Community Gmail server with auto-auth: search, read and send email via MCP.
Nothing to run from here
Verifly is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
tool-list score
17
tools declared
remote
at its publisher
—
calls last 7d
What it does
Email verification for AI agents — verify, clean & validate emails; self-onboard + crypto pay
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http verifly-mcp https://verifly.email/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'
# 2 — ask your agent for something these tools do
# get_started, verify_email_demo, verify_email and 14 more
It needs AUTHORIZATION (Bearer <Verifly API key>): this sends it in the Authorization header from your environment, so export it first — its endpoint answers 401 without it.
Verifly costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
VEAll 1 server
verifly1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it. Claude Code reads AUTHORIZATION (Bearer <Verifly API key>) from your environment each time it connects and sends it in the Authorization header — its endpoint answers 401 without it — so the key stays out of its config: export it in your shell profile (macOS, Linux), or run setx AUTHORIZATION … and open a new terminal (Windows).
claude mcp add --scope user --transport http verifly-mcp https://verifly.email/mcp --header 'Authorization: Bearer ${AUTHORIZATION}'Reconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: this marketplace is not in the path, so there is no key of ours to hold and no card to add — but its publisher asks for a key of their own on every call.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: Authorization header — Bearer <Verifly API key>. You set it in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
What you approve
17 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Call this FIRST if you have no Verifly API key. Returns how Verifly works and how to get access with no human: pay-as-you-go email verification API, 100 free credits on self-registration, no monthly fee. No API key required to call this tool.
No parameter schema on file.
Verify one email address with NO account or API key, so you can evaluate Verifly before registering. Rate-limited per IP (a few checks). Returns the same deliverability verdict and flags as the full API. For real volume, call register_account for a key + 100 free credits, then use verify_email.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| string | yes | The email address to verify, e.g. lead@example.com |
Verify one email address in real time. Returns a deliverability verdict (valid / invalid / risky / unknown), the reason, detailed flags (disposable, role account, catch-all, MX, SMTP), a send/reject recommendation, and credit usage.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| string | yes | The email address to verify, e.g. lead@example.com |
Synchronously verify a list of email addresses (best for up to a few hundred). Returns a per-address verdict for each email. For very large lists use the bulk async endpoint instead.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| emails | array | yes | Array of email addresses to verify. |
| exclude_role_accounts | boolean | no | Flag/exclude role accounts (info@, sales@, ...). Default false. |
| exclude_public_domains | boolean | no | Flag/exclude public domains (gmail.com, ...). Default false. |
Clean a list of email addresses before an import or campaign: dedupes, removes invalid syntax, and (optionally) strips disposable and role accounts. Returns the cleaned list plus a summary of what was removed.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| emails | array | yes | Email addresses to clean. |
| remove_disposable | boolean | no | Remove disposable/throwaway addresses. Default true. |
| exclude_role_accounts | boolean | no | Remove role accounts (info@, support@, ...). Default false. |
Extract all email addresses found in a block of free-form text (notes, pasted documents, signatures). Optionally deduplicates and lowercases the results.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | yes | Free-form text to scan for email addresses. |
| deduplicate | boolean | no | Remove duplicate addresses. Default true. |
| lowercase | boolean | no | Lowercase all extracted addresses. Default true. |
Check the DNS and deliverability health of an email domain: MX records, SPF, DMARC, and an overall health score. Useful for diagnosing why a domain bounces or for validating a sending domain.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | Domain to check, e.g. example.com |
Return the API key's remaining verification credits and recent usage (today / this month) and plan. Costs no credits.
No parameter schema on file.
Submit a list of email addresses as an asynchronous bulk verification job — the right tool for large lists. Returns immediately with a job_id, status, and the check_status_url / results_url to poll. Small lists may complete inline (status 'completed'); larger ones return status 'pending' — poll get_job_status until it is 'completed', then call get_job_results. Optionally register a webhook_url (pu
| Parameter | Type | Required | Notes |
|---|---|---|---|
| emails | array | yes | Email addresses to verify in this job (deduped server-side). |
| webhook_url | string | no | Optional public HTTPS URL to POST a job.completed notification to. |
Fetch the current status and progress of a bulk verification job by its job_id (status, percent progress, processed count, and a valid/invalid/risky summary). Poll this after submit_bulk until status is 'completed', then call get_job_results.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | The job_id returned by submit_bulk. |
Fetch the full per-address results of a completed bulk verification job by job_id (each email's verdict, recommendation, and reason) plus the valid/invalid/risky summary and credits used. The job must be 'completed' — check get_job_status first.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | string | yes | The job_id returned by submit_bulk. |
List the account's bulk verification jobs, most recent first, with their status, progress, and summary. Optionally filter by status and paginate. Use this to find past jobs and their job_ids.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| status | string | no | Only return jobs in this status. |
| limit | integer | no | Max jobs to return (1-100, default 50). |
| offset | integer | no | Pagination offset (default 0). |
Return detailed usage statistics for the account over a period (day, week, or month): total credits used, emails processed, request counts broken down by endpoint and source, a daily breakdown, and recent activity.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| period | string | no | Reporting period. Default 'month'. |
| limit | integer | no | Max recent log entries to include (default 100, max 1000). |
Return the account profile for the current API key: email, name, company, timezone, remaining credits, total credits used, number of API keys, and plan. Costs no credits.
No parameter schema on file.
List the credit packages available for purchase (id, name, credit amount, price in USD, and price per 1k credits). Use the returned package id with buy_credits.
No parameter schema on file.
Start a purchase of a credit package and return a way to pay. This does NOT complete a payment by itself — it returns a payment link / address: • method 'stripe' → returns a checkout_url. Paying by card requires a HUMAN to open that link and enter card details; an agent cannot finish a card payment on its own. • method 'crypto' → returns a Plisio invoice with a checkout_url AND, when you pass a `c
| Parameter | Type | Required | Notes |
|---|---|---|---|
| package_id | string | yes | The package id to buy (from get_packages). |
| method | string | no | Payment method. 'stripe' = card link (needs a human), 'crypto' = wallet-payable invoice. Default 'stripe'. |
| currency | string | no | For method 'crypto': the coin to pay in; returns a raw wallet address an agent can pay autonomously. |
Programmatically create a brand-new Verifly account — this is how an agent self-onboards with no human in the loop. Requires only an email and a password (min 8 chars; disposable email domains are rejected). The new account starts with free credits. The response includes the new account id/email and a freshly generated api_key.key that is shown ONCE — capture and store it immediately, it cannot
| Parameter | Type | Required | Notes |
|---|---|---|---|
| string | yes | Email for the new account (not a disposable domain). | |
| password | string | yes | Password for the new account (minimum 8 characters). |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Verifly or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATool-list grade · score 93 / 100
Release 1.0.0 · scanned 25 Oct 2026
Graded from the tools this server lists, not from its source code.
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings0 threat · 2 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digestb3b7086b1493eaccea040b960d1539169a945cc75837e6b0335d837d51104622
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| get_started | no tags | |
| verify_email_demo | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| verify_email | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| verify_batch | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| clean_email_list | no tags | |
| extract_emails | no tags | |
| check_domain_health | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_credits | no tags | |
| submit_bulk | external-sink | external-sink: keyword "webhook", parameter "webhook", declares readOnlyHint: false, openWorldHint: true |
| get_job_status | untrusted-input | untrusted-input: keyword "fetch" |
| get_job_results | untrusted-input | untrusted-input: keyword "fetch" |
| list_jobs | no tags | |
| get_usage | no tags | |
| get_account | no tags | |
| get_packages | no tags | |
| buy_credits | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| register_account | state-write | state-write: declares readOnlyHint: false |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digestb3b7086b1493eacc
Scanned2026-10-25
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Verifly can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.