# Hubort (mcpb · hubort-mcp.mcpb)

Search your Claude, ChatGPT, Gemini and Grok chats from every account. Read-only, local.

- Trust score: 36/100 (low)
- Change this week: +5
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-25

## Components

- mcpb · `hubort-mcp.mcpb`: 36/100 (this document), [markdown](https://verifymcp.io/servers/fazy221-hubort/hubort-mcp.md), [page](https://verifymcp.io/servers/fazy221-hubort/hubort-mcp)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/Fazy221/Hubort-releases/releases/download/v1.0.73/hubort-mcp.mcpb`
- Transport: `stdio`
- SHA-256: `9806883857b15e48910b550a86faf226b1fd81683bb1c1e917d15328bb8ffef0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, 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 2026-10-25.

- **Supply Chain Security**: 0/100
  - No malware scan is available for this kind of package: the supply-chain vendors we use do not cover it. This is a permanent gap in our coverage, not a finding about the package.
  - Known CVEs could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: we found no dependency list to check in this bundle: either it runs a compiled binary, whose bundled manifests we do not read, or none of the package.json, requirements.txt, pyproject.toml or uv.lock files it ships for its runtime declares a dependency we can read (a requirements.txt that only points at a setup.py project, a local path, or a nested requirements file we cannot follow counts as none).
- **Provenance & Transparency**: 6/100
  - Repository check failed: no source repository is declared.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (LicenseRef-Proprietary) isn't a recognized OSI-approved license.
  - Actively maintained (last published 10 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 904 tokens (~150/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

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

Hubort ships as an MCPB bundle, a single file you download and open in an MCP host that supports MCPB bundles, such as Claude Desktop. The host reads the launch command from the bundle's own manifest, so there is no command to copy. Before opening it, check the file's SHA-256 matches the one the MCP registry declares for it, 9806883857b15e48910b550a86faf226b1fd81683bb1c1e917d15328bb8ffef0; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/Fazy221/Hubort-releases/releases/download/v1.0.73/hubort-mcp.mcpb`
- SHA-256: `9806883857b15e48910b550a86faf226b1fd81683bb1c1e917d15328bb8ffef0`

### Verify on macOS / Linux

```bash
echo "9806883857b15e48910b550a86faf226b1fd81683bb1c1e917d15328bb8ffef0  hubort-mcp.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\hubort-mcp.mcpb).Hash -eq "9806883857b15e48910b550a86faf226b1fd81683bb1c1e917d15328bb8ffef0"
```

## 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.

### 2026-10-25 (score 36, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-23 (score 35, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-10-15 (score 31, +30)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 100

### 2026-10-09 (score 1)

First indexed and scored.

## MCP tools (6)

### `search_chats` (~349 tokens)

Search chats

Search the person's past AI chats, saved by Hubort from every Claude, ChatGPT, Gemini and Grok account they use. Use it when the person refers to something they discussed, decided, wrote or debugged before, in any AI app, or when earlier work would help. Write the query as keywords or a short question; a time phrase in it ("last month", "in March", "yesterday") narrows by when a chat was last active. Returns the best-matching chats, each with up to three passages and the message number each came from. To see more of a chat, call read_chat with its id and a start a couple of messages before the passage.

Input parameters:

- `account` (string): Only chats from the account with this name (list_accounts shows them).
- `after` (string): Only chats last active on or after this, as a date (2026-09-01) or a date and time in ISO 8601.
- `before` (string): Only chats last active before this, as a date (2026-09-01) or a date and time in ISO 8601.
- `folder` (string): Only chats in the folder with this name or id, its subfolders included (list_folders shows them).
- `include_archived` (boolean): Also search chats the person archived in Hubort. Default false.
- `limit` (integer): How many chats to return, 1 to 20. Default 8.
- `query` (string, required): What to look for: keywords, a name, an error message, or a short question.
- `service` (string): Only chats from this AI service.

### `read_chat` (~133 tokens)

Read a chat

Read one chat's messages, in order, from a given message number. Use the id from search_chats, recent_chats or related_chats. Long chats come in parts: when the answer says there is more, call again with start set to its next_start. Start a couple of messages before a search passage to see the question that led to it.

Input parameters:

- `id` (string, required): The chat's id.
- `max_chars` (integer): Roughly how much text to return. Default 30000.
- `start` (integer): The message number to start from. Default 0, the first message.

### `recent_chats` (~163 tokens)

Recent chats

List the person's most recently active AI chats, newest first, with how each began. Use it for "what was I working on" questions, or to pick up where the person left off, when there's nothing specific to search for.

Input parameters:

- `account` (string): Only chats from the account with this name.
- `after` (string): Only chats last active on or after this, as a date (2026-09-01) or a date and time in ISO 8601.
- `folder` (string): Only chats in the folder with this name or id, its subfolders included.
- `limit` (integer): How many chats, 1 to 50. Default 15.
- `service` (string): Only chats from this AI service.

### `list_accounts` (~58 tokens)

List accounts

List the AI accounts whose chats Hubort holds and this app may read: the service, the account's name in Hubort, how many chats it has and when it was last active. Use it to scope a search to one service or account.

### `list_folders` (~48 tokens)

List folders

List the folders the person organizes their chats into in Hubort, as a tree, with how many chats each holds. Use it to scope a search or a list to a project or topic.

### `related_chats` (~86 tokens)

Related chats

Find chats about the same thing as a given chat, across every account and service, by meaning rather than shared words. Use it after finding one relevant chat, to gather the rest of a topic the person may have discussed elsewhere.

Input parameters:

- `id` (string, required): The chat's id.
- `limit` (integer): How many chats, 1 to 20. Default 5.

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/fazy221-hubort/hubort-mcp#diagnostics

## Score history

- 2026-10-25: 36
- 2026-10-24: 35
- 2026-10-23: 35
- 2026-10-22: 31
- 2026-10-21: 31
- 2026-10-20: 31
- 2026-10-19: 31
- 2026-10-18: 31
- 2026-10-17: 31
- 2026-10-16: 31
- 2026-10-15: 31
- 2026-10-14: 1
- 2026-10-13: 1
- 2026-10-12: 1
- 2026-10-10: 1
- 2026-10-09: 1

## Common questions

### What is the Hubort MCP server?

Hubort is an MCP server listed in the public MCP registry as io.github.Fazy221/hubort. Search your Claude, ChatGPT, Gemini and Grok chats from every account. Read-only, local. This page covers its MCPB bundle (https://github.com/Fazy221/Hubort-releases/releases/download/v1.0.73/hubort-mcp.mcpb).

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

Hubort scores 36 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 Hubort MCP server expose?

Hubort exposes 6 tools: search_chats, read_chat, recent_chats, list_accounts, list_folders, related_chats. Their descriptions and schemas cost roughly 837 tokens of context every time the server is loaded.

### What licence is the Hubort MCP server under?

Hubort declares the LicenseRef-Proprietary licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.

## Links

- Website: https://hubort.app/mcp
- Changelog RSS feed: https://verifymcp.io/servers/fazy221-hubort/hubort-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/fazy221-hubort/hubort-mcp.json
- HTML version of this page: https://verifymcp.io/servers/fazy221-hubort/hubort-mcp