Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add KumihoIO/kumiho-plugins/plugin install kumiho-memoryInstalling this writes the configuration, not the program: `python` runs a file from the repository, so clone it first and make the path in the command match where you put it.
Wrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/kumihoio/kumiho-plugins/kumiho-memory)<a href="https://agentmods.dev/mcp/kumihoio/kumiho-plugins/kumiho-memory"><img src="https://agentmods.dev/badge/mcp/kumihoio/kumiho-plugins/kumiho-memory/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/kumihoio/kumiho-plugins/kumiho-memory"><img src="https://agentmods.dev/badge/mcp/kumihoio/kumiho-plugins/kumiho-memory.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
kumiho-memory scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"kumiho-memory": {
"command": "${CLAUDE_PLUGIN_DATA}/venv/bin/python",
"args": [
"-I",
"${CLAUDE_PLUGIN_ROOT}/scripts/run_kumiho_mcp.py"
],
"env": {
"KUMIHO_CLAUDE_HOST": "claude",
"KUMIHO_AUTH_TOKEN": "${KUMIHO_AUTH_TOKEN}",
"KUMIHO_CONTROL_PLANE_URL": "${KUMIHO_CONTROL_PLANE_URL:-https://control.kumiho.cloud}",
"KUMIHO_CLAUDE_DISCOVERY_USER_AGENT": "${KUMIHO_CLAUDE_DISCOVERY_USER_AGENT}",
"KUMIHO_MCP_LOG_LEVEL": "${KUMIHO_MCP_LOG_LEVEL:-INFO}",
"KUMIHO_CLAUDE_PACKAGE_SPEC": "${KUMIHO_CLAUDE_PACKAGE_SPEC:-kumiho[mcp]>=0.12.2 kumiho-memory[all]>=1.5.0}",
"KUMIHO_CLAUDE_DISABLE_LLM_FALLBACK": "${KUMIHO_CLAUDE_DISABLE_LLM_FALLBACK:-}",
"KUMIHO_CLAUDE_MODE": "${KUMIHO_CLAUDE_MODE:-}",
"KUMIHO_CLAUDE_SERVER_ENDPOINT": "${KUMIHO_CLAUDE_SERVER_ENDPOINT:-}",
"KUMIHO_MEMORY_CODE": "${KUMIHO_MEMORY_CODE:-1}",
"KUMIHO_WORKING_MEMORY_TTL": "${KUMIHO_WORKING_MEMORY_TTL:-}",
"KUMIHO_AUTO_ASSESS": "1",
"KUMIHO_REFLEX": "${KUMIHO_REFLEX:-1}",
"KUMIHO_REFLEX_PREFETCH": "${KUMIHO_REFLEX_PREFETCH:-1}",
"KUMIHO_REFLEX_LIMIT": "${KUMIHO_REFLEX_LIMIT:-5}",
"KUMIHO_REFLEX_MIN_INTERVAL_S": "${KUMIHO_REFLEX_MIN_INTERVAL_S:-45}",
"KUMIHO_REFLEX_MAX_CHARS": "${KUMIHO_REFLEX_MAX_CHARS:-1600}",
"KUMIHO_REFLEX_INSIGHTS": "${KUMIHO_REFLEX_INSIGHTS:-0}",
"KUMIHO_REFLEX_LEARNED_SOURCES": "${KUMIHO_REFLEX_LEARNED_SOURCES:-0}",
"KUMIHO_REFLEX_INSIGHT_MAX_CHARS": "${KUMIHO_REFLEX_INSIGHT_MAX_CHARS:-5120}",
"KUMIHO_REFLEX_TTL_S": "${KUMIHO_REFLEX_TTL_S:-900}",
"KUMIHO_REFLEX_FLOOR": "${KUMIHO_REFLEX_FLOOR:-3}",
"KUMIHO_REFLEX_CONSOLIDATE_FLOOR": "${KUMIHO_REFLEX_CONSOLIDATE_FLOOR:-20}",
"KUMIHO_REFLEX_SESSION_BUDGET_CHARS": "${KUMIHO_REFLEX_SESSION_BUDGET_CHARS:-6000}",
"KUMIHO_ARTIFACT_MAX_BYTES": "${KUMIHO_ARTIFACT_MAX_BYTES:-33554432}",
"KUMIHO_REFLEX_STORE_PROMPT": "${KUMIHO_REFLEX_STORE_PROMPT:-1}"
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago Changed · +3 lines 433bbbd8edf1
- 1mo ago Changed · +4 lines b900279f2866
- 1mo ago First seen · 30 lines scan A 8adfff131aad
kumiho-memory is an MCP server published in the GitHub repository KumihoIO/kumiho-plugins (3 stars, last pushed 14d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
hypermnesia-mcp
Scientifically-grounded memory system based on computational neuroscience research. Runs locally from the hypermnesia-mcp Python package.
data-olympus
Governance-grade knowledge-base format (OKF-compatible) plus CLI and single-writer MCP server. Runs locally from the data-olympus Python package. Needs 3 environment variables to run.
fidelis-memory
Fidelis Memory: faithful agent memory with zero-LLM retrieval by default. By Hermes Labs. Runs locally from the fidelis-memory Python package. Needs 1 environment variable to run.
rag-rat
CLI and MCP entrypoint for indexing repositories into local source, graph, history, and memory evidence. Runs locally from the @rag-rat/bin npm package.
chronicle-mcp
Local MCP server to sync, clean, and index AI chat logs locally. Saves up to 40% context tokens. Runs locally from the chronicle-mcp-server Python package.
cgr-capture
MCP server that captures agent judgments and outcomes as CGR substrate on GRAFOMEM Cloud. Runs locally from the grafomem-cgr Python package. Needs 6 environment variables to run.