MCP server for advanced web search using Tavily
Nothing to run from here
AI Answer Guard — Source Integrity & Action Preflight is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
trust score
10
tools declared
local
runs on your machine
87
downloads
What it does
AI answer guard: check sources, tool results and actions; find 313 canonical originals.
Quickstart
Install it the way its author documents:
1. Download nakagawa-original-router-1.2.0.mcpb and open it in Claude Desktop or another client that installs MCP bundles (.mcpb)
2. Its sha256 is c7b30d7b059b7b44065edab4882ed0ee1d87dddbf4f5a19ecbc6790188e6ece7
The full guide: https://github.com/Nakagawa-master/nakagawa-theory-archive/releases/download/mcp-router-v1.2.0/nakagawa-original-router-1.2.0.mcpb
Publishernot claimed
NMAll 1 server
Nakagawa-master1 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts AI Answer Guard — Source Integrity & Action Preflight as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Install it the way its author documents:
1. Download nakagawa-original-router-1.2.0.mcpb and open it in Claude Desktop or another client that installs MCP bundles (.mcpb)
2. Its sha256 is c7b30d7b059b7b44065edab4882ed0ee1d87dddbf4f5a19ecbc6790188e6ece7
The full guide: https://github.com/Nakagawa-master/nakagawa-theory-archive/releases/download/mcp-router-v1.2.0/nakagawa-original-router-1.2.0.mcpb
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
List supported problem-route IDs and the canonical originals they point to, including explicit nonfit/no-original routes.
No parameter schema on file.
One integrated system: ALL 313 published derivative-to-Parent original links, system entrance, epistemic integrity, audit, future effects, and everyday applications.
No parameter schema on file.
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.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| offset | integer | no | — |
| limit | integer | no | — |
Get original Parent for one OD ID and navigate exact shared-Parent and related published themes within the same system.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Find relevant candidates across 313 official derivative titles; original text and fit must be assessed separately. Full inventory is also available without query.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| question | string | yes | — |
| limit | integer | no | — |
Everyday answer and action preflight plus all 313 published original Parent links in one local install.
No parameter schema on file.
Find relevant originals with optional conditional seven-lens exploration.
No parameter schema on file.
Return verified public author/pen name without inferring unpublished kanji.
No parameter schema on file.
Everyday answer, evidence, action and tool-receipt preflight.
No parameter schema on file.
Catch fake independent confirmation across repeated roots.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source is public; its licence metadata reads NOASSERTION rather than naming a licence
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install AI Answer Guard — Source Integrity & Action Preflight or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 93 / 100
Release 1.2.0 · scanned 28 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings9 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest2dc22d3bf39daa3966da07121ef3ae7218597d0cc75600bd6ac9471b4c82a657
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfacenot available
Implementation sourceread
Package metadataread
Live transportnot available
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
can execute shell commands or code
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest2dc22d3bf39daa39
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
It installs from its repository rather than from a versioned package, so the command cannot be pinned to a release. The history below is for reading; the current release on file is 1.2.0.
1.2.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish AI Answer Guard — Source Integrity & Action Preflight can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.