MCP.Market

Manoma MCP server

by paperdavid·io.github.paperdavid/manoma·v0.2.1
No reviews yet

MCP server for soul.md — your portable AI identity layer across every LLM.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

0 stars65 downloads/wk

Reviews

Write one

Nobody has reviewed Manoma yet.

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

Manoma tools (7, 1 write)

write = sends, deletes, buys or posts

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

  • add_decision

    Record a decision in /memory/decisions. Appends a timestamped entry to the decisions section of soul.md. This is how the AI helps maintain soul.md as a living document — capturing decisions as they happen during conversation. Args: - decision (string): The decision to record. Be specific about what was chosen and why. - context (string, optional): Additional reasoning or alternatives considered. R

  • add_lesson

    Record a lesson learned in /memory/lessons. Appends a timestamped entry to the lessons section. Captures insights and hard-won knowledge from debugging, incidents, code reviews, reading, or any learning moment. Args: - lesson (string): The lesson to record. Be specific and actionable. - source (string, optional): Where this lesson came from. Returns: Confirmation with the recorded entry.

  • get_context

    Retrieve the user's identity context for the current or specified mode. Returns all soul.md sections that should be injected for the given mode, as defined by mode_routing in /config. This is the primary way an LLM should bootstrap context about the user. Args: - mode (string, optional): One of work, personal, creative, learning. Defaults to the active_mode in soul.md config. Returns: Combined mar

  • get_injection

    Build a smart context injection from soul.md for an LLM system prompt. Unlike get_context which returns raw sections, this runs the full injection algorithm: three-tier priority (always/by_mode/on_trigger), keyword matching for skill domains, person detection, voice dial conversion to behavioral instructions, and token budgeting (2500 max with priority-aware truncation). Use this when assembling t

  • get_skill_depth

    Retrieve detailed skill information for a specific domain. Searches soul.md skill sections for a matching domain and returns the full detail block including level, years, approach, heuristics, and taste. Args: - skill (string): Skill domain name to look up. Returns: Detailed skill section content if found, or a list of available skills with a suggestion to check skills.summary.

  • list_sections

    List all available sections in soul.md. Returns a tree-like listing of all sections with their paths, names, metadata, and child sections. Useful for discovering what's in the soul.

  • update_nowwrite action

    Replace the /now section with current focus and status. The /now section captures what the user is currently working on, thinking about, and prioritizing. This tool replaces it entirely with new content. Args: - content (string): New markdown content for the /now section. Should describe current projects, focus areas, blockers, and priorities. Returns: Confirmation with the new content.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan9 source files scanned25/25
  • –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 15 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Manoma compares

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

Safety score
92/100
higher than 90% of 4,460 AI and agents servers
Tools
7
the typical AI and agents server has 6
Tools that change things
14%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
65
more than 52% of 1,538 AI and agents servers with a package

What its tools let an agent do: 4 read · 2 create · 1 change

Install Manoma in Claude Code, Cursor or VS Code

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

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

What the publisher says

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

soul.md

Your identity, not theirs. One plain-text file that tells every AI who you are — and that you own.

soul.md is an open format for your AI identity: values, voice, skills, current focus. It lives on your machine, versions in git, and gets compiled into the tools you use. Manoma is the CLI and MCP server that make it work.

npx manoma init        # create your soul.md
npx manoma interview   # let an AI you already use write it with you
npx manoma compile     # wire it into Claude Code — every session knows you

Two more commands close the loop with your AI's own memory:

npx manoma refresh     # the AI that's been learning about you proposes updates
                       # to your file — your approval required, never silent
npx manoma remember    # save your soul.md INTO the AI's memory, so even plain
                       # chats with zero setup know you

Their memory collects; your file is the owned, current copy.

  • User-owned — a file on your machine. No cloud, no account, no vendor.
  • Works everywhere — compiled into tool configs, pasted into instruction fields, readable by anything.
  • Stays alive — add the MCP server and the AI records decisions and lessons into the file as you work, dated and signed; every change is a git diff.

The format

The specification is one page and public domain (CC0): eight plain-markdown sections, a deterministic grammar, and one invariant — a soul.md must stay useful pasted raw into any prompt. Every file written for the older v1.4 format keeps working (migration guide).

The conformance corpus defines correct parsing; a reader that reproduces its expected outputs is conformant. Parallel implementations are welcome — a Python or Rust parser that passes the corpus is a first-class citizen.

The MCP server

{
  "mcpServers": {
    "manoma": { "command": "npx", "args": ["-y", "manoma-mcp"] }
  }
}

One block in Claude Desktop, Cursor, or any MCP client. Six tools: getcontext, getskilldepth, listsections, and the write-back trio adddecision / addlesson / update_now — provenance-stamped, sanitized, disclosed. Details in mcp/README.md.

Repo

manoma/
├── mcp/          — the MCP server + manoma CLI (npm: manoma-mcp, manoma)
├── cli/          — the `manoma` npm name (forwards to manoma-mcp)
├── conformance/  — the normative parsing corpus
├── docs/         — migration guide, archived v1.4 spec
├── templates/    — v1.4-era example files (valid, being modernized)
├── SPEC.md       — the format specification (CC0)
└── LICENSE       — MIT (code)

Philosophy

Every AI vendor keeps its own memory of you, in its own cloud. soul.md is the opposite bet: your identity as a plain file you control, portable between tools, diff-able in git, built to outlive any individual model.

The schema is the thing. The runtime is just how it's read.

Feedback, forks, and parallel implementations welcome — issues. MIT / CC0.

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

Manoma: common questions

Is Manoma MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the Manoma safety report
How do I install Manoma?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Manoma need an API key?
No secret keys are declared. It reads 1 setting from the environment.
Is Manoma maintained?
The last commit was 53 days ago (2026-09-12). The latest release is v0.2.1.
What can I use instead of Manoma?
Servers from other publishers that do the same job: agent-device MCP server, LLM Sandbox MCP server and Agent Recall MCP server.
How does Manoma compare with other AI and agents MCP servers?
safety score 92/100 (higher than 90% of 4,460 AI and agents servers); tools 7 (the typical AI and agents server has 6); tools that change things 14% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Manoma

Same job from other publishers: the closest match first, then the best rated.

  • agent-device
    Open source device layer for AI agents: control mobile, web, TV, and desktop apps over MCP
    A
  • LLM Sandbox
    Securely run LLM-generated code in isolated containers across 7 languages and 3 container backends.
    A
  • Agent Recall
    Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.
    A
  • Agent Lsp
    Orchestrates language servers into 65 code-intelligence tools across 32 languages, token-optimized.
    A
  • Grandet
    Cheapest API for any model across official, inference and relay providers; find free credits
    A