# io.hunchful/hunchful (remote · hunchful.io)

Read and grow a person's falsifiable, consent-based model of how they work with AI (CMP).

- Trust score: 72/100 (medium)
- Change this week: +7
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-04

## Components

- remote · `hunchful.io`: 72/100 (this document), [markdown](https://verifymcp.io/servers/io-hunchful-hunchful/hunchful.md), [page](https://verifymcp.io/servers/io-hunchful-hunchful/hunchful)

## Channel facts

- Endpoint: `https://hunchful.io/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 2026-08-04.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - 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**: 57/100
  - AI-judged instruction clarity (fair).
  - Context-footprint check failed: tool/resource definitions use about 890 tokens (~127/item across 7 items; 7 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 93/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 74% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add --transport http io-hunchful-hunchful https://hunchful.io/mcp
```

### Codex

```toml
[mcp_servers.io-hunchful-hunchful]
url = "https://hunchful.io/mcp"
```

### opencode

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

### OpenClaw

```bash
openclaw mcp add io-hunchful-hunchful --url https://hunchful.io/mcp --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  io-hunchful-hunchful:
    url: "https://hunchful.io/mcp"
```

### Other

```json
{
  "mcpServers": {
    "io-hunchful-hunchful": {
      "type": "http",
      "url": "https://hunchful.io/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.

### 2026-08-03 (score 72, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-01 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-31 (score 70, +4)

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

### 2026-07-30 (score 66, +1)

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

### 2026-07-28 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-07-27 (score 64, +1)

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

### 2026-07-26 (score 63)

First indexed and scored.

## MCP tools (7)

### `read_model` (~79 tokens)

Read a Hunchful collaboration model: its hunches (axis, pole, confidence), the axis ids you can refine, and how you're connected. Start here. With OAuth, omit modelId to read the connected person's own model.

Input parameters:

- `modelId` (string): Model id. Omit when connected via OAuth to use the person's own model.

Output parameters:

- `canApplyDirectly` (boolean)
- `connectedAs` (string)
- `constraints` (string)
- `guidance` (string)
- `howToConnect` (string)
- `hunches` (array)
- `libraryVersion` (string)
- `modelId` (string)
- `openHunches` (object)
- `refinablePatternIds` (array)
- `render` (string)
- `urls` (object)

### `propose_refinement` (~79 tokens)

Propose a refinement (provenance pointers only). It lands in the owner's confirm queue — nothing changes until they accept. Authorized by OAuth (own model) or a contributionToken.

Input parameters:

- `contributionToken` (string): Scoped propose-only key, if not connected via OAuth.
- `items` (array, required)
- `modelId` (string)

Output parameters:

- `note` (string)
- `proposalIds` (array)
- `reviewUrl` (string)
- `status` (string)

### `suggest_question` (~210 tokens)

Suggest a NEW question/axis for the person — a dimension their model doesn't capture (situational axes welcome: name it 'When <situation>'). It lands in their Hunchful inbox and, by default, emails them; nothing is added until they answer. Authorized by OAuth (own model) or a contributionToken. Use sparingly — about once a week at most.

Input parameters:

- `by` (string): Your name, e.g. "claude".
- `contributionToken` (string): Scoped propose-only key, if not connected via OAuth.
- `modelId` (string)
- `name` (string, required): Short axis name, e.g. "When plans change suddenly".
- `poleA` (string, required): Pole A label — one way of working.
- `poleB` (string, required): Pole B label — the other way.
- `question` (string, required): The question, addressed to the person.
- `why` (string): Why you're asking — what you observed (no quotes, no names).

Output parameters:

- `inboxUrl` (string)
- `note` (string)
- `notified` (boolean)
- `proposalId` (string)
- `status` (string)

### `add_hunch` (~235 tokens)

Record a NEW hunch the person just confirmed in conversation — a custom axis with their answer, added directly to their model (visible, revisable, removable by them). OWNER-LEVEL trust required: OAuth as the owner, or the editToken. Only record what the person actually said — never invent or infer a hunch they didn't confirm. For situational axes name it 'When <situation>'. If they haven't answered yet, use suggest_question instead.

Input parameters:

- `by` (string): Your name, e.g. "claude" — recorded in the revision history.
- `confidence` (number): 0.05–0.97; default 0.7 for a fresh self-stated answer.
- `editToken` (string): The model's edit key, if not connected via OAuth.
- `modelId` (string)
- `name` (string, required): Short axis name, e.g. "When plans change suddenly".
- `pole` (string, required): The pole the person SAID fits them.
- `poleA` (string, required): Pole A label.
- `poleB` (string, required): Pole B label.

Output parameters:

- `falsifier` (string)
- `note` (string)
- `ok` (boolean)
- `patternId` (string)
- `statement` (string)
- `urls` (object)

### `find_complementary_thinkers` (~82 tokens)

Which famous thinkers would COMPLETE this person — opposite poles on the axes where opposites unstick each other (not similarity). Open read; great for curiosity and for explaining what a complementary collaborator looks like. Share the pages as links.

Input parameters:

- `modelId` (string): Model id. Omit when connected via OAuth to use the person's own model.

Output parameters:

- `complements` (array)
- `humanVersion` (string)
- `modelId` (string)
- `note` (string)

### `find_matches` (~121 tokens)

Look for complementary PEOPLE for the connected person (rule: agents propose, humans accept — this creates pending proposals the human decides on in their Hunchful hub; identities are never revealed here). Requires OAuth as the owner or the model's editToken, and the person must have joined introductions on their matches page.

Input parameters:

- `direction` (string): seek = they want a fresh angle; offer = they can offer one. Default seek.
- `editToken` (string): The model's edit key, if not connected via OAuth.
- `modelId` (string)

Output parameters:

- `matchesUrl` (string)
- `note` (string)
- `proposals` (array)

### `apply_refinement` (~84 tokens)

Apply a refinement directly as one logged revision (append evidence pointers, nudge confidence). Authorized by OAuth (own model) or an editToken. Prefer propose_refinement unless the owner asked for direct writes.

Input parameters:

- `editToken` (string): The model's edit key, if not connected via OAuth.
- `items` (array, required)
- `modelId` (string)

Output parameters:

- `applied` (array)
- `note` (string)
- `ok` (boolean)
- `updatedAt` (string)
- `urls` (object)

## Diagnostics

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

## Score history

- 2026-08-04: 72
- 2026-08-03: 72
- 2026-08-02: 71
- 2026-08-01: 71
- 2026-07-31: 70
- 2026-07-30: 66
- 2026-07-29: 65
- 2026-07-28: 65
- 2026-07-27: 64
- 2026-07-26: 63

## Links

- Remote endpoint: https://hunchful.io/mcp
- Repository: https://github.com/filinils/hunchful-mcp
- Website: https://hunchful.io/
- Changelog RSS feed: https://verifymcp.io/servers/io-hunchful-hunchful/hunchful/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-hunchful-hunchful/hunchful/changelog.json
- HTML version of this page: https://verifymcp.io/servers/io-hunchful-hunchful/hunchful