Parallel World
REMOTE · PW.MIGUREI.AI
Check which AI bots a site's robots.txt allows; read-only facts about Parallel World
Available components
Last scanned (4 hours ago)
Scores higher than 54% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Web Scraping
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. How we score → Why this is hard to score →
Endpoint Security63
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability64
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 855 tokens (~285/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management33
- Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
- Structured output schemas are declared (67% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 3 Nov 26 +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.
- 1 Nov 26 +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.
- 30 Oct 26 +1
- The server rewrote its instructions, which are the text every model session reads security
- Schema quality: 230 → 285 ▼ functional
- Tool coverage: 50% → 67% ▲ functional
- Schema quality: good → excellent functional
- New tool “verify_ai_bot” functional
- 28 Oct 26 −1
- The server rewrote its instructions, which are the text every model session reads security
- Tool “check_ai_bot_access” rewrote its description, which is the text the model reads security
- Schema quality: 184 → 230 ▼ functional
- 27 Oct 26 +1
- Stability: unverified → 0.03 ▲ functional
- 26 Oct 26 66
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://pw.migurei.ai/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=migurei.ai | CN=WE1,O=Google Trust Services,C=US | 16 Oct 2026 | 14 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | 4df8b3377aaf7f510e78d0e3380021fd |
| SANs: migurei.ai, pw.migurei.ai, *.pw.migurei.ai | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of pw.migurei.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | present | 1814, 3799 | 8, 8 | Verified |
| migurei.ai. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://pw.migurei.ai/mcp | Verified | 200 | |
| http (plaintext) | http://pw.migurei.ai/mcp | Inconclusive | 405 |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
check_ai_bot_access Check which AI bots a site allows ~251
Reads the public robots.txt of a website (one request to https://<host>/robots.txt, nothing else on the site) and says, for each AI crawler and AI agent of the migurei bot registry (training crawlers such as GPTBot and ClaudeBot, search bots, fetchers that act for a user, and others), whether that bot is allowed or disallowed for the path "/", which robots.txt rule decided it, and whether the file exists. Each bot also carries observed_on_pw: the counts our own lab site pw.migurei.ai recorded for that bot (published on https://pw.migurei.ai/ja/research/ai-bot-first-visits; the same for every domain, not about the domain asked, not a prediction). Input is a domain or URL; only public domain names are accepted (no IP addresses, no ports, no private hosts). Read-only; the domain is not stored. robots.txt is a request to bots, not access control, and a User-Agent is only a claim.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | yes | A public domain name or a URL, for example example.com or https://example.com/page. Only its host is used. |
| Name | Type | Req | Description |
|---|---|---|---|
| bots | array | yes | – |
| domain | string | yes | – |
| learn_more | string | yes | – |
| method | string | yes | – |
| registry_version | string | yes | – |
| robots_txt | object | yes | – |
| robots_url | string | yes | – |
| summary | object | yes | – |
No examples provided.
get_site_info Parallel World site information ~82
Returns the facts published on this website, in Japanese: service overview, plans, prices and payment terms, how the scanner behaves, how to contact us, and the operating company. Each fact comes with the URL of the page that shows it. Read-only; it returns nothing that is not on the pages.
| Name | Type | Req | Description |
|---|---|---|---|
| topic | string | yes | Which facts to return |
No output schema declared.
No examples provided.
verify_ai_bot Verify that an IP address is really the AI bot its User-Agent claims ~306
Given the IP address and the User-Agent string of a request (for example from a server log), says whether that IP is inside the IP ranges the bot's operator publishes. The User-Agent is matched against the migurei bot registry (registry/bots); the IP is matched, IPv4 and IPv6, against the operator's published feed snapshot bundled with the registry (the snapshot date and registry version are in the answer). Status: verified (IP is in the operator's published ranges), ip_not_in_feed (the User-Agent names a registered bot but the IP is not in its ranges), no_feed (registered bot, but its operator publishes no IP ranges, so it cannot be checked), unknown_ua (no registered bot matches). Needs no outside request. Only public internet addresses are accepted (private, loopback, link-local, CGNAT, multicast, documentation and reserved addresses are refused). Read-only; the IP address and User-Agent are not stored and not logged. "verified" only means the IP is in the operator's ranges; the snapshot goes stale between updates.
| Name | Type | Req | Description |
|---|---|---|---|
| ip | string | yes | One public IPv4 or IPv6 address, for example from the access log. |
| user_agent | string | yes | The User-Agent header of that request, for example "Mozilla/5.0 AppleWebKit/537.36 (KHTML, like Gecko; compatible; GPTBot/1.1; +https://openai.com/gptbot)". |
| Name | Type | Req | Description |
|---|---|---|---|
| bot | object|null | yes | – |
| feeds | array | yes | – |
| ip | string | yes | – |
| ip_version | integer | yes | – |
| limits | object | – | – |
| matched_feed | string|null | yes | – |
| meaning | object | – | – |
| method | string | – | – |
| privacy | object | – | – |
| registry_version | string | yes | – |
| snapshot_date | string | yes | – |
| status | string | yes | – |
No examples provided.
How do I install the Parallel World MCP server?
Parallel World is a hosted endpoint at https://pw.migurei.ai/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · pw.migurei.ai
claude mcp add --transport http ai-migurei-pw-parallel-world 'https://pw.migurei.ai/mcp'
What is the Parallel World MCP server?
Parallel World is an MCP server listed in the public MCP registry as ai.migurei.pw/parallel-world. Check which AI bots a site's robots.txt allows; read-only facts about Parallel World. This page covers its hosted endpoint (https://pw.migurei.ai/mcp).
Is the Parallel World MCP server safe to use?
Parallel World scores 69 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 Parallel World MCP server expose?
Parallel World exposes 3 tools: get_site_info, check_ai_bot_access, verify_ai_bot. Their descriptions and schemas cost roughly 639 tokens of context every time the server is loaded.
Does the Parallel World MCP server require authentication?
No. We connected to Parallel World without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Parallel World MCP server still maintained?
Parallel World is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.