Community Gmail server with auto-auth: search, read and send email via MCP.
Nothing to run from here
NeverBounce MCP by usefulapi 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
8
tools declared
remote
at its publisher
—
calls last 7d
What it does
MCP server for NeverBounce — business email verification, credits and bulk jobs.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http neverbounce-mcp-by-usefulapi https://neverbounce.usefulapi.io/mcp
# 2 — ask your agent for something these tools do
# neverbounce_get_account_info, neverbounce_verify_email, neverbounce_list_jobs and 5 more
NeverBounce MCP by usefulapi costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
USAll 563 servers
usefulapi563 servers
25 categories
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 mcp add --scope user --transport http neverbounce-mcp-by-usefulapi https://neverbounce.usefulapi.io/mcpReconnect, 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.
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
8 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.
Credits left (paid and free), credits used, and how many verification jobs are completed, queued, processing or under review. Free: it spends no credits. POST /account/info.
No parameter schema on file.
WRITE: SPENDS 1 of your NeverBounce credits per call. Verifies ONE e-mail address and returns result (valid, invalid, disposable, catchall or unknown), flags (e.g. has_dns_mx, role_account, free_email_host), a suggested correction for typos like gmal.com, and optionally the parsed address parts. NeverBounce's usage rules: use this for a single address at the point of entry; do NOT call it in a loo
| Parameter | Type | Required | Notes |
|---|---|---|---|
| string | yes | The one e-mail address to verify. | |
| address_info | boolean | no | Also return the parsed address parts (addr, alias, host, domain, tld...). |
| timeout | integer | no | Seconds NeverBounce may spend before answering 'unknown' (1-60). Omit for the default. |
Bulk verification jobs of the account (most recent first as NeverBounce returns them) with id, status, filename, timestamps, totals per result (valid, invalid, catchall, disposable, unknown, duplicates, bad_syntax), bounce estimate and percent complete. Filter by id, exact filename or status. POST /jobs/search.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | integer | no | NeverBounce job id (from neverbounce_list_jobs or neverbounce_create_job). |
| filename | string | no | Exact filename of the job. |
| job_status | string | no | Only jobs in this status. |
| page | integer | no | Page number, from 1 (default 1). Pass the previous reply's next_page. |
| items_per_page | integer | no | Results per page, 1-100 (default 25). |
One verification job: status (waiting, parsing, running, complete, failed, under_review...), failure reason, timestamps, totals (records, billable = credits it will use, processed, valid, invalid, catchall, disposable, unknown, duplicates, bad_syntax), bounce estimate and percent complete. Poll this until status is complete. POST /jobs/status.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | integer | yes | NeverBounce job id (from neverbounce_list_jobs or neverbounce_create_job). |
Per-address results of a job: the submitted row (data) and its verification (result, flags, suggested_correction, address info). Paged; use neverbounce_download_job_results for a CSV. The job must be complete. POST /jobs/results.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | integer | yes | NeverBounce job id (from neverbounce_list_jobs or neverbounce_create_job). |
| page | integer | no | Page number, from 1 (default 1). Pass the previous reply's next_page. |
| items_per_page | integer | no | Results per page, 1-100 (default 25). |
The results of a complete job as CSV text (the submitted columns plus email_status), cut at 200000 characters with a note when longer (use neverbounce_get_job_results to page through large jobs). By default every result type is included; set a type to false to leave it out. POST /jobs/download.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | integer | yes | NeverBounce job id (from neverbounce_list_jobs or neverbounce_create_job). |
| valids | boolean | no | Include valid addresses (default true). |
| invalids | boolean | no | Include invalid addresses (default true). |
| catchalls | boolean | no | Include catch-all addresses (default true). |
| disposables | boolean | no | Include disposable addresses (default true). |
| unknowns | boolean | no | Include unknown addresses (default true). |
WRITE: creates a bulk verification job from up to 100 e-mail addresses given in this call, and has NeverBounce parse it. It does NOT start the verification and spends NO credits; run neverbounce_start_job afterwards (that spends 1 credit per billable address). Put ALL the addresses of one list into ONE job: NeverBounce's rules allow 10 concurrent jobs and 50 runs a day, and many small jobs in a sh
| Parameter | Type | Required | Notes |
|---|---|---|---|
| emails | array | yes | The e-mail addresses to verify, 1-100. |
| filename | string | no | Name shown in the NeverBounce dashboard (default: a timestamped name). |
| leverage_historical_data | boolean | no | Default true. Set false to use real-time verification only (no historical data). |
WRITE: STARTS a created job and SPENDS 1 credit per billable address (shown as total.billable in neverbounce_get_job); it cannot be stopped or undone. Safety: you must pass max_credits, and the job is refused when its billable count is above it or above 1000 (start bigger jobs in the NeverBounce dashboard). The job must be in status waiting or waiting_analyzed. With run_sample true it only runs th
| Parameter | Type | Required | Notes |
|---|---|---|---|
| job_id | integer | yes | NeverBounce job id (from neverbounce_list_jobs or neverbounce_create_job). |
| max_credits | integer | yes | The most credits you accept to spend (1-1000); the job is refused if its billable count is higher. |
| run_sample | boolean | no | Run only the free sample analysis instead of the full verification. |
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 NeverBounce MCP by usefulapi 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 1.6.1 · scanned 4 Nov 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 · 1 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digestda6c13dc7b70adecfbbcdd434ae46da0dd72becbf8adeb1a558f4db4b4041d8c
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 |
|---|---|---|
| neverbounce_get_account_info | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| neverbounce_verify_email | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
| neverbounce_list_jobs | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| neverbounce_get_job | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| neverbounce_get_job_results | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| neverbounce_download_job_results | untrusted-input | untrusted-input: keyword "download", declares openWorldHint: true (interacts with entities outside the server) |
| neverbounce_create_job | external-sink | external-sink: declares readOnlyHint: false, openWorldHint: true |
| neverbounce_start_job | external-sink | external-sink: declares readOnlyHint: false, destructiveHint: true, openWorldHint: true |
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 digestda6c13dc7b70adec
Scanned2026-11-04
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 1.6.1.
1.6.1
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 NeverBounce MCP by usefulapi 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.