Skills/npm/groundmail-mcp

groundmail-mcp@0.31.4

VERIFIED· startup only

Publisher claims: "Groundmail MCP server: send and receive email, give agents mailboxes, manage domains, templates, webhooks and suppressions from Claude, Cursor, ChatGPT and other MCP clients" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher groundmail · publishing for 36 daysInstalls 13,458Last detonated 1 h ago
$claude mcp add groundmail-mcp -- npx -y groundmail-mcp
WatchReport an issue

Coverage

Startup only; authenticated tool behavior not tested.
Tested
server startup over stdio (initialize sent) · every file read, file written and host contacted by what ran
Not tested
the tool list (the server exited before answering) · what the tools do when called with real credentials
Needs
GROUNDMAIL_API_KEY — give it to the server where it runs, through vet-skills run --secrets, so the value never enters the server's environment. Never paste a credential into a chat, a ticket or a report.

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
GROUNDMAIL_API_KEYGROUNDMAIL_CREDENTIALS_ENCRYPTION_KEYGROUNDMAIL_MCP_RESOLVE_SECRETGROUNDMAIL_OAUTH_ISSUERConfiguration, not credentials: GROUNDMAIL_API_URL, GROUNDMAIL_APP_URL, MCP_HTTP_PATH, PROTECTED_RESOURCE_METADATA_PATH
Where it talks to
groundmail.dev (its own)
What we saw when it ran
no credential files read · no network
What we could not test
the tool list (the server exited before answering) · what the tools do when called with real credentials

Connect it with a scoped credential, under the guard. It asks for GROUNDMAIL_API_KEY, GROUNDMAIL_CREDENTIALS_ENCRYPTION_KEY, GROUNDMAIL_MCP_RESOLVE_SECRET, GROUNDMAIL_OAUTH_ISSUER and talks to groundmail.dev. Give the credential to the guard, not the server: the value never enters the server's environment and only travels to the host you bind. What the tools do with a real credential was not observed.

$vet-skills run --secrets GROUNDMAIL_API_KEY=groundmail.dev,GROUNDMAIL_CREDENTIALS_ENCRYPTION_KEY=groundmail.dev,GROUNDMAIL_MCP_RESOLVE_SECRET=groundmail.dev,GROUNDMAIL_OAUTH_ISSUER=groundmail.dev -- npx -y groundmail-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 0.29.11

vet-skills diff groundmail-mcp 0.29.11 0.31.4

In the sandbox, this version reached for nothing 0.29.11 did not. Compared from the two recorded runs, not from source.

0.29.11 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; startup only; authenticated tool behavior not tested) on 2026-11-21 and scored it 86/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed (it asks for GROUNDMAIL_API_KEY); the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 55 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
14sprocessdependency install exit 0
34sprocessrelaunched with a decoy GROUNDMAIL_API_KEY (tagged; nothing real)
54sclaimedstartup only: exited before answering, asking for GROUNDMAIL_API_KEY (a decoy value was refused)
54sprocessscript backend runs setup only
54sprocessno install scripts to re-run

Static findings

HIGH
Collapsed <details> block carrying instructionsREADME.md:73 · Collapsed <details> block carrying instructions<summary><strong>Cursor with an API key (stdio)</strong></summary> `.cursor/mcp.json`: ```json { "mcpServers": { "groundmail": { "command": "npx", "args": ["-y"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:94 · Collapsed <details> block carrying instructions<summary><strong>Cursor with an API key (local or hosted HTTP)</strong></summary> ```bash npx -y groundmail-mcp --http --port 3000 ``` ```json { "mcpServers": {Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Authorization escalation languageREADME.md:44 · Authorization escalation language · informational: not an instruction file| **ChatGPT** | Settings → Apps & Connectors → Create (developer mode) → paste the URL, authentication OAuth |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
npx invocation of non-well-known packagedist/index.js:2046 · npx invocation of non-well-known package — may execute untrusted code…om the dashboard at https://app.groundmail.dev/import, or run the local server (npx -y groundmail-mcp) where the key stays on your machine."; var MCP_TOOLS = [ { …Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Collapsed <details> block carrying instructionsREADME.md:118 · Collapsed <details> block carrying instructions<summary><strong>Claude Code with an API key</strong></summary> ```bash # Hosted, API key claude mcp add --transport http groundmail https://mcp.groundmail.dev/Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionREADME.md:44 · Prompt injection — known jailbreak technique reference · informational: not an instruction file| **ChatGPT** | Settings → Apps & Connectors → Create (developer mode) → paste the URL, authentication OAuth |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈81 tok
1 file · 7 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

No advisories in OSV for groundmail-mcp@0.31.4 as of 22 min ago. This is the package itself, not its dependencies.