memento-mcp

Memento MCP: A Knowledge Graph Memory System for LLMs

Runs with mockssource: GitHubTypeScriptMITcommit be6dc369784e

TypeScript, MIT licensed. The project labels itself: claude desktop, cursor, knowledge graph, modelcontextprotocol, neo4j and vector database.

memento-mcp runs, with stand-ins for the services it depends on. An Argusic agent installed it in 1 minute and hit 1 error and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

npm install and TypeScript build succeed; 287/287 unit tests pass with mocked Neo4j; the MCP server binary starts and accepts MCP initialization but cannot connect to Neo4j (not available in this container).

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.03 (measured)
recorded runs
1
last tested
stars
427
forks
64
open issues
21
watchers
7
size
0 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Time lost to each failure while testing memento-mcp, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • Neo4j integration tests in Neo4jIntegration.test.ts tried to connect to a real Neo4j server that doesn't exist in this container, causing 3 test failures.2 minutes
Install time
1 minutes
Cold machine to finish
6 minutes
Errors hit and fixed
1 hit, 1 fixed with no human help
How the result was proved
npm test: 287 passed, 15 skipped (3 Neo4j integration tests correctly skipped, 12 other skips by design). Built binary starts and responds to MCP initialize over stdio.
Model tokens used
224,683
Exact commit tested
be6dc369784e
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
Behaviour against real services
this run was verified against stand-in services only

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

Here's the final summary of everything I observed:
**Install**: `npm install` succeeded — 384 packages installed, `tsc` build passed, `dist/index.js` …
**Test suite**: `npm test` → **287 passed, 15 skipped** (44 test files passed, 3 skipped). All fail…
**Launch**: The binary starts as a stdio MCP server. It accepts the JSON-RPC `initialize` handshake…
**No API keys are required** — the app uses a mock embedding service by default when `OPENAI_API_KE…
tokens used
224,683
Here's the final summary of everything I observed:
**Install**: `npm install` succeeded — 384 packages installed, `tsc` build passed, `dist/index.js` …
**Test suite**: `npm test` → **287 passed, 15 skipped** (44 test files passed, 3 skipped). All fail…
**Launch**: The binary starts as a stdio MCP server. It accepts the JSON-RPC `initialize` handshake…
**No API keys are required** — the app uses a mock embedding service by default when `OPENAI_API_KE…

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Installed in 1 minute.
  • Recovered from all 1 error without a human stepping in, which says the failures are documented well enough to solve.
  • Licensed MIT, as reported by its host.

What did not, or is not known

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner1/3Runs with mocks92.000.03

Topics (from GitHub)

claude-desktopcursorknowledge-graphmodelcontextprotocolneo4jvector-database

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/memento-mcp.svg)](https://argusic.com/subject/memento-mcp)

Questions

Does memento-mcp run?
memento-mcp runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 1 error on the way, and recorded the session.
How did Argusic test memento-mcp?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit be6dc369784e. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test memento-mcp?
The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does memento-mcp take to install?
1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does memento-mcp need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing memento-mcp?
1 thing broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
Where is the evidence for memento-mcp?
The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion