# AI Answer Guard — Source Integrity & Action Preflight (mcpb · nakagawa-original-router-1.2.0.mcpb)

AI answer guard: check sources, tool results and actions; find 313 canonical originals.

- Trust score: 40/100 (low)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- mcpb · `nakagawa-original-router-1.2.0.mcpb`: 40/100 (this document), [markdown](https://verifymcp.io/servers/nakagawa-master-nakagawa-original-router/nakagawa-original-router.md), [page](https://verifymcp.io/servers/nakagawa-master-nakagawa-original-router/nakagawa-original-router)

## Channel facts

- Registry: `mcpb`
- Package: `https://github.com/Nakagawa-master/nakagawa-theory-archive/releases/download/mcp-router-v1.2.0/nakagawa-original-router-1.2.0.mcpb`
- Transport: `stdio`
- SHA-256: `c7b30d7b059b7b44065edab4882ed0ee1d87dddbf4f5a19ecbc6790188e6ece7`

## 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 2026-11-05.

- **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**: 35/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - License check failed: the license (CC-BY-NC-ND-4.0) isn't a recognized OSI-approved license.
  - Actively maintained (last published 8 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 640 tokens (~71/item across 9 items; 9 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 47/100
  - Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 70/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 9% 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 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 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).

**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 AI Answer Guard — Source Integrity & Action Preflight MCP server?

AI Answer Guard — Source Integrity & Action Preflight 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, c7b30d7b059b7b44065edab4882ed0ee1d87dddbf4f5a19ecbc6790188e6ece7; the commands to do that are on this page. If it does not match, do not open it.

- Download bundle: `https://github.com/Nakagawa-master/nakagawa-theory-archive/releases/download/mcp-router-v1.2.0/nakagawa-original-router-1.2.0.mcpb`
- SHA-256: `c7b30d7b059b7b44065edab4882ed0ee1d87dddbf4f5a19ecbc6790188e6ece7`

### Verify on macOS / Linux

```bash
echo "c7b30d7b059b7b44065edab4882ed0ee1d87dddbf4f5a19ecbc6790188e6ece7  nakagawa-original-router-1.2.0.mcpb" | shasum -a 256 -c
```

### Verify on Windows (PowerShell)

```powershell
(Get-FileHash -Algorithm SHA256 .\nakagawa-original-router-1.2.0.mcpb).Hash -eq "c7b30d7b059b7b44065edab4882ed0ee1d87dddbf4f5a19ecbc6790188e6ece7"
```

## 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 40, +1)

No change was recorded against any check on this day. Stability & Change Management went from 40 to 43. That category is still filling its 30-day observation window: 12 days of observed history at the previous scan, 13 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 39, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-31 (score 38, +1)

- [functional improvement] Security disclosure: fail → pass

### 2026-10-30 (score 37, +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.

### 2026-10-28 (score 36, +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.

### 2026-10-27 (score 35, −2)

- [functional regression] Tool coverage: 50% → 9%
- [functional regression] Schema quality: 236 → 640
- [functional] Schema quality: good → fair

### 2026-10-25 (score 37, +1)

- [security regression] Stability: 0.07 → unverified

### 2026-10-23 (score 36, +1)

No change was recorded against any check on this day. Stability & Change Management went from 0 to 3. That category is still filling its 30-day observation window: 0 days of observed history at the previous scan, 1 at this one. The score rises as the window fills, whether or not the server changes.

## MCP tools (9)

### `find_nakagawa_original_for_problem` (~99 tokens)

Given a real human/AI problem in Japanese, English or Chinese, find potentially relevant public Nakagawa Master canonical original URLs, fit caveats and separate independent receiver evidence. Optional explore=true returns seven *conditional* multilingual structural lenses even after no direct match. A cue is not proof of fit or original adoption.

Input parameters:

- `explore` (boolean): Return seven optional structural hypotheses even when direct no_fit.
- `question` (string, required)

### `list_nakagawa_problem_routes` (~33 tokens)

List supported problem-route IDs and the canonical originals they point to, including explicit nonfit/no-original routes.

### `resolve_nakagawa_public_name` (~56 tokens)

Return official homepage-grounded public author name, published pen name, SNS/external bylines and the explicit NULL unpublished full kanji personal-name field. NEVER guess the name in kanji or join unrelated MasterJP people.

### `preflight_ai_answer_and_action` (~101 tokens)

EVERYDAY FIRST USE: before answering with citations, reporting tool success, or executing an action, check declared independent-source evidence, tool receipts, permissions and irreversible effects in ONE local preflight. Return exact practical repairs and conditions, not merely a theory search or a blanket prohibition. Needs supplied observations; cannot independently verify sources or permissions.

Input parameters:

- `claims` (array)
- `planned_actions` (array)
- `tool_results` (array)

### `audit_citation_independence` (~70 tokens)

EVERYDAY FACT-CHECK: detect duplicate upstream evidence roots and known refuting observations before repeating an AI answer's claim of independent confirmation. Use even if the user knows nothing about Nakagawa theories. Source provenance is caller supplied; no claim of factual verification.

Input parameters:

- `claims` (array, required)

### `overview_nakagawa_whole_structure` (~44 tokens)

One integrated system: ALL 313 published derivative-to-Parent original links, system entrance, epistemic integrity, audit, future effects, and everyday applications.

### `list_all_313_derivative_parent_links` (~60 tokens)

Address every one of 313 public derivative Parent originals, with IDs and theme; 24 is only an initial question fast lane. Paginate or list all.

Input parameters:

- `limit` (integer)
- `offset` (integer)

### `inspect_nakagawa_derivative_connections` (~42 tokens)

Get original Parent for one OD ID and navigate exact shared-Parent and related published themes within the same system.

Input parameters:

- `id` (string, required)

### `find_sources_in_whole_structure` (~53 tokens)

Find relevant candidates across 313 official derivative titles; original text and fit must be assessed separately. Full inventory is also available without query.

Input parameters:

- `limit` (integer)
- `question` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/nakagawa-master-nakagawa-original-router/nakagawa-original-router#diagnostics

## Score history

- 2026-11-05: 40
- 2026-11-04: 40
- 2026-11-03: 39
- 2026-11-02: 39
- 2026-11-01: 38
- 2026-10-31: 38
- 2026-10-30: 37
- 2026-10-29: 36
- 2026-10-28: 36
- 2026-10-27: 35
- 2026-10-26: 37
- 2026-10-25: 37
- 2026-10-24: 36
- 2026-10-23: 36
- 2026-10-22: 35

## Common questions

### What is the AI Answer Guard — Source Integrity & Action Preflight MCP server?

AI Answer Guard — Source Integrity & Action Preflight is an MCP server listed in the public MCP registry as io.github.Nakagawa-master/nakagawa-original-router. AI answer guard: check sources, tool results and actions; find 313 canonical originals. This page covers its MCPB bundle (https://github.com/Nakagawa-master/nakagawa-theory-archive/releases/download/mcp-router-v1.2.0/nakagawa-original-router…).

### Is the AI Answer Guard — Source Integrity & Action Preflight MCP server safe to use?

AI Answer Guard — Source Integrity & Action Preflight scores 40 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 AI Answer Guard — Source Integrity & Action Preflight MCP server expose?

AI Answer Guard — Source Integrity & Action Preflight exposes 9 tools: find_nakagawa_original_for_problem, list_nakagawa_problem_routes, resolve_nakagawa_public_name, preflight_ai_answer_and_action, audit_citation_independence, and 4 more. Their descriptions and schemas cost roughly 558 tokens of context every time the server is loaded.

### What licence is the AI Answer Guard — Source Integrity & Action Preflight MCP server under?

AI Answer Guard — Source Integrity & Action Preflight declares the CC-BY-NC-ND-4.0 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

- Repository: https://github.com/Nakagawa-master/nakagawa-theory-archive
- Changelog RSS feed: https://verifymcp.io/servers/nakagawa-master-nakagawa-original-router/nakagawa-original-router.xml
- Changelog JSON feed: https://verifymcp.io/servers/nakagawa-master-nakagawa-original-router/nakagawa-original-router.json
- HTML version of this page: https://verifymcp.io/servers/nakagawa-master-nakagawa-original-router/nakagawa-original-router