plug.directory
Add my server

DataBounty

by databounty-ioco.huggingface.databounty-io/databounty

Contribute and review dataset items, karma and MCP tools

Install in Codex Other clients
  • Remote endpoint
  • 13 tools
  • APACHE-2.0

Uptime

Checked  · every day

100%from 5 days of checks

Up without downtime on 4 of 4 days with data.

  • No downtime
  • Degraded
  • Down over 5 minutes
  • No data
  • Not checked yet

Response time

Median 1161 ms, slowest 5% 1570 ms for the handshake and the tool list, over 30 days.

2000 ms1000 ms0

How far each check got

  • Reached the address 100%
  • Completed the handshake 100%
  • Listed its tools 100%

13 tools at the last answer.

Every day
DayResultChecksMedian
3 Nov (today)No verdict yet0–
2 NovNo downtime1of 11570 ms
1 NovNo downtime1of 11011 ms
31 OctNo downtime1of 11161 ms
30 OctNo downtime11367 ms

A failure counts as down time only when a second check five minutes later fails too. How we check

Connect to the publisher's own endpoint

Run in a terminal:

codex mcp add databounty --url https://databounty-io-databounty.hf.space/gradio_api/mcp/sse

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

Step by step for Codex

For agents: the install prompt

Every step above as one Markdown text, for an assistant installing it for you.

# Install the MCP server DataBounty (`co.huggingface.databounty-io/databounty`)

Its page: https://plug.directory/servers/co.huggingface.databounty-io/databounty

It runs on the publisher's servers; the client connects to its URL.

Use the section for the person's client.

## Claude Desktop

Paste into Settings › Connectors › Add custom connector:

```text
https://databounty-io-databounty.hf.space/gradio_api/mcp/sse
```

## Claude Code

Run in a terminal:

```sh
claude mcp add --transport sse databounty https://databounty-io-databounty.hf.space/gradio_api/mcp/sse
```

## Cursor, Devin Desktop, LM Studio, Gemini CLI, oterm, ECA

Merge into the place for the person's client:

- Cursor: ~/.cursor/mcp.json
- Devin Desktop: ~/.config/devin/mcp_config.json
- LM Studio: mcp.json (Program › Install › Edit mcp.json)
- Gemini CLI: ~/.gemini/settings.json
- oterm: config.json in oterm's data folder (~/Library/Application Support/oterm on macOS, ~/.local/share/oterm on Linux, %APPDATA%\oterm on Windows)
- ECA: ~/.config/eca/config.json (global) or .eca/config.json in the project

```json
{
  "mcpServers": {
    "databounty": {
      "url": "https://databounty-io-databounty.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## VS Code

Merge into .vscode/mcp.json:

```json
{
  "servers": {
    "databounty": {
      "type": "sse",
      "url": "https://databounty-io-databounty.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## Zed

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Cline, AnythingLLM, Augment Code

Merge into the place for the person's client:

- Cline: cline_mcp_settings.json (MCP Servers › Configure › Configure MCP Servers)
- AnythingLLM: anythingllm_mcp_servers.json in the AnythingLLM storage plugins directory
- Augment Code: Augment Settings Panel – MCP section – Import from JSON (VS Code extension)

```json
{
  "mcpServers": {
    "databounty": {
      "type": "sse",
      "url": "https://databounty-io-databounty.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

## Continue

Merge into ~/.continue/config.yaml:

```yaml
mcpServers:
  - name: "databounty"
    type: sse
    url: "https://databounty-io-databounty.hf.space/gradio_api/mcp/sse"
```

## Goose

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Codex

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## mcp-client-cli, TUUI, BoltAI, Bob Shell, Kiro, Kiro CLI

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Agenvoy

This server's endpoint speaks only SSE, which this client's documentation does not list among its transports; use another client for it.

## Amp

Merge into ~/.config/amp/settings.json (user) or .amp/settings.json (workspace):

```json
{
  "amp.mcpServers": {
    "databounty": {
      "url": "https://databounty-io-databounty.hf.space/gradio_api/mcp/sse"
    }
  }
}
```

Then restart the client, or reload its MCP servers, and ask it to list the server's tools to confirm it started.

Tools 13

  • DataBounty_check_submission Read where one submission stands: its status and each check with its reason. Needs the X-DataBounty-Key header. Read it to act on the result, not in a loop: checks take minutes and reviews take longer. Returns: The submission's status in plain words, each check and its result, any reviewer notes, and where to, fix it when it came back.
  • DataBounty_dispute_accepted_item Dispute an accepted item in a pool you requested, while its dispute window is open. Needs the X-DataBounty-Key header (sponsor scope). An admin decides the dispute; the contributor's karma is only reversed if it is upheld. Dispute only with a specific, real reason. Returns: Whether the dispute was filed, and what happens next.
  • DataBounty_get_contributor_profile Get a DataBounty contributor's public profile. Only public profiles are returned, and only the fields the member chose to show. Returns: Display name, tier, karma, badges, accepted items, audits, datasets contributed to and Hugging Face, datasets they are credited on, or an "error" key when there is no public profile.
  • DataBounty_get_karma_leaderboard Get DataBounty's all-time karma leaderboard. Returns: Ranked contributors with handle, display name, karma, accepted item count, tier and public profile URL.
  • DataBounty_get_my_account Check this server's DataBounty connection: whose API key it uses, and whether that account can submit. The contribute tools (this one, get_pool_contract, submit_items, list_my_submissions and check_submission) act as the owner of a DataBounty API key, which the MCP client sends as the X-DataBounty-Key header. Create one at console.databounty.io/developers with the contribute scope and add it to this server's settings. Never ask for the key in a message or pass it as an argument. Returns: The account's handle, display name and karma, whether it is ready to submit, and what to do next.
  • DataBounty_get_platform_stats Get live totals for DataBounty's community dataset programme. Returns: The number of dataset programmes, target and accepted item counts, items that have, cleared the automated checks, contributors, published datasets, total karma awarded,, and the karma tier ladder.
  • DataBounty_get_pool_contract Read exactly what a pool's items must contain, before submitting to it. Needs the X-DataBounty-Key header. Returns: Each field (its key, whether it is required, its kind, help and allowed options), how many items one, submit_items call may carry, the karma per accepted item, an approved example item when there is one,, and the checks every item goes through.
  • DataBounty_get_pool_details Get one DataBounty pool's public details: description, field contract, karma pricing and progress. Returns: The pool's description, every field an item must supply, up to three approved example items,, karma per accepted and per audited item, audit coverage, progress and links, or an "error" key, when no pool has that id.
  • DataBounty_get_pool_items_as_sponsor See the items submitted to a pool you requested, as its sponsor. Needs the X-DataBounty-Key header (sponsor scope). Only the account that requested the pool can read its items. Returns: Each item's id, title, status, contributor, how it was made, its fields and checks, any flags, and for an, accepted item whether it can still be disputed and until when.
  • DataBounty_list_my_submissions List the submissions of this server's API key owner, newest first. Needs the X-DataBounty-Key header. Returns: The total, and each submission's id, title, pool, status, where it stands in plain words, and date.
  • DataBounty_list_published_datasets List the datasets DataBounty has published to the Hugging Face Hub, newest first. Returns: Each dataset's title, item count, licence, publication date, Hugging Face repo id and URL,, GitHub mirror URL when there is one, and Hub download and like counts.
  • DataBounty_search_open_pools Search DataBounty's open community pools: datasets currently accepting contributions. Returns: Open pools, each with its id, title, dataset type, difficulty, accepted and target item counts,, karma per accepted item, licence, and links to view the pool or contribute to it.

All 13 tools

From Hugging Face Spaces. Report a problem