# Kunkafa (remote · kunkafa.com)

Market forecasts with their own track record, inside Claude, ChatGPT and other MCP apps.

- Trust score: 97/100 (high trust)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `kunkafa.com`: 97/100 (this document), [markdown](https://verifymcp.io/servers/com-kunkafa-kunkafa/kunkafa.md), [page](https://verifymcp.io/servers/com-kunkafa-kunkafa/kunkafa)

## Channel facts

- Endpoint: `https://kunkafa.com/mcp`
- Transports: `streamable-http`
- Auth: `required`
- 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 2026-11-05.

- **Endpoint Security**: 100/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC is configured correctly; the domain's records validate against the full chain to the root.
  - The authorisation server supports Client ID Metadata Documents, the current MCP client-registration mechanism.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 85/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 899 tokens (~89/item across 10 items; 9 tools + 1 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 100/100
  - No destabilizing schema changes in the last 30 days.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Kunkafa MCP server?

Kunkafa is a hosted endpoint at https://kunkafa.com/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 com-kunkafa-kunkafa 'https://kunkafa.com/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "com-kunkafa-kunkafa": {
      "url": "https://kunkafa.com/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-kunkafa-kunkafa": {
      "type": "http",
      "url": "https://kunkafa.com/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.com-kunkafa-kunkafa]
url = "https://kunkafa.com/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add com-kunkafa-kunkafa --url 'https://kunkafa.com/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  com-kunkafa-kunkafa:
    url: "https://kunkafa.com/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "com-kunkafa-kunkafa": {
      "Transport": "http",
      "Url": "https://kunkafa.com/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-kunkafa-kunkafa -t streamable-http -u 'https://kunkafa.com/mcp'
```

### Other

```json
{
  "mcpServers": {
    "com-kunkafa-kunkafa": {
      "type": "http",
      "url": "https://kunkafa.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.

### 2026-11-05 (score 97, 0)

- [security] Stability: 0.97 → pass

### 2026-11-04 (score 97, 0)

- [functional] Stability: pass → 0.97

### 2026-11-02 (score 97, 0)

- [security] Stability: 0.97 → pass

### 2026-11-01 (score 97, +1)

No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 96, +1)

No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-27 (score 95, +1)

No change was recorded against any check on this day. Stability & Change Management went from 77 to 80. That category is still filling its 30-day observation window: 23 days of observed history at the previous scan, 24 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 94, +1)

No change was recorded against any check on this day. Stability & Change Management went from 70 to 73. That category is still filling its 30-day observation window: 21 days of observed history at the previous scan, 22 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 93, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (9)

### `list_markets` (~81 tokens)

Available markets

Markets this account can read, each with the durations that have forecasts now, and what it follows. Page with page.nextCursor.

Input parameters:

- `cursor` (string): page.nextCursor from the previous reply, to read the next page; omit for the first page
- `limit` (integer): Items per page, 1 to 50; default 50

Output parameters:

- `data` (array)
- `dataUse` (string): Use restriction on every reply: data collection is prohibited; the data may not be collected, saved, stored, exported or compiled, or used to train, retrain, fine-tune or distil any model.
- `following`
- `notices` (array)
- `page`
- `usage`

### `get_outlooks` (~259 tokens)

Current forecasts

Current forecasts for one market; one market per call by design, so data is not pulled in bulk. Choose durations (exact or a range) and optionally direction, confidence or target filters. At most 6 durations and 72 forecasts per call; calls can run in parallel.

Input parameters:

- `direction` (string): Default both
- `durations` (array): Exact duration labels from list_markets, for example ["1 hour", "6 hours"]
- `market` (string, required): Market slug from list_markets, for example bitcoin
- `maxDuration` (string): Longest duration to include, for example "1 day"
- `maxDurationExclusive` (boolean): true for "less than maxDuration"; default includes maxDuration
- `maxProbabilityPercent` (number): Only forecasts whose probability is at most this
- `maxTargetPercent` (number): Only targets at most this far from the reference price, in percent
- `minDuration` (string): Shortest duration to include, for example "1 hour"
- `minProbabilityPercent` (number): Only forecasts whose probability (Kunkafa's confidence) is at least this
- `minTargetPercent` (number): Only targets at least this far from the reference price, in percent

Output parameters:

- `data`
- `dataUse` (string): Use restriction on every reply: data collection is prohibited; the data may not be collected, saved, stored, exported or compiled, or used to train, retrain, fine-tune or distil any model.
- `fieldGuide`
- `notices` (array)
- `usage`

### `get_performance` (~77 tokens)

Past performance

How often past forecasts touched their target, by confidence level and period. Pass probabilityPercent for the matching row (headline).

Input parameters:

- `market` (string, required): Market slug from list_markets, for example bitcoin
- `probabilityPercent` (number): A forecast's confidence; the headline shows past results at the nearest published level at or below it

Output parameters:

- `data`
- `dataUse` (string): Use restriction on every reply: data collection is prohibited; the data may not be collected, saved, stored, exported or compiled, or used to train, retrain, fine-tune or distil any model.
- `fieldGuide` (object): Plain meanings of the returned fields.
- `headline`
- `notices` (array)
- `usage`

### `get_results` (~62 tokens)

Past results

Recent example forecasts with their outcomes; not a full record.

Input parameters:

- `durations` (array): Only these duration labels, for example ["1 hour", "1 day"]; default every duration
- `market` (string, required): Market slug from list_markets, for example bitcoin

Output parameters:

- `data`
- `dataUse` (string): Use restriction on every reply: data collection is prohibited; the data may not be collected, saved, stored, exported or compiled, or used to train, retrain, fine-tune or distil any model.
- `fieldGuide` (object): Plain meanings of the returned fields.
- `notices` (array)
- `usage`

### `get_usage` (~80 tokens)

Usage and limits

Remaining allowances, what one get_outlooks call returns, and this connection's permissions, canFollow and expiry. Uses no allowance.

Input parameters:

- `cursor` (string): page.nextCursor from the previous reply, to read the next page; omit for the first page
- `limit` (integer): Items per page, 1 to 50; default 50

Output parameters:

- `data` (object)
- `dataUse` (string): Use restriction on every reply: data collection is prohibited; the data may not be collected, saved, stored, exported or compiled, or used to train, retrain, fine-tune or distil any model.
- `following`
- `notices` (array)
- `page`
- `usage`

### `follow_market` (~86 tokens)

Follow a market

Follow a market for this account. Check canFollow in get_usage first. Replacing a followed market is allowed once every 30 days: ask the user, then call with confirmReplacement true.

Input parameters:

- `confirmReplacement` (boolean): Set true only after the user agreed to replace a market they already follow
- `market` (string, required): Market slug from list_markets, for example bitcoin

Output parameters:

- `data`
- `dataUse` (string): Use restriction on every reply: data collection is prohibited; the data may not be collected, saved, stored, exported or compiled, or used to train, retrain, fine-tune or distil any model.
- `following`
- `notices` (array)
- `usage`

### `unfollow_market` (~45 tokens)

Unfollow a market

Stop following a market; its data stops being readable. Check canFollow in get_usage first.

Input parameters:

- `market` (string, required): Market slug from list_markets, for example bitcoin

Output parameters:

- `data`
- `dataUse` (string): Use restriction on every reply: data collection is prohibited; the data may not be collected, saved, stored, exported or compiled, or used to train, retrain, fine-tune or distil any model.
- `following`
- `notices` (array)
- `usage`

### `get_glossary` (~36 tokens)

Glossary

What every Kunkafa term and number means and how to read them. Call once before explaining results. No sign-in needed.

Output parameters:

- `glossary` (object)

### `get_account_links` (~21 tokens)

Kunkafa account links

Links to create an account, sign in and manage connections.

Output parameters:

- `availabilityMessage` (string)
- `browserConfirmationRequired`
- `disclosureUnits`
- `links` (object)
- `mcp`
- `mcpAvailability`: Public availability follows release controls.

## Diagnostics

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

## Score history

- 2026-11-05: 97
- 2026-11-04: 97
- 2026-11-03: 97
- 2026-11-02: 97
- 2026-11-01: 97
- 2026-10-31: 96
- 2026-10-30: 96
- 2026-10-29: 95
- 2026-10-28: 95
- 2026-10-27: 95
- 2026-10-26: 94
- 2026-10-25: 94
- 2026-10-24: 93
- 2026-10-23: 93
- 2026-10-22: 92
- 2026-10-21: 92
- 2026-10-20: 91
- 2026-10-19: 91
- 2026-10-18: 90
- 2026-10-17: 90
- 2026-10-16: 89
- 2026-10-15: 89
- 2026-10-14: 88
- 2026-10-13: 88
- 2026-10-12: 88
- 2026-10-10: 87
- 2026-10-08: 86
- 2026-10-06: 85
- 2026-10-04: 84
- 2026-10-03: 83

## Common questions

### What is the Kunkafa MCP server?

Kunkafa is an MCP server listed in the public MCP registry as com.kunkafa/kunkafa. Market forecasts with their own track record, inside Claude, ChatGPT and other MCP apps. This page covers its hosted endpoint (https://kunkafa.com/mcp).

### Is the Kunkafa MCP server safe to use?

Kunkafa scores 97 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 Kunkafa MCP server expose?

Kunkafa exposes 9 tools: list_markets, get_outlooks, get_performance, get_results, get_usage, and 4 more. Their descriptions and schemas cost roughly 747 tokens of context every time the server is loaded.

### Does the Kunkafa MCP server require authentication?

Yes. Kunkafa asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the Kunkafa MCP server still maintained?

Kunkafa 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://kunkafa.com/mcp
- Repository: https://github.com/Kareemfarid/kunkafa-mcp
- Website: https://kunkafa.com/developers/setup
- Changelog RSS feed: https://verifymcp.io/servers/com-kunkafa-kunkafa/kunkafa.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-kunkafa-kunkafa/kunkafa.json
- HTML version of this page: https://verifymcp.io/servers/com-kunkafa-kunkafa/kunkafa