# Prediction Market Rule Check MCP (remote · prediction-rules-mcp.donniertf.workers.dev)

Risk-scores Polymarket/Kalshi settlement rules; Kalshi weather settlements. Not advice.

- Trust score: 58/100 (low)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `prediction-rules-mcp.donniertf.workers.dev`: 58/100 (this document), [markdown](https://verifymcp.io/servers/donniertf-hub-prediction-rules-mcp/prediction-rules-mcp.md), [page](https://verifymcp.io/servers/donniertf-hub-prediction-rules-mcp/prediction-rules-mcp)

## Channel facts

- Endpoint: `https://prediction-rules-mcp.donniertf.workers.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.3.0`

## 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 2026-11-05.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 12 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS check failed: the endpoint is reachable over plaintext HTTP.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - 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**: 64/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1429 tokens (~119/item across 12 items; 12 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 94/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 81% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 12 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 13 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 40/100
  - Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28.

## Install

### How do I install the Prediction Market Rule Check MCP server?

Prediction Market Rule Check MCP is a hosted endpoint at https://prediction-rules-mcp.donniertf.workers.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http donniertf-hub-prediction-rules-mcp 'https://prediction-rules-mcp.donniertf.workers.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "donniertf-hub-prediction-rules-mcp": {
      "url": "https://prediction-rules-mcp.donniertf.workers.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "donniertf-hub-prediction-rules-mcp": {
      "type": "http",
      "url": "https://prediction-rules-mcp.donniertf.workers.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.donniertf-hub-prediction-rules-mcp]
url = "https://prediction-rules-mcp.donniertf.workers.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "donniertf-hub-prediction-rules-mcp": {
      "type": "remote",
      "url": "https://prediction-rules-mcp.donniertf.workers.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add donniertf-hub-prediction-rules-mcp --url 'https://prediction-rules-mcp.donniertf.workers.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  donniertf-hub-prediction-rules-mcp:
    url: "https://prediction-rules-mcp.donniertf.workers.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "donniertf-hub-prediction-rules-mcp": {
      "Transport": "http",
      "Url": "https://prediction-rules-mcp.donniertf.workers.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add donniertf-hub-prediction-rules-mcp -t streamable-http -u 'https://prediction-rules-mcp.donniertf.workers.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "donniertf-hub-prediction-rules-mcp": {
      "type": "http",
      "url": "https://prediction-rules-mcp.donniertf.workers.dev/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.

### 2026-11-04 (score 58, +1)

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

### 2026-11-02 (score 57, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 56, +1)

- [security] Tool “doubles_today” rewrote its description, which is the text the model reads
- [functional] Server version: 1.3.0 → 1.4.0
- [cosmetic] “doubles_today” reworded the description of “access_token”

### 2026-10-30 (score 55, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-10-29 (score 55)

First indexed and scored.

## MCP tools (12)

### `rule_check` (~57 tokens)

FREE. Risk-score the settlement rules of a Polymarket market (slug or search words): flags discretion, vague sources, cancellation and deadline traps. Top 2 markets.

Input parameters:

- `market` (string, required): Polymarket slug or search words

### `rule_check_full` (~61 tokens)

PRO. Full rule text + resolution source + all flags for up to 10 Polymarket markets matching a slug or search.

Input parameters:

- `access_token` (string): Subscriber token from /success (or Authorization: Bearer)
- `market` (string, required)

### `kalshi_check` (~54 tokens)

PRO. Risk-score a Kalshi market's rules by ticker (rules_primary + rules_secondary).

Input parameters:

- `access_token` (string): Subscriber token from /success (or Authorization: Bearer)
- `ticker` (string, required)

### `scan_risky` (~67 tokens)

PRO. Scan the top live Polymarket markets by volume and list the ones with the riskiest settlement wording.

Input parameters:

- `access_token` (string): Subscriber token from /success (or Authorization: Bearer)
- `limit` (number)
- `min_score` (number)

### `market_lookup` (~85 tokens)

FREE. Live price, volume and close time for ONE prediction market in the normalised Polymarket+Kalshi schema. Give a Polymarket slug or a Kalshi ticker.

Input parameters:

- `id` (string, required): Polymarket market slug (e.g. will-x-happen) or Kalshi market ticker (e.g. KXFEDDECISION-26DEC-H0)

### `live_markets` (~113 tokens)

PAID $0.02/call (x402) or subscription. Live open markets from Polymarket and Kalshi in one schema, ranked by 24h volume within each venue (interleaved). Filter by venue or text.

Input parameters:

- `access_token` (string): Subscriber token from /success (or Authorization: Bearer)
- `contains` (string): Optional text filter on question
- `limit` (number): 1-100, default 25
- `venue` (string): Default all

### `search_markets` (~106 tokens)

PAID $0.02/call (x402) or subscription. Keyword search across live Polymarket and Kalshi markets (e.g. 'fed rate', 'bitcoin', 'election'); normalised prices and volumes.

Input parameters:

- `access_token` (string): Subscriber token from /success (or Authorization: Bearer)
- `limit` (number): 1-50, default 20
- `query` (string, required)
- `venue` (string): Default all

### `top_movers` (~89 tokens)

PAID $0.02/call (x402) or subscription. Live markets with the biggest 24h price moves on Polymarket and Kalshi, in one schema.

Input parameters:

- `access_token` (string): Subscriber token from /success (or Authorization: Bearer)
- `limit` (number): 1-50, default 15
- `venue` (string): Default all

### `doubles_record` (~160 tokens)

FREE. Sports doubles feed (info only, 18+): the full SETTLED record of Grok Double Bot's daily doubles, every pick including losses, with legs, odds at tip time and result; won/lost/void counts, win rate, average combined odds and running profit on a flat £10 stake, plus pre-kickoff SHA-256 fingerprints of each day's sealed picks (salt + text revealed after they settle; public page /record). Never shows unsettled picks. Information only, not betting advice. No guaranteed returns. 18+. BeGambleAware.org

Input parameters:

- `limit` (number): Most recent N settled picks to list (1-500, default all up to 500). Stats always cover the full record.

### `doubles_today` (~146 tokens)

PAID $1.00/call (x402 USDC on Base; one call returns the whole day's picks, so $1 a day) or the $15/month doubles plan. Not included in the £12/month plan, bundle passes or trial keys. Sports doubles feed (info only, 18+): today's stats-led doubles from Grok Double Bot with legs, kick-off/start times (UK), odds at tip time, combined odds, confidence and rationale. Information only, not betting advice. No guaranteed returns. 18+. BeGambleAware.org

Input parameters:

- `access_token` (string): $15/month doubles plan token from /success (or Authorization: Bearer)

### `kalshi_weather_series` (~118 tokens)

FREE. List Kalshi weather series (daily high/low temperature, rain, snow) by city or keyword, with series ticker, frequency and official settlement source. Use the ticker with kalshi_weather_settlements. Information only, not betting advice. Historical settlements do not predict future results. 18+. BeGambleAware.org

Input parameters:

- `city` (string): City or keyword, e.g. London, NYC, Chicago
- `kind` (string)
- `limit` (number): default 25, max 100

### `kalshi_weather_settlements` (~325 tokens)

PAID $0.02/call (x402) or subscription / bundle pass. Settled Kalshi weather markets for a series (e.g. KXHIGHNY) or city: per market the ticker, close date, exact close_time (ISO 8601 UTC, Z) and close_time_local (ISO with the city's UTC offset; local_tz IANA zone, null if unknown), settlement_time (Kalshi settlement timestamp, ISO UTC; null if Kalshi gives none) and close_to_settlement_seconds / close_to_settlement_minutes (gap from close to settlement, to spot late settlements or revisions), expiration_time, strike/bucket, yes/no result and settlement payout, plus the observed settlement value per day and the official settlement source. Optional date range. Information only, not betting advice. Historical settlements do not predict future results. 18+. BeGambleAware.org

Input parameters:

- `access_token` (string): Subscriber token from /success (or Authorization: Bearer)
- `city` (string): Alternative to series: city/station keyword (e.g. London, Chicago)
- `from` (string): Close date from, YYYY-MM-DD
- `kind` (string): With city: which series type (default high)
- `limit` (number): Max markets, default 100, max 500
- `series` (string): Series ticker, e.g. KXHIGHNY, KXHIGHTEGLL, KXRAINNYC
- `to` (string): Close date to, YYYY-MM-DD

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/donniertf-hub-prediction-rules-mcp/prediction-rules-mcp#diagnostics

## Score history

- 2026-11-05: 58
- 2026-11-04: 58
- 2026-11-03: 57
- 2026-11-02: 57
- 2026-11-01: 56
- 2026-10-31: 56
- 2026-10-30: 55
- 2026-10-29: 55

## Common questions

### What is the Prediction Market Rule Check MCP server?

Prediction Market Rule Check MCP is listed in the public MCP registry as io.github.donniertf-hub/prediction-rules-mcp. Risk-scores Polymarket/Kalshi settlement rules; Kalshi weather settlements. Not advice. This page covers its hosted endpoint (https://prediction-rules-mcp.donniertf.workers.dev/mcp).

### Is the Prediction Market Rule Check MCP server safe to use?

Prediction Market Rule Check MCP scores 58 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Prediction Market Rule Check MCP server expose?

Prediction Market Rule Check MCP exposes 12 tools: rule_check, rule_check_full, kalshi_check, scan_risky, market_lookup, and 7 more. Their descriptions and schemas cost roughly 1,381 tokens of context every time the server is loaded.

### Does the Prediction Market Rule Check MCP server require authentication?

No. We connected to Prediction Market Rule Check MCP without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Prediction Market Rule Check MCP server still maintained?

Prediction Market Rule Check MCP is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://prediction-rules-mcp.donniertf.workers.dev/mcp
- Repository: https://github.com/donniertf-hub/uk-mcp-fleet
- Website: https://prediction-rules-mcp.donniertf.workers.dev/
- Changelog RSS feed: https://verifymcp.io/servers/donniertf-hub-prediction-rules-mcp/prediction-rules-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/donniertf-hub-prediction-rules-mcp/prediction-rules-mcp.json
- HTML version of this page: https://verifymcp.io/servers/donniertf-hub-prediction-rules-mcp/prediction-rules-mcp