A local, persistent knowledge store for an agent's understanding of a project. It represents that understanding as a revisable graph, where related pieces of information can be connected.

Use it to store, update, and retrieve connected project knowledge through the understanding-graph MCP server. It requires two environment variables to run.

It lets an agent keep project understanding between runs instead of rebuilding it from scratch each time.

ug — MCP server by emergent-wisdom/understanding-graph

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/emergent-wisdom/understanding-graph

Made for: Claude Code.

Or install understanding-graph, the plugin that ships this one along with the rest of its 10 skills, 2 MCP servers.

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.

README.md

[![agentmods](https://agentmods.dev/badge/mcp/emergent-wisdom/understanding-graph/ug/github.svg)](https://agentmods.dev/mcp/emergent-wisdom/understanding-graph/ug)

Your own site

<a href="https://agentmods.dev/mcp/emergent-wisdom/understanding-graph/ug"><img src="https://agentmods.dev/badge/mcp/emergent-wisdom/understanding-graph/ug/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.

Your own site · 80×15

<a href="https://agentmods.dev/mcp/emergent-wisdom/understanding-graph/ug"><img src="https://agentmods.dev/badge/mcp/emergent-wisdom/understanding-graph/ug.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

Socket warn 15 Oct 2026

How audits are shown

Origin original No closer match found in the catalogue.

Security

Grade A, and why

ug 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 6d 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.

.mcp.json · 14 lines

What it actually says

{
  "ug": {
    "command": "npx",
    "args": [
      "-y",
      "[email protected]",
      "mcp"
    ],
    "env": {
      "PROJECT_DIR": "./projects",
      "UG_SOURCE_ROOT": "."
    }
  }
}

Changes

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.

6d ago Changed 49f3581ecf8c
1mo ago First seen · 14 lines scan A 7cfe07d52c25

Subscribe to this mod's changes

ug is an MCP server published in the GitHub repository emergent-wisdom/understanding-graph (1 stars, last pushed 6d 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.

LLM Memory and context agent ai claude knowledge-graph mcp

plexus

Typed on-prem knowledge graph for AI agents — read-only for humans, write-only for agents via MCP. Remote server at {plexus_host}.

pcas-io/plexus · not measured

telemem

Long-term & multimodal memory for AI agents — character isolation, video pipeline, MCP server, mem0-compatible. Runs locally from the telemem Python package. Needs 3 environment variables to run.

TeleAI-UAGI/telemem · not measured

ori-memory

Persistent memory infrastructure for AI agents. Identity, knowledge graph, and search. Runs locally from the ori-memory npm package.

aayoawoyemi/Ori-Mnemos · not measured

codebase-memory-mcp

MCP server "codebase-memory-mcp" as configured in suyoumo/ClawProBench. Launched with codebase-memory-mcp.

suyoumo/ClawProBench · not measured

keymem

Associative memory for LLM agents — a key-graph memory layer (MCP server) that recalls by association, not just vector similarity. A graph-based alternative to vector-store agent memory. Runs locally from the keymem npm package. Needs 3 environment variables to run.

donggyun112/keymem · not measured

akb

Git-backed org memory for AI agents — hybrid search, tables, files & a URI graph over MCP. Runs locally from the akb-mcp npm package. Needs 2 environment variables to run.

dnotitia/akb · not measured