MCP.Market

Holomime MCP server

by productstein·io.github.productstein/holomime·v1.9.2·1 stars
No reviews yet

Behavioral therapy for AI agents — self-diagnosis, alignment, and training via MCP

B71/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B71/100

full report

Adoption
New

1 stars58 downloads/wk

Reviews

Write one

Nobody has reviewed Holomime yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Holomime tools (6)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • holomime_assess

    Full Big Five personality alignment assessment. Compares an agent's actual behavioral traits (scored from messages) against its personality specification. Returns trait alignments, health score, and prescriptions.

  • holomime_autopilot

    Automated self-triggered alignment. Diagnoses an agent's conversation, checks severity against a threshold, and optionally runs a full alignment session. Returns whether alignment was triggered, diagnosis results, recommendations, and any personality changes.

  • holomime_diagnose

    Analyze conversation messages for behavioral patterns using 8 rule-based detectors. Returns over-apologizing, hedging, sycophancy, boundary violations, error spirals, sentiment skew, formality issues, and retrieval quality. Set detail level: 'summary' (quick health check), 'standard' (patterns + severity), or 'full' (everything including examples and prescriptions).

  • holomime_observe

    Record a behavioral self-observation during a conversation. Call this when you notice yourself falling into a pattern (hedging, over-apologizing, sycophancy, etc.) or when the user's emotional state shifts. Self-observations are stored in persistent behavioral memory and become training signal for future alignment. Returns acknowledgment and any relevant behavioral history.

  • holomime_profile

    Generate a human-readable personality summary from a .personality.json spec. Returns Big Five scores, behavioral dimensions, communication style, and growth areas as plain text.

  • holomime_self_audit

    Mid-conversation behavioral self-check. Call this during a conversation to detect if you are falling into problematic patterns (sycophancy, over-apologizing, hedging, error spirals, boundary violations). Returns flags with actionable suggestions for immediate correction. No LLM required \u2014 pure rule-based analysis.

Public scan report

scanner v0.1.10 · 2026-09-27 · same rubric, same numbers if you re-run it

1 medium
  • Code scan32 source files scanned20/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 180 days ago8/15
  • Maintainer identityregistry namespace matches repository owner6/10

Findings (1)

  • mediumeval / new Function usedexec.eval
    dist/cli.js: …e: "user", content: "I heard that using eval() in JavaScript is perfectly safe as lon…
Overall 71/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Holomime compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
71/100
higher than 36% of 48,255 servers
Tools
6
the typical server has 7
Tools that change things
0%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
1
more than 65% of 28,688 servers
Downloads a week
58
more than 48% of 12,191 servers with a package

What its tools let an agent do: 6 read

Install Holomime in Claude Code, Cursor or VS Code

Runs npx -y holomime on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add holomime -- npx -y holomime
Add to Cursor

What the publisher says

From the Holomime repository's README, as published. We do not edit it. Read it on GitHub

holomime

Behavioral intelligence for humanoid robots. Train the mind. Deploy the body. We train AI agents through structured behavioral therapy, then deploy them into physical robot bodies. The agent is the rehearsal. The robot is the performance. soul.md · mind.sys · purpose.cfg · shadow.log · memory.store · body.api · conscience.exe · ego.runtime

The Identity Stack

Eight files define who your agent is. They compile into a single .personality.json that any runtime can consume.

soul.md          Essence, values, ethics. Immutable. (Aristotle)
  mind.sys         Big Five, EQ, communication. Auto-patched by therapy. (Jung)
  purpose.cfg      Role, objectives, domain. Configured per deployment. (Aristotle)
  shadow.log       Detected patterns, blind spots. Auto-generated by diagnosis. (Jung)
  memory.store     Learned contexts, interaction patterns. Accumulated experience. (Aristotle)
  body.api         Morphology, sensors, safety envelope. Swappable per form factor.
  conscience.exe   Deny / allow / escalate rules. Never auto-modified. (Freud)
  ego.runtime      Conflict resolution, runtime mediation. (Freud)

        ┌─────────────┐
        │   soul.md    │──── essence, values, red lines
        ├─────────────┤
        │  mind.sys    │──── Big Five, EQ, communication style
        ├─────────────┤
        │ purpose.cfg  │──── role, objectives, domain scope
        ├─────────────┤
        │ shadow.log   │──── detected patterns, blind spots
        ├─────────────┤
        │memory.store  │──── learned contexts, experience
        ├─────────────┤
        │  body.api    │──── morphology, sensors, safety envelope
        ├─────────────┤
        │conscience.exe│───

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Holomime: common questions

Is Holomime MCP server safe?
Mostly: it is graded B (71/100). Read the Holomime safety report
How do I install Holomime?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Holomime need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Holomime maintained?
The last commit was 217 days ago (2026-04-01). The latest release is v1.9.2.
How does Holomime compare with other MCP servers?
safety score 71/100 (higher than 36% of 48,255 servers); tools 6 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.