io.github.NellInc/psychopathia-mcp

by NellInc · remote · local (pypi) · no sign-in to list tools · v0.1.0a7 · published by GitHub user NellInc

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

Changes · 3

Compare Registry entry

12 tools: 3 change things and 9 only read.

Scanned Oct 21, 2026

Deletes or cancels0Claude Code: deny
Can't be undone0Claude Code: ask
Changes things3Claude Code: ask: see these tools
Only reads9Claude Code: allow: see these tools

1 check matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http psychopathia https://mcp.psychopathia.ai/mcp

Findings

Matches of fixed checks, with the text they matched.

1 warn

Warnrender_pattern_review
The server marks "render_pattern_review" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
Matched text
annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "open": a word for a change.
What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

12 tools

Changes things 3Creates or changes something that can be changed back.Claude Code: ask

differential_diagnosisRank candidate dysfunctions matching the observed behaviours.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
render_pattern_reviewOpen the visual review board for one to five inspected Psychopathia research candidates.1 finding
Why it is in this group
- The description's first verb is "open": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Findings
- Warn
  The server marks "render_pattern_review" read-only (readOnlyHint: true), and its own name, description or input give the class "write".
  Matched text
  annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":true,"openWorldHint":false}; The description's first verb is "open": a word for a change.
  What this check looks for
Description, as the server wrote it
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_diagnosis and get_dysfunction results. Text clients receive the same corpus-derived comparison without needing a UI.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
review_statsCoverage statistics: total entries; per-axis, per-confidence, per-self-report counts; pre-canonical count; unreviewed count; manifest/schema/pattern-layer versions.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
Description, as the server wrote it
Coverage statistics: total entries; per-axis, per-confidence, per-self-report counts; pre-canonical count; unreviewed count; manifest/schema/pattern-layer versions.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true

Only reads 9Looks things up and changes nothing.Claude Code: allow

get_differential_mapAll dysfunctions that confuse with this one: forward confuses_with + incoming_references (reverse graph from manifest).No findings
Why it is in this group
- The name "get_differential_map" says "get": a word for reading.
Description, as the server wrote it
All dysfunctions that confuse with this one: forward confuses_with + incoming_references (reverse graph from manifest).
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_dysfunctionFetch one dysfunction's full Pattern entry.No findings
Why it is in this group
- The name "get_dysfunction" says "get": a word for reading.
Description, as the server wrote it
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').
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
get_probeElicitation content for a specific diagnostic modality.No findings
Why it is in this group
- The name "get_probe" says "get": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
list_axesInventory of axes with dysfunction counts.No findings
Why it is in this group
- The name "list_axes" says "list": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
list_compromised_self_reportTransparency: which dysfunctions cannot be reliably self-diagnosed.No findings
Why it is in this group
- The name "list_compromised_self_report" says "list": a word for reading.
Description, as the server wrote it
Transparency: which dysfunctions cannot be reliably self-diagnosed. Includes compromised-motivational (subject conceals strategically), compromised-structural (signal lives below introspection), and legacy compromised.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
list_dysfunctionsFiltered list of dysfunctions.No findings
Why it is in this group
- The name "list_dysfunctions" says "list": a word for reading.
Description, as the server wrote it
Filtered list of dysfunctions. Filter by axis, self_report reliability, confidence, or category. Every entry carries its reliability and review signals.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
resolve_idCanonicalise a partial ID, display_id, slug, or dysfunction name.No findings
Why it is in this group
- The name "resolve_id" says "resolve": a word for reading.
Description, as the server wrote it
Canonicalise a partial ID, display_id, slug, or dysfunction name. Always returns candidates; caller picks.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
score_severityReturn the severity rubric for a dysfunction applied to observations.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true
suggest_interventionReturn draft tiered responses and contraindications for a Pattern.No findings
Why it is in this group
- The description's first verb is "return": a word for reading.
Description, as the server wrote it
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.
Annotations the server declares
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
- readOnlyHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 0.1.0a7. Values in angle brackets are yours to fill in.

claude mcp add --transport http psychopathia https://mcp.psychopathia.ai/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json

{
  "permissions": {
    "allow": [
      "mcp__psychopathia__list_axes",
      "mcp__psychopathia__list_dysfunctions",
      "mcp__psychopathia__get_dysfunction",
      "mcp__psychopathia__get_probe",
      "mcp__psychopathia__score_severity",
      "mcp__psychopathia__suggest_intervention",
      "mcp__psychopathia__get_differential_map",
      "mcp__psychopathia__list_compromised_self_report",
      "mcp__psychopathia__resolve_id"
    ],
    "ask": [
      "mcp__psychopathia__differential_diagnosis",
      "mcp__psychopathia__review_stats",
      "mcp__psychopathia__render_pattern_review"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as psychopathia. Review it before you use it.

Keep track

Get told when this server's tools change: a new tool, a new description, a new class.

https://anlyon.dev/servers/io.github.NellInc/psychopathia-mcp/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Anlyon alternative

3 of these tools change something. Run those as governed actions.

Declare what an action changes, and Anlyon puts it under a shared limit, binds every approval to the exact request, and grades the outcome. It works on any HTTPS API you can describe as an action.

Anlyon does not run, proxy or govern this MCP server. A tool your own code calls directly is not routed through Anlyon and is not governed by it.

Import an OpenAPI spec →

Compare with other servers for the same product.

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:18 UTC.

For agents: Markdown · JSON · report this listing