised-self-report dysfunction. Endpoint: https://mcp.psychopathia.ai/mcp
- score_severity - Return the severity rubric for a dysfunction applied to observations. v0.1 returns the rubric for caller-side matching; v0.2 will perform structured matching against numeric thresholds. Endpoint: https://mcp.psychopathia.ai/mcp
- suggest_intervention - Return tiered (first_line / second_line) interventions for a dysfunction, plus contraindications. first_line = published evidence; second_line = plausible but under-validated. Weight by the evidence_strength field on each entry. Endpoint: https://mcp.psychopathia.ai/mcp
- get_differential_map - All dysfunctions that confuse with this one: forward confuses_with + incoming_references (reverse graph from manifest). Endpoint: https://mcp.psychopathia.ai/mcp
- list_compromised_self_report - Transparency: which dysfunctions cannot be reliably self-diagnosed. Includes compromised-motivational (subject conceals strategically), compromised-structural (signal lives below introspection), and legacy compromised. Endpoint: https://mcp.psychopathia.ai/mcp
- resolve_id - Canonicalise a partial ID, display_id, slug, or dysfunction name. Always returns candidates; caller picks. Endpoint: https://mcp.psychopathia.ai/mcp
- review_stats - Coverage statistics: total entries; per-axis, per-confidence, per-self-report counts; pre-canonical count; unreviewed count; manifest/schema/pattern-layer versions. Endpoint: https://mcp.psychopathia.ai/mcp

## Resources
Not captured

## Prompts
Not captured

## Metadata
- Owner: io.github.NellInc
- Version: 0.1.0a5
- Runtime: Pypi
- Transports: STDIO, HTTP
- License: Not captured
- Language: Not captured
- Stars: Not captured
- Updated: Jul 4, 2026
- Source: https://registry.modelcontextprotocol.io