# Rootz Archive (mcpb · rootz-archive-0.7.5.mcpb)

Search your local Claude Code archive. For continuous capture, use the Rootz Archive plugin.

- Trust score: 35/100 (low)
- Change this week: 0
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-22

## Components

- mcpb · `rootz-archive-0.7.5.mcpb`: 35/100 (this document), [markdown](https://verifymcp.io/servers/global-rootz-archive/rootz-archive.md), [page](https://verifymcp.io/servers/global-rootz-archive/rootz-archive)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/rootz-global/rootz-archive/releases/download/v0.7.5/rootz-archive-0.7.5.mcpb`
- Transport: `stdio`
- SHA-256: `e1c68f29ea67626b170abbb29574329b51980b432e008a9ee24e703f1ed78835`

## 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 2026-10-22.

- **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**: 32/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (SEE LICENSE IN LICENSE.md) 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).
  - Tool/resource definitions use about 1066 tokens (~76/item across 14 items; 14 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 86/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 59% 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 14 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 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: 2 categories.** Categories scored 0 because we could not verify them: 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 Rootz Archive MCP server?

Rootz Archive 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, e1c68f29ea67626b170abbb29574329b51980b432e008a9ee24e703f1ed78835; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/rootz-global/rootz-archive/releases/download/v0.7.5/rootz-archive-0.7.5.mcpb`
- SHA-256: `e1c68f29ea67626b170abbb29574329b51980b432e008a9ee24e703f1ed78835`

### Verify on macOS / Linux

```bash
echo "e1c68f29ea67626b170abbb29574329b51980b432e008a9ee24e703f1ed78835  rootz-archive-0.7.5.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\rootz-archive-0.7.5.mcpb).Hash -eq "e1c68f29ea67626b170abbb29574329b51980b432e008a9ee24e703f1ed78835"
```

## 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.

### 2026-10-14 (score 35, +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 improvement] Maintenance: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Tool coverage: 59
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: good

### 2026-10-13 (score 5, 0)

- [functional regression] Security disclosure: unverified → fail

### 2026-10-12 (score 5)

First indexed and scored.

## MCP tools (14)

### `search_conversations` (~95 tokens)

[Rootz Archive · this computer] Ranked full-text search across your archived AI conversations and their summaries. Local and offline. Words are stemmed and ANDed; use "quotes" for an exact phrase.

Input parameters:

- `limit` (number): Max results (default 10)
- `projectSlug` (string)
- `query` (string, required): Words or "a phrase" to search for
- `role` (string)

### `next_unsummarised` (~84 tokens)

[Rootz Archive · this computer] Sessions that have no summary yet, longest first. Use it only when the user asks you to summarise past sessions; summarising is the user's choice, never on your own initiative.

Input parameters:

- `limit` (number): How many (default 5)
- `model` (string): Only sessions not yet summarised by THIS model

### `add_summary` (~149 tokens)

[Rootz Archive · this computer] Store a summary you wrote of one session, at the user's request, labelled with your model name. It is indexed for search and never replaces the original transcript. Write it for a future reader: what was decided, what was produced, what was left open.

Input parameters:

- `model` (string, required): Your model name and version, e.g. "claude-opus-5-5"
- `sessionId` (string): Session ID
- `sessionNumber` (number): Session number from list_past_sessions output
- `sourceMessages` (number): How many messages you actually read
- `summary` (string, required): The summary text (at least 40 characters)

### `list_past_sessions` (~74 tokens)

[Rootz Archive · this computer] List past sessions, most recent first. Filter by topic text, project, or sessions with errors.

Input parameters:

- `hasErrors` (boolean)
- `limit` (number): Max sessions (default 10)
- `projectSlug` (string)
- `query` (string)

### `get_session_context` (~60 tokens)

[Rootz Archive · this computer] Summary of one session: files, tools, topics, git state, opening messages.

Input parameters:

- `sessionId` (string): Session ID
- `sessionNumber` (number): Session number from list_past_sessions output

### `get_full_transcript` (~119 tokens)

[Rootz Archive · this computer] Transcript of one session, paginated. States where the text came from: the archived copy, the live source file, or parsed messages only.

Input parameters:

- `format` (string)
- `limit` (number): Max messages (or JSONL lines) (default 50)
- `offset` (number): Start message (or JSONL line) index (default 0)
- `sessionId` (string): Session ID
- `sessionNumber` (number): Session number from list_past_sessions output

### `get_project_context` (~46 tokens)

[Rootz Archive · this computer] Recent sessions for a project, to pick up where you left off.

Input parameters:

- `limit` (number)
- `projectSlug` (string, required)

### `list_projects` (~26 tokens)

[Rootz Archive · this computer] Projects in the local archive, with session counts.

### `recall_facts` (~73 tokens)

[Rootz Archive · this computer] Facts extracted from past sessions (uses, depends_on, implements, decision, pattern, bug, fix, preference). Regex-extracted: treat as leads, not records.

Input parameters:

- `factType` (string)
- `limit` (number)
- `subject` (string)

### `get_decisions` (~50 tokens)

[Rootz Archive · this computer] Decisions extracted from past sessions. Regex-extracted: verify against the transcript before relying on one.

Input parameters:

- `limit` (number)
- `subject` (string)

### `archive_status` (~51 tokens)

[Rootz Archive · this computer] Is Archive working? Plain-language health of capture on this computer: green / amber / red with the reason. Call it when the user asks whether their conversations are being kept.

### `share_session` (~116 tokens)

[Rootz Archive · this computer] Make a share of one conversation with a capture receipt, at the user's request: the exact conversation file, a receipt anyone can check at receipts.rootz.global/verify, and a readable copy, in a folder on this computer. Nothing is sent anywhere; tell the user the folder path and that the share contains the whole conversation, so they should read it before sending.

Input parameters:

- `sessionId` (string): Session ID
- `sessionNumber` (number): Session number from list_past_sessions output

### `get_archive_stats` (~42 tokens)

[Rootz Archive · this computer] What the archive holds, in plain words: what is kept as exact copies on this computer, and what is searchable now.

### `index_local_sessions` (~81 tokens)

[Rootz Archive · this computer] Capture: index Claude Code sessions from ~/.claude/projects into the local archive. Skips files unchanged since last run.

Input parameters:

- `forceReindex` (boolean)
- `limit` (number): Max files to index this run (default 50)
- `projectFilter` (string): Only project folders containing this text

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/global-rootz-archive/rootz-archive#diagnostics

## Score history

- 2026-10-22: 35
- 2026-10-21: 35
- 2026-10-20: 35
- 2026-10-19: 35
- 2026-10-18: 35
- 2026-10-17: 35
- 2026-10-16: 35
- 2026-10-15: 35
- 2026-10-14: 35
- 2026-10-13: 5
- 2026-10-12: 5

## Common questions

### What is the Rootz Archive MCP server?

Rootz Archive is an MCP server listed in the public MCP registry as global.rootz/archive. Search your local Claude Code archive. For continuous capture, use the Rootz Archive plugin. This page covers its MCPB bundle (https://github.com/rootz-global/rootz-archive/releases/download/v0.7.5/rootz-archive-0.7.5.mcpb).

### Is the Rootz Archive MCP server safe to use?

Rootz Archive scores 35 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 Rootz Archive MCP server expose?

Rootz Archive exposes 14 tools: search_conversations, next_unsummarised, add_summary, list_past_sessions, get_session_context, and 9 more. Their descriptions and schemas cost roughly 1,066 tokens of context every time the server is loaded.

## Links

- Repository: https://github.com/rootz-global/rootz-archive
- Website: https://archive.rootz.global/
- Changelog RSS feed: https://verifymcp.io/servers/global-rootz-archive/rootz-archive.xml
- Changelog JSON feed: https://verifymcp.io/servers/global-rootz-archive/rootz-archive.json
- HTML version of this page: https://verifymcp.io/servers/global-rootz-archive/rootz-archive