MCP.Market

KMP MCP server

by underpass-ai·io.github.underpass-ai/kmp·v0.24.0

Local-first agent memory that preserves what happened, when and why

A90/100grade A
What users say
No reviews yet
Be the first
Safety scan
A90/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed KMP yet.

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

KMP tools

No tool declarations could be read from the package source. They show once the server is installed.

Public scan report

scanner v0.1.10 · 2026-10-03 · same rubric, same numbers if you re-run it

no findings
  • –Code scanpackage could not be scannedn/a
  • –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 2 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year9/10
Overall 90/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How KMP compares

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

Safety score
90/100
higher than 85% of 4,460 AI and agents servers

Release history: 6 versions in the registry since 2026-09-15, latest 2026-09-27, typically one every 2 days.

Install KMP in Claude Code, Cursor or VS Code

The registry entry has no remote endpoint or installable package.

What the publisher says

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

KMP — Agent memory that remembers why

Local first. Evidence attached. Time included.

<!-- kmp:public-overview:begin --> KMP gives Codex and Claude Code local-first memory that preserves what happened, when and why. It stores decisions and evidence, not transcripts, on embedded SQLite, and exposes them through fourteen memory tools, three semantic view tools over a shared ChronoLoom view and a progressive agent guide.

Ask “Show me the memory behind this decision.” The agent retrieves the evidence, opens ChronoLoom at the relevant moment and lights up the proof path. ChronoLoom names who is guiding, shows why the agent moved, and lets you take control without losing the frame or its undo. A shared time window crosses real 3D about layers; a flat camera shows the same memory, with labels as filters. <!-- kmp:public-overview:end -->

Why KMP?

Agents are good at doing the work in front of them. Tomorrow is harder. A decision survives, its rationale disappears, and somebody gets to rediscover the same incident from scratch.

KMP gives the agent a typed, temporal memory instead of a bag of text:

  • evidence decides what can be claimed;
  • relations carry the reason two memories belong together;
  • time travel is explicit, cursor-based and auditable;
  • old decisions are superseded, never quietly rewritten;
  • UNKNOWN is an honest answer when the evidence is not there.

The normal path runs entirely on your machine. No KMP account. No hosted memory server. No Underpass cloud.

Install and initialize your memory

Codex CLI

codex plugin marketplace add underpass-ai/kmp --ref marketplace
codex plugin add kmp@underpass

Then ask Codex to run kmp-setup and restart Codex once.

Claude Code

/plugin marketplace add underpass-ai/kmp@marketplace
/plugin install kmp@underpass
/kmp:setup

Restart Claude Code once. Verify either host with its kmp-doctor workflow, or from a terminal:

kmp-mcp info
kmp-mcp doctor

Then ask Codex to run kmp-guide, or run /kmp:guide in Claude Code. This loads the installed agent and human guides into the selected store. Setup installs assets without writing memory; a fresh store can return GUIDE_UNAVAILABLE until the explicit guide sync runs.

The plugin owns the MCP registration, so do not add a second KMP server by hand. Store selection and repair live in Embedded KMP.

Talk to it like a human

You normally ask for the outcome. The KMP skill chooses the memory moves.

Shortened. The full README is on GitHub.

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

KMP: common questions

Is KMP MCP server safe?
Yes, by our scan: it is graded A (90/100). Read the KMP safety report
Does KMP need an API key?
No secret keys are declared. It reads 6 settings from the environment.
Is KMP maintained?
The last commit was 34 days ago (2026-10-01). The latest release is v0.24.0.
What can I use instead of KMP?
Servers from other publishers that do the same job: Basic Memory MCP server, Agent Recall MCP server and HOL Guard MCP server.

Alternatives to KMP

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

  • Basic Memory
    Local-first knowledge management with bi-directional LLM sync via Markdown files.
    B
  • Agent Recall
    Correction-first agent memory. Precision KPI tracks if agents heed warnings. 5 layers, local-only.
    A
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • Agent-Native Chat
    Minimal chat-first app with durable threads, actions, and the app-agent loop
    A
  • IWE (iwe.md)
    Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
    A