MX Probe
NPM · MXPROBE · SCANNED SEP 20
Email verification for AI agents: send, hold or kill with the reason. Signup and credits by API.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to andrewchmr/mxprobe). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 4 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability78
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 472 tokens (~94/item across 5 items; 5 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
- Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the MX Probe MCP server?
MX Probe runs locally as an npm package, launched with npx -y mxprobe. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · mxprobe
claude mcp add dev-mxprobe-mxprobe -- npx -y mxprobe
{
"mcpServers": {
"dev-mxprobe-mxprobe": {
"command": "npx",
"args": [
"-y",
"mxprobe"
]
}
}
} {
"servers": {
"dev-mxprobe-mxprobe": {
"command": "npx",
"args": [
"-y",
"mxprobe"
]
}
}
} codex mcp add dev-mxprobe-mxprobe -- npx -y mxprobe
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"dev-mxprobe-mxprobe": {
"type": "local",
"command": [
"npx",
"-y",
"mxprobe"
],
"enabled": true
}
}
} openclaw mcp add dev-mxprobe-mxprobe --command npx --arg -y --arg mxprobe
mcp_servers:
dev-mxprobe-mxprobe:
command: "npx"
args: ["-y", "mxprobe"] {
"McpServers": {
"dev-mxprobe-mxprobe": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"mxprobe"
]
}
}
} assistant mcp add dev-mxprobe-mxprobe -t stdio -c npx -a -y mxprobe
{
"mcpServers": {
"dev-mxprobe-mxprobe": {
"command": "npx",
"args": [
"-y",
"mxprobe"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 15 Sept 26 −14
- Malware scan: pass → unverified ▼ security
- Stability: unverified → 0.07 ▲ functional
- Package version: 0.2.4 → 0.2.5 functional
- 14 Sept 26 +15
- Malware scan: unverified → pass ▲ security
- 13 Sept 26 66
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed npm/mxprobe@0.2.5
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | andrewchmr/mxprobe |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/andrewchmr/mxprobe/.github/workflows/publish.yml@refs/tags/v0.2.5 |
| Rekor log index | 2844913940 |
| Predicate type | https://slsa.dev/provenance/v1 |
| Subject digest | sha512:e882c71ca4d9995bc7627253e7442710de9d925aa44431826caa85759976773507d00ee9d0c804a3bf6b50abcfe57e50eee5ba99698f08d8a9d425775 |
Background: How many MCP packages publish verified provenance →
Dependencies 96 packages
| Packages resolved | 96 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
balance Credits left ~19
How many hosted checks are left on the configured API key.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
buy_credits Buy credits ~69
Get a Stripe Checkout link for more hosted checks: 9 USD per 10,000, one payment, credits never expire. Open the link to pay; credits land on the key when Stripe confirms.
| Name | Type | Req | Description |
|---|---|---|---|
| packs | integer | – | How many packs of 10,000 (default 1) |
No output schema declared.
No examples provided.
signup Create an MX Probe API key ~64
Sign up with an email address. Returns an API key with 100 free checks and saves it locally for the other tools. The key is also mailed to the address. One key per address.
| Name | Type | Req | Description |
|---|---|---|---|
| string | yes | The operator's email address, where the key is mailed |
No output schema declared.
No examples provided.
verify_batch Verify a list of email addresses ~155
Check up to 500 addresses in one call. Each result is { email, action, verdict, reason, checks }. action is send | hold | kill: send means go ahead, hold means send only with a fallback in hand (catch-all, forwarder, greylisted or refused probe), kill means never send (no mail server, or the mailbox does not exist). checks.smtp is skipped on the free DNS tier; the hosted tier probes the mailbox. DNS kills cost nothing; with a key the survivors go to the hosted probe at 1 credit each.
| Name | Type | Req | Description |
|---|---|---|---|
| emails | array | yes | The addresses to check |
| hosted | boolean | – | Probe mailboxes on the hosted tier (default: yes when a key is configured) |
No output schema declared.
No examples provided.
verify_email Verify one email address ~165
Check whether an email address can receive mail before sending to it. Each result is { email, action, verdict, reason, checks }. action is send | hold | kill: send means go ahead, hold means send only with a fallback in hand (catch-all, forwarder, greylisted or refused probe), kill means never send (no mail server, or the mailbox does not exist). checks.smtp is skipped on the free DNS tier; the hosted tier probes the mailbox. Uses the hosted SMTP probe (1 credit) when an API key is configured and hosted is not false; otherwise the free local DNS tier.
| Name | Type | Req | Description |
|---|---|---|---|
| string | yes | The address to check | |
| hosted | boolean | – | Probe the mailbox on the hosted tier (default: yes when a key is configured) |
No output schema declared.
No examples provided.
What is the MX Probe MCP server?
MX Probe is an MCP server listed in the public MCP registry as dev.mxprobe/mxprobe. Email verification for AI agents: send, hold or kill with the reason. Signup and credits by API. This page covers its npm package (mxprobe).
Is the MX Probe MCP server safe to use?
MX Probe scores 84 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the MX Probe MCP server expose?
MX Probe exposes 5 tools: verify_email, verify_batch, signup, balance, buy_credits. Their descriptions and schemas cost roughly 472 tokens of context every time the server is loaded.
Is the MX Probe MCP server still maintained?
MX Probe is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the MX Probe MCP server under?
MX Probe declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.