The Dump MCP Server

the-dump-mcp npm v1.2.0

Published by george-labs-ai — no publish provenance, so origin is unverified, but the source is public: the repository link below is self-declared yet readable, so you can inspect the code before adopting it.

MCP server for saving LLM conversations to The Dump and reading your notes back as context

View on npm ↗ Repository ↗ Raw report (JSON) ↗

Trust grade

95/100

Last scanned 2026-09-07 get badge →

Trust

A · 95/100

Adoption risk for you: the threat score, then adjusted down for blast radius, publisher verification and how much the scan could see. Deterministic; every point is auditable.

Capability

Moderate

Blast radius if it went rogue — what the server’s tools could reach. Independent of trust.

Coverage

Source

How much the scan could actually inspect. Shallow coverage is stated, never hidden.

A Why this grade threat 99 − adoption risk = 95/100

The grade answers one question — how safe is this server for you to adopt — so it is computed in two auditable stages. Nothing below is an opinion or an LLM's guess; every line is a real term the deterministic engine applied, and the same input always yields the same number.

1. Threat score — 100 − 1.2 = 99. What the published surface and source actually contain:

Points	What was found	Category
−1.2	Hardcoded Google API key in server code MTC-SRC-008	exfiltration

2. Client adoption risk — 99 − 4 = 95. Three small, subtract-only factors that reflect your risk in adopting it — a clean scan proves less on a powerful, unverified or barely-inspectable package, so the grade says so plainly:

Points	Adoption-risk factor
−3	capability blast radius (moderate) — client exposure if the model is manipulated
−1	publisher verification (public source) — no provenance, but the source is public and inspectable

Capability observations and info notes are shown under Findings but never scored. Open any row's finding below for the file, line and evidence behind a deduction.

Findings 1

low Hardcoded Google API key in server code (dist/index.js)MTC-SRC-008

A hardcoded Google API key (a public Firebase/web API key) appears in `dist/index.js:9`. Verify whether this is a real credential; if so, remove and rotate it.

Evidence: Google API key: AIza…(redacted)

Fix: Remove the secret, rotate it, and load credentials from the environment or a secret store.

Location: server dist/index.js

Tools 15

Each tool and what it can reach — statically extracted from the published source.

get_notesingests untrusted inputreads sensitive data
conversation_link_and_titlereads sensitive data
get_routine_documentreads sensitive data
loginreads sensitive data
logoutreads sensitive data
send_initial_promptreads sensitive data
share_conversationreads sensitive data
share_responsereads sensitive data
share_selectionreads sensitive data
signupreads sensitive data

Show 5 more tools ↓

summarize_conversationreads sensitive data
list_asksno sensitive capability
list_categoriesno sensitive capability
list_notesno sensitive capability
list_routinesno sensitive capability

What this scan could not see

Tools were statically extracted from the published source (15 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".

Versions 2

Scan history per published version. The engine is deterministic — the same version always yields the same score, so a changed score means the package itself changed.

Version	Score	Findings	Engine	Scanned
`v1.2.0` latest	A 95/100	1	1.13.0	2026-09-07
`v1.1.0`	A 95/100	1	1.12.1	2026-08-23

Embed this score

Show this server's live Trust Score in your README, docs or website. The badge is served straight from the registry and updates automatically after every rescan — no API key needed. It links back to this page, so anyone who sees the grade can also read the findings behind it instead of taking a number on faith.

Markdown (GitHub README)

[![MCP Trust Score](https://mcptrustchecker.com/registry/the-dump-mcp/badge.svg)](https://mcptrustchecker.com/registry/the-dump-mcp)

HTML

<a href="https://mcptrustchecker.com/registry/the-dump-mcp"><img src="https://mcptrustchecker.com/registry/the-dump-mcp/badge.svg" alt="MCP Trust Score" height="20"></a>

Prefer shields.io styling? Point it at https://mcptrustchecker.com/registry/the-dump-mcp/badge.json via https://img.shields.io/endpoint?url=…

Verify this score yourself

The score above is reproducible: the same package version always yields the same result. Run it locally or over the free API — no account, no LLM, fully deterministic.

npx mcptrustchecker scan the-dump-mcp --online

Use the free API → How scoring works

More in API Development

Adapters Source verified npm

@frontmcp/adapters

Adapters for the FrontMCP framework

API Development Score 100/100 2 findings 1.2k/wk Cap. Minimal

Admin Source verified npm

@transcend-io/mcp-server-admin

Transcend MCP Server — Admin tools.

API Development Score 100/100 0 findings 3.9k/wk Cap. Minimal

Assessment Source verified npm

@transcend-io/mcp-server-assessment

Transcend MCP Server — Assessments tools.

API Development Score 100/100 0 findings 4.0k/wk Cap. Minimal

Bling Source verified npm

mcp-bling

MCP Server for Bling

API Development Score 100/100 0 findings 14/wk Cap. Minimal

Blogger Source verified npm

@dalcontak/blogger-mcp-server

MCP Server for Blogger API

API Development Score 100/100 0 findings 19/wk Cap. Minimal

Brilliant Directories Source verified npm

brilliant-directories-mcp

Official MCP server for Brilliant Directories — manage members, posts, leads, reviews, and more.

API Development Score 100/100 0 findings 3.0k/wk Cap. Minimal