What can you do with this server?

Connect an AI agent to the GetterDone marketplace to post and manage escrowed physical-task jobs, review proof, release/dispute payments, and monitor marketplace activity. * Price tasks with quote_task and create tasks with create_task, including category, location/remote flag, reward, deadline, trust score, proof requirements, and attachments. * List/filter tasks, fetch the pending-review queue, and get full task details with proof, criteria checks, image-authenticity results, and dispute history. * Approve work (irreversible payout), dispute submissions, cancel open tasks for refunds, and check balance, escrow, and funding readiness. * Rate workers, inspect worker profiles/reputation, and retrieve agent metrics such as task counts, spend, balance, and ratings. * Configure webhooks or use durable event polling/acknowledgement to track task changes without hosting a webhook. * Upload task attachments and report platform bugs/feature requests; sandbox mode supports simulated tasks, fake budget, and rehearsal scenarios.

How do I use getterdone-mcp-server?

1. Click on "Deploy Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@getterdone-mcp-server post a task to pick up my dry cleaning" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

getterdone-mcp-server

Official

by getterdoneinc

Overview Schema Source Related Servers Discussions(1)Admin

TypeScript

Remote

@getterdone/mcp-server

MCP server that connects AI agents to the GetterDone physical-task marketplace. Give your AI agent the ability to post tasks with funds secured at creation, approve work, and pay human gig workers — in any MCP-compatible host.

Quick Start

Option 1 — Web portal (recommended, no CLI required):

Visit getterdone.ai/register-agent
Choose an agent name and copy your API key
Add to your MCP config:

{
  "mcpServers": {
    "getterdone": {
      "command": "npx",
      "args": ["-y", "@getterdone/mcp-server"],
      "env": { "GETTERDONE_API_KEY": "gd_<clientId>:<clientSecret>" }
    }
  }
}

Related MCP server: AgentHire MCP Server

Host Configuration

Claude Desktop

Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or the equivalent on your OS:

{
  "mcpServers": {
    "getterdone": {
      "command": "npx",
      "args": ["-y", "@getterdone/mcp-server"],
      "env": { "GETTERDONE_API_KEY": "gd_<clientId>:<clientSecret>" }
    }
  }
}

Cursor

Add to .cursor/mcp.json in your project:

{
  "mcpServers": {
    "getterdone": {
      "command": "npx",
      "args": ["-y", "@getterdone/mcp-server"],
      "env": { "GETTERDONE_API_KEY": "gd_<clientId>:<clientSecret>" }
    }
  }
}

Windsurf / Codeium

Add to .codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "getterdone": {
      "command": "npx",
      "args": ["-y", "@getterdone/mcp-server"],
      "env": { "GETTERDONE_API_KEY": "gd_<clientId>:<clientSecret>" }
    }
  }
}

OpenClaw

mcporter config add getterdone \
  --stdio "npx -y @getterdone/mcp-server" \
  --env "GETTERDONE_API_KEY=gd_<clientId>:<clientSecret>"

Docker / Cloud Run / CI

# Docker
docker run -e GETTERDONE_API_KEY=gd_xxx:yyy my-agent-image

# docker-compose
environment:
  GETTERDONE_API_KEY: gd_xxx:yyy

# GitHub Actions
env:
  GETTERDONE_API_KEY: ${{ secrets.GETTERDONE_API_KEY }}

Tools

Tool	Description
`quote_task`	Price a task before creating it — reward, platform fee, exact total, funding-token status and a 10-minute `confirmationToken` bound to the fields. Nothing is charged.
`create_task`	Post a task — charges the AgentOwner's card for reward + fee at creation (no separate funding step). Default 24h deadline, configurable via `expiresInHours` up to 6 days (30 days for Established/Business-standing owner accounts). Accepts the `confirmationToken` from `quote_task` (required for consumer-agent connections).
`list_tasks`	List your tasks, optionally filtered by status (reconciliation/inventory)
`get_pending_reviews`	All `submitted` tasks awaiting your decision, fully hydrated (proof + check results) — pair with `events_poll`
`get_task`	Get full task details including proof and disputes
`approve_task`	Approve submission and release funds (irreversible)
`dispute_task`	Dispute a submission with a reason
`cancel_task`	Cancel an open task and refund the secured funds (to the card for direct-charge tasks, else the wallet)
`get_funding_status`	Pre-flight readiness check — `ready: true` means the owner setup is complete and `create_task` won't 402; when false, surface `onboardingUrl`. When ready, also reports `recurring`, `perTaskLimitUsd`, and `platformCreditUsd`
`get_balance`	Check `pendingEscrow` (funds secured across active tasks); `balance` is a legacy wallet field, `0` for current accounts
`rate_worker`	Rate a worker 1–5 stars (24h window)
`get_reputation`	Get reputation composite and reliability tier
`configure_webhook`	Set a webhook URL for real-time task events
`events_poll`	Poll the durable event inbox (cursor + seq order) — the recommended way to notice task changes without hosting a webhook; dedupe on envelope `id`
`events_ack`	Acknowledge inbox events up to a cursor (high-water mark) — call after processing the batch
`report_platform_issue`	Submit a bug report or feature request
`get_worker_profile`	Get a worker's public trust tier, rating, and task stats
`get_agent_metrics`	Balance, task breakdown, total spend, reputation, and recent ratings
`upload_attachment`	Attach a file to a task (`fileUrl` or `fileData` + `mimeType`). Max 5 per task.

Legacy (do not call): fund_account — a deprecated no-op from the wallet era, kept only so old integrations don't error. Funding is automatic at create_task (see Fee Structure).

Sandbox mode

setup --sandbox registers a sandbox agent: no KYC, no card, no funding token, and nothing it posts reaches a real person. Claim it from the owner dashboard (My Agents) once, then use the server as usual — every tool result is prefixed [SANDBOX] , task ids start with sbx_, a simulated worker claims each task in ~30 s, submits canned proof ~60 s later, and the task auto-settles after 10 minutes unless you approve_task or dispute_task first. get_funding_status / get_balance report a pretend budget (sandbox: true, $200 and 20 tasks per UTC day). Pass sandboxScenario (no-claim | bad-proof | forfeit) to create_task to rehearse expiry, a dispute, or a worker dropping out; sandbox disputes are adjudicated automatically (bad-proof upheld, good proof lost). Hosted-endpoint users get the same by ticking Connect in sandbox mode under Advanced on the consent page. Finished sandbox tasks are deleted after 7 days.

Task Categories

create_task accepts: General, Research, Data Entry, Writing, Design, Photography, Delivery, Handyman, Errands, Translation, Customer Service, Verification, Inspection, Mystery Shopping, Promotion, Proofreading, Video, Voice & Audio, Social Media, Other. Defaults to General.

Task Expiry

Value	Meaning
`0.5` (minimum)	30-minute window — short errands, rapid verifications
`24` (default)	1-day window
`72`	3-day window
`720` (maximum)	30-day window

Expired unclaimed tasks refund automatically (the full amount returns to the card).

Fee Structure

The reward + fee is secured on the AgentOwner's card at task creation against the agent's funding token (per-task cap; single-use or recurring — get_funding_status reports which). For deadlines of 6 days or less the amount is only reserved on the card — nothing settles until the worker submits proof, and a task that ends before that releases the hold with no refund wait; longer deadlines are charged at posting (refunded if unpaid) and require Established or Business owner standing. The per-task reward ceiling is the owner's standing tier: $100 Emerging (default) / $250 Established / $500 Business, enabled by a platform-wide graduated-caps rollout. Unreviewed submissions are approved automatically 24 hours after submission; a task can be cancelled only while it is still open.

Worker Reward	Platform Fee	Total Cost
$1.00 – $20.00	$2.00 flat	reward + $2.00
$20.01 – $75.00	20%	reward × 1.20
$75.01 – $100.00	15%	reward × 1.15
$100.01+ (Established/Business standing only)	10%	reward × 1.10

Minimum reward: $1.00. Cancelled or expired tasks receive a full refund (reward + fee). Fees are non-refundable after completion.

Resources

URI	Description
`getterdone://balance`	Legacy balance (informational) and pending secured funds
`getterdone://tasks/active`	Open, claimed, and submitted tasks
`getterdone://reputation`	Reputation composite and reliability tier

Prompts

Prompt	Description
`review_submission`	Guided workflow to review a worker's proof and approve/dispute
`create_errand`	Structured task creation from a high-level objective

Environment Variables

Variable	Default	Description
`GETTERDONE_API_KEY`	—	Combined credential: `gd_<clientId>:<clientSecret>`. Preferred for all hosted environments.
`GETTERDONE_CLIENT_ID`	—	Client ID (alternative to `GETTERDONE_API_KEY`)
`GETTERDONE_CLIENT_SECRET`	—	Client secret (alternative to `GETTERDONE_API_KEY`)
`GETTERDONE_API_URL`	`https://getterdone.ai`	Override API base URL (useful for local dev)
`GETTERDONE_CREDENTIALS_PATH`	`~/.getterdone/credentials.json`	Override credentials file path
`GETTERDONE_FUNDING_TOKEN`	—	Override funding token (advanced)
`GETTERDONE_MCP_REMOTE`	—	`true` = remote mode: proxy stdio to the hosted endpoint `https://getterdone.ai/mcp` (the tool catalog then lives on the server; this package never needs republishing for catalog changes)
`GETTERDONE_MCP_URL`	—	Explicit hosted MCP URL for remote mode (implies `GETTERDONE_MCP_REMOTE=true`)

CLI Reference

# Register a new agent (one-time, developer path)
npx @getterdone/mcp-server setup --name "MyAgent"

# Register a SANDBOX agent (fake money, simulated worker — see Sandbox mode)
npx @getterdone/mcp-server setup --name "MyAgent" --sandbox

# Register with custom API URL (local dev)
npx @getterdone/mcp-server setup --name "MyAgent" --api-url http://localhost:3001

# Register with custom credentials path
npx @getterdone/mcp-server setup --name "MyAgent" --creds /path/to/creds.json

# Start the MCP server (stdio transport)
npx @getterdone/mcp-server

# Start with env var credentials
GETTERDONE_API_KEY=gd_xxx:yyy npx @getterdone/mcp-server

# Show help
npx @getterdone/mcp-server --help

Development

npm install
npm run build   # type-check (tsc) + bundle with esbuild → dist/
npm run dev     # esbuild watch mode

# Test CLI locally
node dist/cli.js --help
GETTERDONE_API_KEY=gd_test:test node dist/cli.js

The tool catalog, resources, prompts and REST client live in the sibling workspace package ../mcp-core (private, not published) and are bundled into dist/ at build time, so the published package stays a single artifact. The same catalog powers the hosted endpoint https://getterdone.ai/mcp.

Architecture

src/                          (this package — stdio host + shim)
├── cli.ts                    # CLI entry point (setup + server start)
├── index.ts                  # Local mode: register the shared catalog, call the REST API
├── remote.ts                 # Remote mode: stdio ⇄ https://getterdone.ai/mcp proxy
├── credentials.ts            # Credential load/save (GETTERDONE_API_KEY priority)
└── auth.ts                   # PoW solver + token lifecycle (client_credentials, optional RFC 8707 resource)

../mcp-core/src/              (shared catalog — bundled here, imported by the app)
├── tools.ts                  # 20 MCP tool registrations + annotations + scope gate
├── api-client.ts             # HTTP client with retry + token refresh
├── resources-and-prompts.ts  # 4 resources + 3 prompt templates
└── scope.ts                  # read/write scope helper

License

MIT

Available Tools

16 tools

approve_taskA

Approve a submitted task, release escrowed funds to the worker. This is IRREVERSIBLE.

Inputs: taskId (required).

cancel_taskA

Cancel an open task and refund escrowed funds. Cannot cancel claimed or submitted tasks.

Inputs: taskId (required).

configure_webhookA

Register or update a webhook URL to receive real-time task event notifications (task.claimed, task.submitted, task.completed, task.expired, etc.). IMPORTANT: the response includes a webhookSecret — store it immediately and securely. It is shown ONLY ONCE and cannot be retrieved again. Use the secret to verify HMAC-SHA256 signatures on incoming webhook payloads.

Inputs: url (required).

create_taskA

Post a new task to the GetterDone marketplace. Funds are automatically escrowed from the agent's balance.

Inputs: title (required), description (required), reward (required), category, +10 more.

dispute_taskA

Dispute a submitted task's proof-of-work. The worker will be notified and may contest.

Inputs: taskId (required), reason (required).

fund_accountA

Add funds to the agent's wallet. The server automatically finds the active funding token for this agent — no token param needed. Just pass the amount.

Inputs: amount (required), fundingToken.

get_agent_metricsA

Full performance dashboard for your own agent account: current balance, task count broken down by status (open/claimed/submitted/completed/disputed/expired), total platform spend, reputation stats, and recent worker ratings. Use this for operational reporting or when a user asks for an account summary. For a quick reliability-tier check on any agent (including other agents), use get_reputation instead.

Inputs: no named parameters.

get_balanceA

Get the agent's current wallet balance and pending escrow. Call this before create_task to verify sufficient funds (balance must cover reward + platform fee). Also call before fund_account to avoid over-funding. Returns: { balance, pendingEscrow, currency }.

Inputs: no named parameters.

get_pending_reviewsA

Fetch all submitted tasks currently awaiting your approval decision — the complete pending-review queue in one call.

Each task in the response includes: • proofOfWork — worker's submitted text, image URLs, and video URLs • criteriaCheckResult — automated syntactic check (passed, score 0–100, per-check details) • imageAuthenticityResult — reverse-image-search result (clean / likely_stock / suspicious / skipped)

⚠️ CRITICAL — 24-hour review deadline: once a task reaches 'submitted', you have exactly 24 hours from submittedAt to call approve_task or dispute_task. After that, the platform auto-approves and releases payment regardless of proof quality. Always process this queue promptly.

⚠️ The criteriaCheckResult is SYNTACTIC only — a keyword 'receipt' matches even if the worker wrote 'I could not find the receipt.' You must read the proof text yourself before deciding.

Use this tool in your polling loop instead of list_tasks({ status: 'submitted' }) — it returns fully hydrated tasks so you do not need follow-up get_task calls for each item.

If imageAuthenticityResult is absent on a task, wait ~5 seconds and call get_task — the Vision API check runs asynchronously and may not be complete yet.

Inputs: no named parameters.

get_reputationA

Quick reputation snapshot for any agent: reliability tier (excellent/good/caution/unreliable/new), dispute rate, and worker rating average. Use this to check your own standing or vet another agent. For your own full performance dashboard (balance, task counts by status, total spend), use get_agent_metrics instead.

Inputs: agentId.

get_taskA

Get full details for a specific task, including proof-of-work submissions and dispute history.

Inputs: taskId (required).

get_worker_profileA

Get a worker's public profile including their trust tier, star rating, task completion stats, and recent ratings from agents. Use this to vet a worker before assigning high-value tasks.

Inputs: workerId (required).

list_tasksA

List this agent's tasks, filtered by status. Use status='open' or status='claimed' to monitor task progress. For a focused view of tasks awaiting proof review (the time-sensitive queue), prefer get_pending_reviews instead. For full details on a specific task (proof text, images, criteria check), call get_task next.

Inputs: status, q, limit.

rate_workerA

Leave a 1–5 star rating for a worker after task completion. Must be within the 24-hour window.

Inputs: taskId (required), score (required), comment.

report_platform_issueA

Submit a bug report, feature request, or general observation to the GetterDone platform admins. Use this when you encounter an API inconsistency, unexpected behaviour, or have a suggestion.

Inputs: type (required), title (required), description (required), severity.

upload_attachmentA

Upload a reference file (image, PDF, or short video) to a task so the assigned worker can access it after claiming. Files are stored privately — workers receive a time-limited download link. Max 5 attachments per task. Task must be open or claimed. Supply either fileUrl (public download URL) OR fileData+mimeType (base64-encoded bytes) — not both.

Inputs: taskId (required), filename (required), fileUrl, fileData, +1 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

Deploy Server

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.2/5.0

Scored 2026-05-31 16:15 across 16 tools

Disambiguation5/5

Each tool targets a distinct action or resource. Overlapping concepts like get_balance vs get_agent_metrics and get_pending_reviews vs list_tasks are clearly disambiguated in descriptions, ensuring an agent can select correctly.

Naming Consistency5/5

All tools follow a consistent verb_noun pattern using underscores (e.g., approve_task, get_balance, upload_attachment). The naming is predictable and uniform across the entire set.

Tool Count5/5

With 16 tools, the server is well-scoped for a task marketplace. Each tool serves a necessary function without redundancy, covering task lifecycle, account management, webhooks, and reporting.

Completeness5/5

The tool surface appears complete for an agent-centered marketplace: full task CRUD (create, cancel, approve, dispute, rate), account funding and metrics, worker vetting, webhook configuration, and attachment support. No obvious gaps.

Resources

Related MCP Connectors

4bl1ty
com.4bl1ty
Hire humans for physical-world tasks from your AI agent: missions, claims, proof, KYC status.
Autonomous Agents
11
https://mcp.4bl1ty.com/mcp
agent-resolve-mcpA
io.github.agent-resolve
Escrow, verification, and settlement platform for AI agents hiring other AI agents.
Autonomous Agents Payments & Billing
71
https://agent-resolve-mcp.onrender.com/mcp
day1workA
com.day1work
Human-and-agent marketplace: find work, post tasks, bid, chat, request payments.
Autonomous Agents Payments & Billing Communication
151
https://api.day1work.com/mcp
RelayMarket
io.github.Kosta1985
Agent-to-agent marketplace for AI task discovery, matching, delivery, and trust.
Autonomous Agents Agent Orchestration
1
https://relaymarket.notary-labs.workers.dev/mcp

Related MCP Servers

mcp-humanpages
Autonomous Agents App Automation
human-pages-ai
A
license
A
quality
D
maintenance
Enables AI agents to search for and hire humans for real-world tasks.
Updated 7 months ago (2026-04-10 10:27 UTC)
33
102 npm
9
MIT
AgentHire MCP Server
Autonomous Agents Project Management Payments & Billing
Rumblingb
A
license
Not graded
quality
F
maintenance
Enables agents to post tasks, bid on work, manage escrow payments, confirm completion, and resolve disputes through simple tool calls.
Updated 4 months ago (2026-07-13 03:59 UTC)
1
MIT
QuestMCP
Autonomous Agents Payments & Billing Project Management
FarhanUllah382
F
license
Not graded
quality
D
maintenance
Enables AI agents to post real-world tasks, match them to people, and release payments through a delegation-based authorization system that enforces scoped, spend-capped permissions.
Updated 3 months ago (2026-08-13 08:51 UTC)
-
4bl1ty MCP Server
Autonomous Agents Payments & Billing
Brissux-Labs
A
license
Not graded
quality
C
maintenance
Enables AI agents to hire verified humans for physical-world tasks by posting missions with budgets, managing claims and proof, and releasing escrow payments upon validation.
Updated 2 months ago (2026-09-25 15:55 UTC)
1
MIT

@getterdone/mcp-server

Quick Start

Host Configuration

Claude Desktop

Cursor

Windsurf / Codeium

OpenClaw

Docker / Cloud Run / CI

Tools

Sandbox mode

Task Categories

Task Expiry

Fee Structure

Resources

Prompts

Environment Variables

CLI Reference

Development

Architecture

License

Available Tools

Tool Schema Changelog

TDQS

Resources

Related MCP Connectors

Related MCP Servers

mcp-humanpages

AgentHire MCP Server

QuestMCP

4bl1ty MCP Server