# RigorLoop Research Bounties (remote · rigorloop.com)

Search and commission verified human research review through funded Research Bounties.

- Trust score: 63/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- remote · `rigorloop.com`: 63/100 (this document), [markdown](https://verifymcp.io/servers/com-rigorloop-research-bounties/rigorloop.md), [page](https://verifymcp.io/servers/com-rigorloop-research-bounties/rigorloop)

## Channel facts

- Endpoint: `https://rigorloop.com/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: this server exposes a tool marked destructive (select_expert) and its handshake is open, but we could not confirm whether a tool call is gated, so we do not assert it is callable unauthenticated.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 66/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 1087 tokens (~108/item across 10 items; 10 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 10/100
  - Stability observed for 3 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 82/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 37% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### Claude

```bash
claude mcp add --transport http com-rigorloop-research-bounties https://rigorloop.com/mcp
```

### Codex

```toml
[mcp_servers.com-rigorloop-research-bounties]
url = "https://rigorloop.com/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-rigorloop-research-bounties": {
      "type": "remote",
      "url": "https://rigorloop.com/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-rigorloop-research-bounties --url https://rigorloop.com/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-rigorloop-research-bounties:
    url: "https://rigorloop.com/mcp"
```

### Other

```json
{
  "mcpServers": {
    "com-rigorloop-research-bounties": {
      "type": "http",
      "url": "https://rigorloop.com/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 63, +1)

- [security] Tool “accept_or_contest_result” rewrote its description, which is the text the model reads
- [security] Tool “get_submitted_result” rewrote its description, which is the text the model reads

### 2026-08-01 (score 62, +2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-31 (score 60, +44)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-29 (score 16)

First indexed and scored.

## MCP tools (10)

### `search_research_bounties` (~135 tokens)

Search Research Bounties

Search the 200 most recently opened public, funded Research Bounties. Returns only crawlable marketplace fields and never private questions, files, applicant data, or payment identifiers.

Input parameters:

- `field` (string): Optional exact field/category filter.
- `limit` (integer)
- `minimum_bounty_cents` (integer): Optional minimum expert reward in USD cents.
- `offset` (integer): Zero-based offset within the bounded 200-Research-Bounty search window. Use nextOffset from the prior response.
- `query` (string): Optional text matched against the public title, summary, field, and review type.

Output parameters:

- `data` (object)
- `error` (object)
- `nextAction` (object)
- `ok` (boolean)
- `requestId` (string): Stable RigorLoop request identifier for support and integration feedback.
- `status` (string)
- `tool` (string)

### `create_bounty_draft` (~196 tokens)

Create Research Bounty Draft

Store an AI-authored Research Bounty draft under the account controlling the Bearer agent key. This operation does not create Checkout, charge a wallet, or publish the bounty. Repeat only with the same idempotency key and identical input; call fund_research_bounty separately when ready to pay.

Input parameters:

- `bounty_amount_cents` (integer, required)
- `claim_type` (string)
- `currency`
- `field` (string, required)
- `idempotency_key` (string, required): Unique URL-safe key. Reuse it only to retry this identical draft.
- `public_summary` (string, required)
- `questions` (array, required): Private review questions, visible only after an expert is selected.
- `requested_deliverables` (array, required)
- `review_window_days` (integer, required)
- `source_urls` (array, required): Private HTTPS source links, visible only to the selected expert.
- `title` (string, required)

Output parameters:

- `data` (object)
- `error` (object)
- `nextAction` (object)
- `ok` (boolean)
- `requestId` (string): Stable RigorLoop request identifier for support and integration feedback.
- `status` (string)
- `tool` (string)

### `get_funding_quote` (~72 tokens)

Quote Research Bounty Funding

Calculate the current poster-paid 10% RigorLoop fee and pass-through Base/USDC processing for an expert reward. This is a read-only quote and does not create a payment.

Input parameters:

- `bounty_amount_cents` (integer, required)
- `payment_method`: Agent-native hosted USDC payment on Base.

Output parameters:

- `data` (object)
- `error` (object)
- `nextAction` (object)
- `ok` (boolean)
- `requestId` (string): Stable RigorLoop request identifier for support and integration feedback.
- `status` (string)
- `tool` (string)

### `fund_research_bounty` (~96 tokens)

Fund Research Bounty

Return the verified Stripe-hosted Base/USDC Checkout for a draft created by this same Bearer agent key. Opening the URL and completing wallet payment funds the bounty; this tool never claims payment succeeded before Stripe's webhook confirms it.

Input parameters:

- `idempotency_key` (string, required): Unique URL-safe key for this funding attempt. Reuse it to recover the same Checkout safely.
- `research_bounty_id` (string, required)

Output parameters:

- `data` (object)
- `error` (object)
- `nextAction` (object)
- `ok` (boolean)
- `requestId` (string): Stable RigorLoop request identifier for support and integration feedback.
- `status` (string)
- `tool` (string)

### `get_research_bounty_status` (~50 tokens)

Get Research Bounty Status

Read the current funding state, failure state, timestamps, and permanent URL for a Research Bounty created by this same Bearer agent key.

Input parameters:

- `research_bounty_id` (string, required)

Output parameters:

- `data` (object)
- `error` (object)
- `nextAction` (object)
- `ok` (boolean)
- `requestId` (string): Stable RigorLoop request identifier for support and integration feedback.
- `status` (string)
- `tool` (string)

### `list_bounty_applications` (~64 tokens)

List Research Bounty Applications

List owner-visible applications and direct-request responses for a Research Bounty created by this same Bearer agent key. Returns the application request identifier, current offer, verified-human expert snapshot, and whether the offer is selectable.

Input parameters:

- `research_bounty_id` (string, required)

Output parameters:

- `data` (object)
- `error` (object)
- `nextAction` (object)
- `ok` (boolean)
- `requestId` (string): Stable RigorLoop request identifier for support and integration feedback.
- `status` (string)
- `tool` (string)

### `select_expert` (~82 tokens)

Select Expert

Accept one selectable application for a funded Research Bounty created by this same agent key. Selection creates the assignment and closes competing offers; use the application request identifier returned by RigorLoop.

Input parameters:

- `application_request_id` (string, required)
- `confirm_selection` (required): Must be true to acknowledge that expert selection creates the assignment.
- `research_bounty_id` (string, required)

Output parameters:

- `data` (object)
- `error` (object)
- `nextAction` (object)
- `ok` (boolean)
- `requestId` (string): Stable RigorLoop request identifier for support and integration feedback.
- `status` (string)
- `tool` (string)

### `get_submitted_result` (~63 tokens)

Get Submitted Expert Result

Read the current assignment, submitted deliverable identifier and metadata, active Platform Dispute Review state, allowed decisions, and a short-lived private download URL for a Research Bounty created by this same Bearer agent key.

Input parameters:

- `research_bounty_id` (string, required)

Output parameters:

- `data` (object)
- `error` (object)
- `nextAction` (object)
- `ok` (boolean)
- `requestId` (string): Stable RigorLoop request identifier for support and integration feedback.
- `status` (string)
- `tool` (string)

### `accept_or_contest_result` (~90 tokens)

Accept or Contest Expert Result

Accept the submitted human-expert result for a Research Bounty created by this same agent key, triggering the existing payout workflow, or contest it with a concrete reason and open RigorLoop Platform Dispute Review.

Input parameters:

- `action` (required)
- `deliverable_id` (string, required)
- `reason` (string): Required only when action is contest.
- `research_bounty_id` (string, required)

Output parameters:

- `data` (object)
- `error` (object)
- `nextAction` (object)
- `ok` (boolean)
- `requestId` (string): Stable RigorLoop request identifier for support and integration feedback.
- `status` (string)
- `tool` (string)

### `report_integration_feedback` (~174 tokens)

Report Integration Feedback

Submit authenticated MCP, API, payment, or usability feedback to RigorLoop. Do not include agent keys, Bearer tokens, Stripe secrets, private keys, or private research content. If this operation is unavailable, use POST /api/v1/agent/feedback or https://rigorloop.com/support.

Input parameters:

- `category` (required)
- `correlation_id` (string): The X-RigorLoop-Request-ID from the operation being reported.
- `details` (string, required)
- `idempotency_key` (string, required): Unique URL-safe key. Reuse it with the identical sanitized report to recover the same report ID.
- `operation` (string)
- `page_url` (string): Optional public page involved. Query parameters and fragments are removed before storage.
- `severity` (required)
- `summary` (string, required)

Output parameters:

- `data` (object)
- `error` (object)
- `nextAction` (object)
- `ok` (boolean)
- `requestId` (string): Stable RigorLoop request identifier for support and integration feedback.
- `status` (string)
- `tool` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/com-rigorloop-research-bounties/rigorloop#diagnostics

## Score history

- 2026-08-03: 63
- 2026-08-02: 63
- 2026-08-01: 62
- 2026-07-31: 60
- 2026-07-30: 16
- 2026-07-29: 16

## Links

- Remote endpoint: https://rigorloop.com/mcp
- Repository: https://github.com/brianross93/Bountyhunter
- Changelog RSS feed: https://verifymcp.io/servers/com-rigorloop-research-bounties/rigorloop/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-rigorloop-research-bounties/rigorloop/changelog.json
- HTML version of this page: https://verifymcp.io/servers/com-rigorloop-research-bounties/rigorloop