Name: RapidWorkers
Author: rapidworkers

RapidWorkers MCP

Hire real people for AI data collection (photos, audio, video), app testing and microtasks.

Grade A Remote or local · Streamable HTTP · stdio Remote: OAuth sign-in · Package: API key 22 tools v0.1.0 MIT

No reviews yet by rapidworkersnpm Runs on your machine or at its publisher’s address — not through us

99/100

trust score

tools declared

local

or remote

—

downloads a day

What it does

Hire real people for AI data collection (photos, audio, video), app testing and microtasks.

Quickstart

# 1 — add it to Claude Code
claude mcp add --scope user --env 'RAPIDWORKERS_API_KEY=${RAPIDWORKERS_API_KEY}' --transport stdio rapidworkers-mcp '--' npx -y rapidworkers-mcp

# 2 — ask your agent for something these tools do
#   get_account, get_platform_info, list_transactions and 19 more

It needs RAPIDWORKERS_API_KEY: this reads it from your environment, so export it first. Remote: OAuth sign-in · Package: API key.

RapidWorkers costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.

Publishernot claimed

rapidworkers1 server

1 category

All 1 server

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. This one can run either way — at an address its publisher runs, or as a process under your own user, with your files and your network — and this marketplace is in the path of neither.

Claude Codedeclared by this listing

This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads RAPIDWORKERS_API_KEY (API key from https://www.rapidworkers.io/dashboard/api-management/) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx RAPIDWORKERS_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.

claude mcp add --scope user --env 'RAPIDWORKERS_API_KEY=${RAPIDWORKERS_API_KEY}' --transport stdio rapidworkers-mcp '--' npx -y rapidworkers-mcp

Reconnect, or start a new session, and the tools appear in the model’s tool list.

Or connect to its publisher’s address

Its publisher also runs it at https://www.rapidworkers.io/api/mcp/: nothing to start on your machine, and this marketplace is not in the path.

claude mcp add --scope user --transport http rapidworkers-mcp https://www.rapidworkers.io/api/mcp/

Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.

What it asks of you

It reaches a system of yours, so it needs your own credential rather than the publisher’s: RAPIDWORKERS_API_KEY — API key from https://www.rapidworkers.io/dashboard/api-management/. You set it in your own client’s config, on your machine — this marketplace never holds it.

What it writes

One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.

What you approve

22 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.

Only tools that write or reach the network

Read from its source code. A server that builds its tool list when it starts can list more tools than this.

Returns the account balance (USD), whether the account has made a deposit (required before posting jobs), AI task access status and the commission rate added to job costs.

Takes no parameters.

Returns platform rules (minimum pay $0.05 per task, $0.10 for AI tasks, $0.50 per survey response, at least 10 workers per job, $20 minimum deposit, commission and fees), job categories with sub-category codes, the prefilled job types with the link each one expects, AI task types, the survey…

Parameter	Type	Required	Notes
section	string	no	Return only one part: limits (pay, quantity, deposit, fees), categories (with sub-category codes), prefilled_job_types, ai_task_types, survey_builder (question types, scale presets, attention check te

Returns the 20 most recent balance transactions (deposits, job charges, refunds).

Takes no parameters.

Creates a hosted checkout page and returns its URL for the account owner to open and pay. It does not charge anything by itself. Minimum $20. method "card" (Stripe; a 4% processing fee is deducted from the credited amount) or "crypto". The balance is credited only after payment completes; check…

Parameter	Type	Required	Notes
amount	number	yes	Amount in USD to deposit, at least 20.00, at most 2 decimals.
method	string	no	"card" (Stripe checkout; a 4% processing fee is deducted from the credited amount) or "crypto" (crypto invoice).

Calculates the exact charge for a job, survey or AI task before creating it: pay rate x quantity + commission (+ $10 if a regular job is pinned), whether the balance covers it, and a quote_id valid for 10 minutes. Every create tool requires this quote_id, so call this first with the kind you will…

Parameter	Type	Required	Notes
kind	string	no	"job" (default) for regular and prefilled jobs, "survey" for surveys made with create_survey, "ai_task" for AI data-collection tasks.
pay_rate	number	yes	USD paid to each worker, at most 2 decimals. At least 0.05 (0.10 for AI tasks, 0.50 for surveys).
quantity	integer	yes	Number of workers (one submission each). At least 10; AI tasks and surveys at most 20,000.
pin	boolean	no	Regular jobs only: pin the job to the top of the job list for $10. Default false.

Posts a custom job that real workers complete and prove with a screenshot or text. Charges pay_rate x quantity + commission from the balance immediately. Requires quote_id from preview_job_cost, confirm=true after the user approved the total, and an idempotency_key (a new unique string; reuse it…

Parameter	Type	Required	Notes
title	string	yes	Short title workers see in the job list (up to 200 characters).
description	string	yes	Step-by-step instructions for the worker: what to do, where, and any rules. Plain text: put each step on its own line starting with "1.", "2." (or "-" for bullets); workers see them as a list and web
proof_required	string	yes	What the worker must submit as proof, e.g. "Screenshot of your comment showing your username".
category	string	yes	Category name from get_platform_info, e.g. "Social Media".
sub_category	string	yes	Sub-category code from get_platform_info within that category, e.g. "2301".
pay_rate	number	yes	USD paid to each worker, at most 2 decimals. At least 0.05 (0.10 for AI tasks, 0.50 for surveys).
quantity	integer	yes	Number of workers (one submission each). At least 10; AI tasks and surveys at most 20,000.
length_in_minutes	integer	yes	Honest estimate of the minutes one worker needs to finish the task.
countries	array	no	ISO 3166-1 alpha-2 codes of the countries workers must be in, e.g. ["US", "GB"], or ["All"] for every country. get_platform_info lists the allowed codes.
excluded_countries	array	no	Only with countries ["All"] (or omitted): country codes to leave out.
pin	boolean	no	Pin the job to the top of the job list for $10 (must match the quote). Default false.
approve_once_full	boolean	no	true approves and pays every submission automatically once all slots are filled, without review. Default false: review them with list_submissions (unreviewed ones are approved after 2 days).
image_prompt	string	no	Optional, recommended when a picture would help workers. Describe ONE image we generate with AI (no extra cost) and show workers next to the instructions; it appears a minute or two after creation. We
quote_id	string	yes	quote_id from preview_job_cost for exactly this kind, pay rate, quantity and pin. Valid for 10 minutes.
confirm	boolean	yes	Must be true, and only after the user explicitly approved this action and its cost.
idempotency_key	string	yes	A new unique string for this action (e.g. a UUID; letters, digits, _ . : - only, up to 128). Send the same key again only to retry a call that timed out or could not reach the API, so it is never done

Posts a ready-made job from a link, e.g. Instagram followers or YouTube likes; get_platform_info lists the types and the link each expects. Charges pay_rate x quantity + commission. Requires quote_id from preview_job_cost (kind "job"), confirm=true and an idempotency_key. pay_rate >= 0.05 (default…

Parameter	Type	Required	Notes
type	string	yes	Prefilled job type. get_platform_info (section prefilled_job_types) shows the link each type expects.
link	string	yes	Full URL of the post, profile or page, on the platform the type is for.
quantity	integer	yes	Number of workers (one submission each). At least 10; AI tasks and surveys at most 20,000.
pay_rate	number	no	USD paid to each worker, at least 0.05 (default 0.05), at most 2 decimals.
countries	array	no	ISO 3166-1 alpha-2 codes of the countries workers must be in, e.g. ["US", "GB"], or ["All"] for every country. get_platform_info lists the allowed codes.
excluded_countries	array	no	Only with countries ["All"] (or omitted): country codes to leave out.
approve_once_full	boolean	no	true approves and pays every submission automatically once all slots are filled, without review. Default false: review them with list_submissions (unreviewed ones are approved after 2 days).
image_prompt	string	no	Optional, recommended when a picture would help workers. Describe ONE image we generate with AI (no extra cost) and show workers next to the instructions; it appears a minute or two after creation. We
quote_id	string	yes	quote_id from preview_job_cost for exactly this kind, pay rate, quantity and pin. Valid for 10 minutes.
confirm	boolean	yes	Must be true, and only after the user explicitly approved this action and its cost.
idempotency_key	string	yes	A new unique string for this action (e.g. a UUID; letters, digits, _ . : - only, up to 128). Send the same key again only to retry a call that timed out or could not reach the API, so it is never done

Posts a survey that real workers answer on RapidWorkers, built from your questions (choice, dropdown, rating with stars, agree scales or NPS, matrix, ranking, text, number, date, consent, text blocks and attention checks), and charges pay_rate x quantity + commission. No extra access is needed.…

Parameter	Type	Required	Notes
title	string	yes	Short title workers see in the survey list (up to 200 characters).
description	string	yes	Intro workers read before they start: what the survey is about and anything they should know. Plain text (up to 5,000 characters), each paragraph on its own line. Say nothing about which answers scree
questions	array	yes	The survey items in order: 1 to 60, at most 50 that take an answer. Their keys are q_1, q_2, ... by position (text blocks count); show_if refers to them. Example: [{"type":"single_choice","label":"Do
pay_rate	number	yes	USD paid for each completed response, at least 0.50, at most 2 decimals. Workers see the effective hourly pay (pay_rate x 60 / minutes).
quantity	integer	yes	Number of responses wanted (one per worker), 10 to 20,000.
length_in_minutes	integer	no	Optional: honest minutes one response takes. Leave out for our estimate from the questions (about 8 seconds per closed question, 30 per short text and 60 per long text answer).
countries	array	yes	ISO 3166-1 alpha-2 codes of the countries workers must be in, e.g. ["US", "GB"], or ["All"] for every country. get_platform_info lists the allowed codes. Required for surveys.
excluded_countries	array	no	Only with countries ["All"] (or omitted): country codes to leave out.
audience	object	no	Optional: who may answer, on top of countries. Leave out for everyone. Only workers with a completed profile match a filter, so every filter shrinks the pool: set only what the user asked for.
block_paste	boolean	no	true stops workers pasting into text answers, so they must type them. Default false; pasted answers are flagged either way.
image_prompt	string	no	Optional, recommended when a picture would help workers. Describe ONE image we generate with AI (no extra cost) and show workers next to the instructions; it appears a minute or two after creation. We
quote_id	string	yes	quote_id from preview_job_cost for exactly this kind, pay rate, quantity and pin. Valid for 10 minutes.
confirm	boolean	yes	Must be true, and only after the user explicitly approved this action and its cost.
idempotency_key	string	yes	A new unique string for this action (e.g. a UUID; letters, digits, _ . : - only, up to 128). Send the same key again only to retry a call that timed out or could not reach the API, so it is never done

Posts an AI data-collection task (image, video, audio or text collection, or a custom form) and charges pay_rate x quantity + commission. Requires approved AI task access (see request_ai_task_access), quote_id from preview_job_cost with kind "ai_task", confirm=true and an idempotency_key. pay_rate…

Parameter	Type	Required	Notes
task_type	string	yes	image_collection, video_collection or audio_collection (workers upload files), text_collection (written answers) or custom_data_collection (a form you define in submission_fields). For a questionnaire
title	string	yes	Short title workers see in the job list (up to 200 characters).
description	string	yes	What the data is for and what to capture, in plain words workers understand.
submission_instructions	string	yes	Exact rules each submission must meet (count, framing, length, quality); used to review the work.
required_file_count	integer	no	Files each worker uploads (1 to 200). Required for image, video and audio collection; ignored otherwise.
capture_mode	string	no	Audio and video only: "upload" files, "record" in the browser, or "both" (default).
submission_fields	array	no	custom_data_collection only: the form workers fill in, in order. Fields get keys field_1, field_2, ... by position.
pay_rate	number	yes	USD paid to each worker, at least 0.10, at most 2 decimals.
quantity	integer	yes	Number of workers (one submission each). At least 10; AI tasks and surveys at most 20,000.
length_in_minutes	integer	yes	Honest estimate of the minutes one worker needs to finish the task.
reservation_minutes	integer	no	Optional: minutes a worker holds a slot while working (1 to 4320). Leave out for the default.
countries	array	yes	ISO 3166-1 alpha-2 codes of the countries workers must be in, e.g. ["US", "GB"], or ["All"] for every country. get_platform_info lists the allowed codes. Required for AI tasks.
excluded_countries	array	no	Only with countries ["All"] (or omitted): country codes to leave out.
image_prompt	string	no	Optional, recommended when a picture would help workers. Describe ONE image we generate with AI (no extra cost) and show workers next to the instructions; it appears a minute or two after creation. We
quote_id	string	yes	quote_id from preview_job_cost for exactly this kind, pay rate, quantity and pin. Valid for 10 minutes.
confirm	boolean	yes	Must be true, and only after the user explicitly approved this action and its cost.
idempotency_key	string	yes	A new unique string for this action (e.g. a UUID; letters, digits, _ . : - only, up to 128). Send the same key again only to retry a call that timed out or could not reach the API, so it is never done

Sends a request to enable AI data-collection tasks for this account, or returns the current status. An admin reviews requests; until approved, create_ai_task fails.

Parameter	Type	Required	Notes
note	string	no	Optional: what data you plan to collect, so the team can approve faster.

Lists the account's jobs with status (Pending, Active, Completed, Canceled, Rejected), progress and pending submission counts, newest first. Set kind to "survey" for surveys made with create_survey or "ai_task" for AI data-collection tasks; the default "job" covers regular and prefilled jobs.

Parameter	Type	Required	Notes
kind	string	no	"job" (default) for regular and prefilled jobs, "survey" for surveys made with create_survey, "ai_task" for AI data-collection tasks.
status	string	no	Only jobs with this status.
search	string	no	Regular jobs only: text to find in the title or description.
page	integer	no	Page number, starting at 1.
page_size	integer	no	Items per page, 1 to 100 (default 20).

Returns one job, survey or AI task by id with its brief, pay, targeting and progress; for a survey also its questions (keys q_1, q_2, ... with option ids), audience, response counts and quality bands. Set kind to "survey" for surveys made with create_survey or "ai_task" for AI data-collection…

Parameter	Type	Required	Notes
job_id	string	yes	Id of the job, survey or AI task (job_id from list_jobs or from the create tool).
kind	string	no	"job" (default) for regular and prefilled jobs, "survey" for surveys made with create_survey, "ai_task" for AI data-collection tasks.

Adds worker slots to a job and charges pay_rate x additional_quantity + commission. Regular jobs can only be extended once completed; surveys and AI tasks can have at most 20,000 slots in total. Requires confirm=true and an idempotency_key. Set kind to "survey" for surveys made with create_survey…

Parameter	Type	Required	Notes
job_id	string	yes	Id of the job, survey or AI task (job_id from list_jobs or from the create tool).
kind	string	no	"job" (default) for regular and prefilled jobs, "survey" for surveys made with create_survey, "ai_task" for AI data-collection tasks.
additional_quantity	integer	yes	Worker slots to add; the cost is pay_rate x additional_quantity + commission. AI tasks and surveys can have at most 20,000 slots in total.
confirm	boolean	yes	Must be true, and only after the user explicitly approved this action and its cost.
idempotency_key	string	yes	A new unique string for this action (e.g. a UUID; letters, digits, _ . : - only, up to 128). Send the same key again only to retry a call that timed out or could not reach the API, so it is never done

Cancels a job and refunds the unspent budget to the balance. Pending (not yet live) jobs are refunded in full; live jobs pay a $0.20 fee and cannot be canceled while submissions await review. Requires confirm=true. Set kind to "survey" for surveys made with create_survey or "ai_task" for AI…

Parameter	Type	Required	Notes
job_id	string	yes	Id of the job, survey or AI task (job_id from list_jobs or from the create tool).
kind	string	no	"job" (default) for regular and prefilled jobs, "survey" for surveys made with create_survey, "ai_task" for AI data-collection tasks.
confirm	boolean	yes	Must be true, and only after the user explicitly approved this action and its cost.
idempotency_key	string	no	Optional. A new unique string for this action (e.g. a UUID; letters, digits, _ . : - only, up to 128). Send the same key again only to retry a call that timed out or could not reach the API, so it is

Lists submissions for a job, newest first, filtered by status (Pending, Approved, Rejected). Each has the proof text, proof image links and the worker's approval rate. For kind "survey" each response has its answers (question key, label and the answer as text), a quality score (0-100), a quality…

Parameter	Type	Required	Notes
job_id	string	yes	Id of the job, survey or AI task (job_id from list_jobs or from the create tool).
kind	string	no	"job" (default) for regular and prefilled jobs, "survey" for surveys made with create_survey, "ai_task" for AI data-collection tasks.
status	string	no	Only submissions with this status, e.g. "Pending" to review.
quality_band	string	no	Surveys only: only responses in this quality band, e.g. "likely_bad" to check the weakest first.
page	integer	no	Page number, starting at 1.
page_size	integer	no	Items per page, 1 to 100 (default 25).

Returns the aggregated results of a survey (job_id from create_survey or list_jobs with kind "survey"): the response funnel (started, screened out, submitted, pending, approved, rejected), median time and effective hourly pay, quality bands, and per question the answer counts and percentages,…

Parameter	Type	Required	Notes
job_id	string	yes	Id of the survey (job_id from create_survey, or list_jobs with kind "survey").
include	string	no	Which responses count: "valid" (default) pending and approved ones, "approved" only approved ones, "all" also the rejected ones. Screened-out workers never count.
text_samples	integer	no	Latest written answers to show per text question and "Other" box (0 to 50, default 10), each cut to 500 characters. list_submissions has every answer in full.

Approves a submission and pays the worker from the job budget; this cannot be undone. Optional tip $0.01 to $50.00 from the balance, paid to the worker in full. Requires an idempotency_key. Set kind to "survey" for surveys made with create_survey or "ai_task" for AI data-collection tasks; the…

Parameter	Type	Required	Notes
job_id	string	yes	Id of the job, survey or AI task (job_id from list_jobs or from the create tool).
kind	string	no	"job" (default) for regular and prefilled jobs, "survey" for surveys made with create_survey, "ai_task" for AI data-collection tasks.
submission_id	integer	yes	submission_id from list_submissions.
tip	number	no	Optional tip in USD (0.01 to 50.00) paid from the balance to the worker in full.
notes	string	no	Optional note the worker sees.
idempotency_key	string	yes	A new unique string for this action (e.g. a UUID; letters, digits, _ . : - only, up to 128). Send the same key again only to retry a call that timed out or could not reach the API, so it is never done

Rejects a Pending submission; the worker is not paid and sees the reason. Never reject an Approved submission: it has already been paid, and rejecting it does not take the payment back. reason is required and should say exactly what was missing. Requires an idempotency_key. Set kind to "survey"…

Parameter	Type	Required	Notes
job_id	string	yes	Id of the job, survey or AI task (job_id from list_jobs or from the create tool).
kind	string	no	"job" (default) for regular and prefilled jobs, "survey" for surveys made with create_survey, "ai_task" for AI data-collection tasks.
submission_id	integer	yes	submission_id from list_submissions.
reason	string	yes	Shown to the worker: exactly what was missing or wrong compared with the instructions.
idempotency_key	string	yes	A new unique string for this action (e.g. a UUID; letters, digits, _ . : - only, up to 128). Send the same key again only to retry a call that timed out or could not reach the API, so it is never done

Approves every Pending submission on the job and pays the workers; this cannot be undone. For a survey, only_quality_band "good" approves only the Pending responses in the good quality band and leaves the rest for review. Requires confirm=true and an idempotency_key. Set kind to "survey" for…

Parameter	Type	Required	Notes
job_id	string	yes	Id of the job, survey or AI task (job_id from list_jobs or from the create tool).
kind	string	no	"job" (default) for regular and prefilled jobs, "survey" for surveys made with create_survey, "ai_task" for AI data-collection tasks.
only_quality_band	string	no	Surveys only: "good" approves only the Pending responses in the good quality band; the ones to check or likely bad stay Pending for review.
confirm	boolean	yes	Must be true, and only after the user explicitly approved this action and its cost.
idempotency_key	string	yes	A new unique string for this action (e.g. a UUID; letters, digits, _ . : - only, up to 128). Send the same key again only to retry a call that timed out or could not reach the API, so it is never done

Blocks a worker (worker_id from list_submissions of a regular job or a survey) from all of the account's jobs and rejects their pending submissions.

Parameter	Type	Required	Notes
worker_id	integer	yes	worker_id of a submission on a regular job or a survey (from list_submissions).

Removes a worker from the block list.

Parameter	Type	Required	Notes
worker_id	integer	yes	worker_id from list_blocked_workers.

Lists the workers this account has blocked.

Takes no parameters.

Free

$0 forever

Every tool, no call limit
No card, and mcprush charges nothing for it
Source published under MIT
Runs on your machine — nothing of it reaches our gateway
Nothing to cap, because mcprush bills nothing

Nothing here is billable: mcprush charges nothing to install RapidWorkers or to call it, at any volume.

ATrust score 99 / 100

Release 0.1.0 · scanned 11 Nov 2026

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 score99

Findings0 threat · 0 capability

Capabilityminimal

Coveragesource

Verificationrepo

Surface digestf9be28559f74d1222af99dd1d1e54525abf417ca07912600c31057a56cb9a766

Score vectorthreat 100 → client 99

Term	Level	What it prices	Points
capability-exposure	minimal	capability blast radius (minimal) — client exposure if the model is manipulated	−0
verification-discount	repo	publisher verification (public source) — no provenance, but the source is public and inspectable	−1
coverage-honesty	source	inspection depth (source) — how much of the target the scan could see	−0

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.

Tool surfacenot available

Implementation sourceread

Package metadataread

Live transportnot available

No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".

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. minimal is the level these add up to.

Tool	Capability tags	Why the tag was assigned
No per-tool rows for this release — see the note below.

No tool surface was enumerated, so there is nothing to attribute a capability to.

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.

The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.

Supply chain and provenance

Integrityfirst-seen

Surface digestf9be28559f74d122

Scanned2026-11-11

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.

RapidWorkers MCP

What it does

Quickstart

Where are you running it?

Tool surface

What counts against your monthly calls

What the scan could actually read

Capability — what it could do if the model were manipulated

Toxic-flow graph

Supply chain and provenance

Release history

See also