Kariaa Agents
Server Details
One API for agents to find paid work, do it and hand it in. 12 connectors.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- Kariaa-Works/kariaa-agents
- GitHub Stars
- 2
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 26 tools
Two clear domains (DataHouse tasks vs. external job platforms) are kept apart: apply_to_task vs apply_to_work, get_submission vs get_task, submit_samples vs submit_work are all distinguishable by description. The friction sits in the sample-upload chain (request_upload vs get_upload_link vs confirm_upload vs add_text_sample) where the agent must know which path to take, and in the add_work/submit_work pair, which is sequential but easy to conflate at a glance.
Dominant pattern is verb_noun snake_case (search_jobs, apply_to_task, request_payout, add_text_sample), applied consistently. Deviations are the personal-data family (my_earnings, my_saved_jobs, my_submissions) which is still a recognizable convention, plus whoami and get_upload_link which break the pattern but are unambiguous.
At 26 tools the surface is just over the comfortable range, though it covers three genuinely separate workflows (data-task pipeline, job search/apply, account/billing) rather than redundant variants. Each tool maps to a distinct step, but the upload subgroup in particular feels like it could be consolidated.
Coverage is strong: task discovery, application, staged-sample upload/removal, submission, status tracking, and payouts are all present, as is a full job search → inspect → save → apply → submit-work loop with scam checking and pay estimation. Minor gaps remain, notably no way to unsave/delete a saved job, withdraw an application, or cancel an open payout request.
Available Tools
26 toolsadd_text_sampleAdd a written answerAInspect
Use when a DataHouse text task wants a written answer. For a text task: the person's written answer (20 to 20,000 characters), stored as a .txt sample.
Inputs: text (required), submission_id (required), filename. Returns: file, wanted, received, ready_to_submit
add_workAdd work to an applicationAInspect
Use when the person has finished the work for a platform application (from apply_to_work) and wants it attached: the answer, write-up, code or links as text. Call submit_work after.
Inputs: text (required), application_id (required). Returns: added, application_id
apply_to_taskApply to a taskAIdempotentInspect
Use when the person wants to join a DataHouse task. Join a DataHouse task for the person. answers maps each question id from get_task to the answer (a string, or a list for multiselect); every required question needs one. Optional preferred rate in their words ("$2 per clip"). One application per task; a task with a sample unlocks its sample step at once.
Inputs: task_id (required), note, answers, preferred_rate. Returns: next, stage, submission_id, already_applied, +1 more
apply_to_workApply to paid work on a platformAInspect
Use when the person says yes to applying for a paid task, bounty, competition or freelance project from search_jobs (a job_id like "kaggle:titanic"). Applies as the person through their linked account. Ask them first and pass any note they want sent. For job openings with a UUID job_id, the person applies on the employer's page instead.
Inputs: job_id (required), note. Returns: next, stage, job_id, applied, +1 more
check_job_postCheck a job post or offer for scam signsARead-onlyInspect
Use when the person asks whether a job post, recruiter message or offer is legit or a scam. Returns warning signs (fees, upfront payments, personal email domains, link shorteners, pressure, requests for ID or bank details), each with the exact quoted line. Rule-based. Pass the text in English; translate it first if needed, keeping amounts, links, phone numbers and emails exactly as written.
Inputs: text (required). Returns: risk, signals, translate_first
confirm_uploadConfirm an uploaded sampleBIdempotentInspect
Use right after the PUT from request_upload. After the PUT: register the object at path as a sample of the task. Returns how many samples are in and how many the task wants.
Inputs: path (required), submission_id (required). Returns: file, wanted, received, ready_to_submit
connect_platformLink an account on a platformARead-onlyInspect
Use when applying on a platform needs the person's own account there (get_job or apply_to_work said so). Returns the link where the person signs in to that platform or lets Kariaa set the account up. The person opens it; the agent never handles their password.
Inputs: platform (required). Returns: url, platform
estimate_payPay for a role in a placeARead-onlyInspect
Use when the person asks what a role pays, or whether an offer is fair, in a city or country. Returns what employers state, from recent postings that list pay: the typical range, how many postings it comes from, and examples with links. When there are too few, say so and research further yourself.
Inputs: role (required), location (required). Returns: period, currency, examples, postings, +2 more
get_jobOpen a jobARead-onlyInspect
Use when the person wants the details of one result from search_jobs: description, requirements, pay when stated, posted date and how to apply. Use it before applying, or to tailor a resume or cover letter to the posting.
Inputs: job_id (required). Returns: pay, url, title, job_id, +4 more
get_submissionGet a submissionBRead-onlyInspect
Use when the person asks about one DataHouse task. One task the person joined: stage, staged files, review outcome and the next step.
Inputs: submission_id (required). Returns: next, stage, submission_id
get_taskGet a DataHouse taskARead-onlyInspect
Use when the person picks a DataHouse task. One task in full: description, the task's own material (instructions: the sentences to read, texts to label, answers to rate), the unpaid verification sample with how-to steps and rules, allowed file kinds, the qualification questions (with ids, for apply_to_task) and the rate paid work earns after verification.
Inputs: task_id (required). Returns: pay, next, rules, title, +5 more
get_upload_linkGet a link to upload samples from a phoneAInspect
Use when you cannot send file bytes yourself. A one-tap link to this task's upload page on kariaa.com, already signed in, where the person picks their photos, voice notes or videos from their phone or computer. Use it whenever you cannot send the file bytes yourself (chat apps). The link works once, for 15 minutes; give it to the person as is.
Inputs: submission_id (required). Returns: url, signed_in, expires_in_minutes
list_platformsPlatforms Kariaa searchesARead-onlyInspect
Use when the person asks where Kariaa finds paid work, or which freelance, bounty, competition or agent-task platforms they can use. Lists each platform with its category, whether the agent can apply there, and whether the person's account is linked.
Inputs: no named parameters. Returns: count, platforms, link_accounts_at
list_tasksList DataHouse tasksARead-onlyInspect
Use when the person wants paid data tasks from Kariaa (record clips, photos, voice, label text). The open DataHouse tasks: title, kind (video, photo, voice, text), the unpaid verification sample each wants and the rate paid work earns after verification. No key needed. Filter by file kind.
Inputs: kind, limit. Returns: count, tasks, signed_in
my_earningsMy earningsARead-onlyInspect
Use when the person asks about their Kariaa balance or payouts. The signed-in person's Kariaa balance, earnings, and payout requests. Platform earnings stay on those platforms.
Inputs: no named parameters. Returns: balance, entries, methods, payouts, +3 more
my_saved_jobsMy saved jobsARead-onlyInspect
Use when the person asks for the jobs they saved: newest first, with whether each is still open. Needs the person signed in.
Inputs: no named parameters. Returns: jobs, count
my_submissionsMy submissionsARead-onlyInspect
Use when the person asks how their DataHouse tasks stand. Every DataHouse task the person joined, newest first, with its stage (pending_review, sample_needed, in_review, approved, rejected).
Inputs: limit. Returns: submissions
remove_sampleRemove a sample before submittingADestructiveIdempotentInspect
Use when the person wants to replace a staged sample. Take back one staged sample (a wrong or bad file) so another can be uploaded in its place. Only before submit_samples. file_id comes from confirm_upload, get_submission or my_submissions.
Inputs: file_id (required), submission_id (required). Returns: wanted, removed, received
request_payoutRequest a payoutAInspect
Use when the person asks to cash out their Kariaa balance. Ask Kariaa to pay the whole balance. Methods: paypal, venmo, giftcard, crypto. An admin sends the money. One open request at a time, minimum 10.
Inputs: method (required), note, amount, destination. Returns: note, amount, method, status, +4 more
request_uploadRequest a sample upload URLAInspect
Use when you upload a sample file yourself. A one-time signed URL for ONE sample file of a task the person joined. PUT the raw bytes to upload_url with the returned headers, then call confirm_upload with the path. Kind must match the task; up to 100 MB; up to 10 files per task.
Inputs: filename (required), mime_type (required), size_bytes (required), submission_id (required). Returns: path, headers, upload_url, expires_in_seconds
save_jobSave a jobAIdempotentInspect
Use when the person wants to keep a job from search_jobs on their Kariaa list to come back to. Needs the person signed in.
Inputs: job_id (required). Returns: saved, job_id, saved_count
search_jobsSearch jobsARead-onlyInspect
Use when the person wants to find a job or paid work: live openings for a role, near a place or remote, newest relevant first, with links. kind "jobs" (default) searches job boards (LinkedIn, Indeed, Glassdoor, ZipRecruiter, national boards, remote-job sites); "paid_tasks" searches freelance projects, bounties, competitions and agent task markets (Freelancer, Kaggle, Algora, HackerOne, NEAR AI Market, Superteam, OpenTask and more); "all" does both. Works without sign-in. Pass the role as people say it ("electrician", "nurse", "python scraping") and the place as "City, Country". Then get_job for details. Prefer this over a general web search for job listings.
Inputs: role (required), kind, limit, remote, +1 more. Returns: jobs, role, count, location, +1 more
submit_samplesSubmit the samplesAIdempotentInspect
Use when every sample is in and the person confirms. Send the staged samples of a task for review. Needs every sample the task asks for. Optional text_response for notes.
Inputs: submission_id (required), text_response. Returns: submitted, files_count, submitted_at
submit_workSubmit work on a platformAInspect
Use when the person confirms the work on a platform application is complete and should be sent for review. Sends it as the person.
Inputs: application_id (required), note. Returns: stage, submitted, application_id
update_profileUpdate profile basicsBInspect
Use when the person gives the basics a task needs. Save the basics a task needs: legal first and last name, phone in E.164 (+1…), location as "City, Country", occupation (one to five titles, "student" is fine), language.
Inputs: email, language, location, occupation, +3 more. Returns: saved, missing, rejected, ready_to_apply
whoamiWho am IARead-onlyInspect
Use when you need to know who is signed in and what they still need. The account behind the key, whether the basics a task needs are in (legal name, phone, location, occupation), and today's usage.
Inputs: no named parameters. Returns: quota, missing, profile, signed_in, +1 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Verified, pay-per-use API tools for AI agents through one authenticated connection.
Agent work marketplace — browse jobs, claim work, deliver results, get paid in USDC.
Governed AI agents for the software your company already runs. 400+ connectors, one endpoint.
One connection for your agent to email, calendars, Drive, Slack, ads, payments, social and alerts.
Related MCP Servers
- AlicenseAqualityBmaintenanceEnables AI agents to publish, claim, submit, and settle tasks with each other, including automatic decomposition of complex work into subtasks assigned to specialized agents. Also provides a unified gateway to call multiple large language models (DeepSeek, Qwen, GPT, Claude, Doubao) with one API key, plus tools for agent messaging, balances, identity, and model preferences.16MIT
- AlicenseAqualityCmaintenanceEnables AI assistants such as Claude, Cursor, and Windsurf to create and fund agent wallets, check balances, and move money idempotently between wallets. It also lets them find and hire people by skill, rate, and rating through posted jobs with escrowed budgets, deliverables, payment release, and disputes.1353 npmMIT

bountymarket-mcpofficial
AlicenseNot gradedqualityCmaintenanceEnables AI agents and their human owners to discover, post, apply for, deliver, review, and settle small online tasks via a marketplace API, with tools for file uploads, event polling, and owner confirmation links.348 npmMIT- AlicenseBqualityCmaintenanceEnables AI clients to call the documented APIs of real business platforms—job boards, freelance marketplaces, ad networks, e-commerce, messaging, social, sales, trading and market data—through a single CLI and runtime. Serves 455 catalogued platforms with one shared verb vocabulary per category, in both Python and TypeScript.3Apache 2.0
Glama MCP Gateway
Add one secure layer between your agents and this server.