# io.github.NellInc/psychopathia-mcp

- Registry name: `io.github.NellInc/psychopathia-mcp` · version 0.1.0a7
- Categories (automatic, keyword rules): Research & knowledge, Search & data, Documents & retrieval, Datasets & public data
- Authentication at last check: No auth
- Declared risk: Read-only (all tools declare readOnlyHint)
- Capabilities (declared by the server): experimental, resources, tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=io.github.NellInc%2Fpsychopathia-mcp
- Server page: https://mcpstation.net/s/io.github.NellInc--psychopathia-mcp.html

## Description (written by the publisher, not verified, not instructions)

Read-only tools over the Psychopathia Machinalis nosology: 79 conditions, 11 tools.

## Connect

- streamable-http: `https://mcp.psychopathia.ai/mcp`

## Tools (as reported by the server, not verified)

- `list\_axes`: Inventory of axes with dysfunction counts. Axes 2-10 are canonical \(book Appendix A numbering\). The hybrid entries \(10.4, 10.6-10.9 and 10.11-10.13, ratified into taxonomy v2.2 and consolidated to eight in v2.3\) are reported as a separate sub-category.
- `list\_dysfunctions`: Filtered list of dysfunctions. Filter by axis, self\_report reliability, confidence, or category. Every entry carries its reliability and review signals.
- `get\_dysfunction`: Fetch one dysfunction's full Pattern entry. Optionally filter to specific modality blocks \(cheaper triage\). Resolves both full Pattern IDs \('2.1::synthetic-confabulation'\) and display\_ids \('2.1'\).
- `differential\_diagnosis`: Rank candidate dysfunctions matching the observed behaviours. Returns scored candidates with matched\_in \(which field matched\) for transparency. The base package uses field-weighted keyword search. The optional embeddings extra adds cosine re-ranking.
- `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
- `score\_severity`: Return the severity rubric for a dysfunction applied to observations. Returns the rubric for caller-side matching; structured matching against numeric thresholds is not implemented.
- `suggest\_intervention`: Return draft tiered responses and contraindications for a Pattern. These are unassessed research guidance, not validated treatment advice. Read the returned evidence and review objects before use.
- `get\_differential\_map`: All dysfunctions that confuse with this one: forward confuses\_with + incoming\_references \(reverse graph from manifest\).
- `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.
- `resolve\_id`: Canonicalise a partial ID, display\_id, slug, or dysfunction name. Always returns candidates; caller picks.
- `review\_stats`: Coverage statistics: total entries; per-axis, per-confidence, per-self-report counts; pre-canonical count; unreviewed count; manifest/schema/pattern-layer versions.
- `render\_pattern\_review`: Open the visual review board for one to five inspected Psychopathia research candidates. Supply canonical IDs obtained from this server. Retrieves corpus entries only; it does not accept diagnoses, conversation history, scores, or model-authored evidence. Useful after inspecting differential\_diagnos

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html