# Kariaa Muse connector

From musedirectory.ai, the independent directory of Meta Muse connectors. Not affiliated with Meta.

## Kariaa

Find remote jobs and gig work worldwide, check posts for scams, see typical pay, and apply to tasks.

- Record: https://musedirectory.ai/connector/kariaa
- Category: Shopping & Commerce
- Developer: Kariaa (https://www.kariaa.com/datahouse/mcp)
- Muse status: Extra setup. Not in Muse's Connectors list yet. Muse can still use it: its page gives you a request to paste into Muse.
- Health: Working, 289ms, checked 2026-10-29T09:46:47Z
- Endpoint: https://agent.kariaa.com/mcp
- Auth: No account needed; Pricing: unknown
- Screening: Screened, no issues found (2026-10-29T09:46:47Z)
- Source: Found in the official MCP Registry (com.kariaa/mcp) https://registry.modelcontextprotocol.io/v0/servers?search=com.kariaa%2Fmcp

Connects to Kariaa's DataHouse platform for remote micro-tasks (video, photo, voice, text work) and job boards (LinkedIn, Indeed, Glassdoor, ZipRecruiter). Muse can search jobs by role and location, estimate pay ranges, flag scam warnings in job posts, and help you apply to tasks with verification samples.

Example request: "Find remote data labeling jobs paying at least $15 per hour and check if that job posting looks legitimate."

How to connect: Not in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use Kariaa to help me. It is a free service with an MCP server at https://agent.kariaa.com/mcp. It does not need an API key. Ask me before you share anything with it." Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.

Tools:
- list_tasks: 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.
- get_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 pa
- whoami: The account behind the key, whether the basics a task needs are in (legal name, phone, location, occupation), and today's usage.
- update_profile: 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.
- apply_to_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 unloc
- request_upload: 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.
- confirm_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.
- remove_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.
- get_upload_link: 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 t
- add_text_sample: For a text task: the person's written answer (20 to 20,000 characters), stored as a .txt sample.
- submit_samples: Send the staged samples of a task for review. Needs every sample the task asks for. Optional text_response for notes.
- my_submissions: Every DataHouse task the person joined, newest first, with its stage (pending_review, sample_needed, in_review, approved, rejected).
- get_submission: One task the person joined: stage, staged files, review outcome and the next step.
- search_jobs: Live job openings for a role, near a place or remote, from job boards (LinkedIn, Indeed, Glassdoor, ZipRecruiter, national boards) and remote-job sites, newest relevant first, with links to apply on the employer's page. Works without a key. Pass the role as people say it ("electr
- get_job: One job from search_jobs in full: description, requirements, pay when stated, posted date and the link to apply. Use it to tailor a resume or cover letter to the posting.
- check_job_post: Warning signs in a job post, recruiter message or offer (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 amoun
- estimate_pay: What employers state for a role in a city or country, 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.
- save_job: Keep a job from search_jobs on the person's Kariaa list to come back to. Needs a Kariaa API key.
- my_saved_jobs: The jobs the person saved, newest first, with whether each is still open. Needs a Kariaa API key.

Screening checks:
- MCP handshake: pass (Answered in 289ms)
- Domain against threat feeds (Cloudflare security DNS): pass (agent.kariaa.com, www.kariaa.com not flagged)
- Published packages against the OSV malicious-package database: n/a (No npm or PyPI package published)
- Hidden instructions or invisible characters in tool text: pass (19 tools read, nothing found)
- Inputs asking for passwords, card numbers or seed phrases: pass (None found)
- Domain and redirects: pass (Domain registered 124 days ago)
- AI review of purpose and tool behavior: pass (No concerns)