INITE AI Visibility — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow-up value is specific to INITE local site checks and hosted answer-engine visibility audits: Do local probes remain separate from paid model observations and weighted visibility scores?

Reviewed Oct 5, 2026 · Documentation review; complete setup workflow not independently tested

Best fit

Audit how major AI assistants and crawler/identity signals perceive a website.

What we know

Local MCP for AI-visibility checks. Some crawler-policy/identity/page-signal checks run without an account; full multi-engine audits and score require sign-in.

Maintenance / activity evidence

@inite/visibility 1.1.2 published 2026-09-06T04:30:17.049Z

Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Mostly read/analyze website and answer-engine results.
Local token/sign-in for full audit.
Sensitive access: Website/business positioning, Audit prompts/results, Authentication token for full service

Read-oriented marketing audit; main risks are data sharing with answer engines and interpreting noisy sample-based scores.

Full authority, access and evidence limits are available in Review context and Access & risk.

All limitations / Review context

Do local probes remain separate from paid model observations and weighted visibility scores?

The bounded review of the publisher's documented INITE local site checks and hosted answer-engine visibility audits and release notices identified no disclosed material condition preventing an accurately scoped public tracking entry. The resource's operational permissions remain uncertainty; this assessment does not certify installation safety.

Read-oriented marketing audit; main risks are data sharing with answer engines and interpreting noisy sample-based scores.
Mostly read/analyze website and answer-engine results.
Local token/sign-in for full audit.
Website content and audit prompts/results are processed locally/remotely depending on check; full audit queries answer engines.
Sensitive access: Website/business positioning, Audit prompts/results, Authentication token for full service
Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited.
Documented tool authority and any remote data handling must be checked before installation or use.
Tool inventory, client matrix and permissions completeness were not requirements for this Radar tracking review.
full retention/privacy for audit runs
exact sign-in/token details from package
Full audit is probabilistic and sample-size dependent.
Some engines do not expose source URLs consistently.
Full audit/sign-in flows use remote services/models.
Exact auth/token storage and retention details need first-party package review.

Original activity observations

@inite/visibility 1.1.2 published 2026-09-06T04:30:17.049Z

Technical identity

npm/@inite/visibility

Exact implementation source: https://www.npmjs.com/package/@inite/visibility ↗
Reviewed resource type: MCP Server
Repository identity: inite-ai/inite-visibility
Package identity: npm:@inite/visibility

Evidence & Sources

Evidence basis: Recorded source evidence
Setup runtime verification: Not independently runtime-tested by MCP100 for this setup workflow.

Reviewed Oct 5, 2026 · Latest source observation Oct 8, 2026

Package registry metadata ↗
@inite/visibility
Recorded package identity, distribution or download evidence.
Evidence source ↗
inite.ai/en/methodology
Source material retained for this review.
Includes references whose attribution is not established.
Evidence source ↗
inite.ai/en/analyze
Source material retained for this review.
Includes references whose attribution is not established.
GitHub repository ↗
inite-ai/inite-visibility
Repository reference; implementation attribution is not established for every document.
Includes references whose attribution is not established.

Setup · Watchlist

Install & Agents

Publisher instructions.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Install / connect
Publisher instructions
OAuth PKCE browser flow stores credentials at ~/.config/inite/mcp.json, optional INITE_TOKEN; remote MCP possible.
oauth browser login · Publisher instructions
npx @inite/visibility login
stdio mcp server launch · Publisher instructions
npx @inite/visibility
Configure / authenticate
MCP100 setup guide
Register publisher npx stdio server. On first use the browser PKCE login creates token in ~/.config/inite/mcp.json; INITE_TOKEN may override it. `inite-visibility whoami` checks the local credential. Never equate deleting local file with provider-side revocation.
Check connection
Suggested check
`inite-visibility whoami` checks stored token; separately verify the MCP client can discover the tools, and use read-only check_ai_access.
Remove / uninstall / revoke
MCP100 setup guide
If you added this integration to Claude Code under the registration name `visibility`, run `claude mcp remove visibility` to unregister that client entry. In Claude Desktop, Cursor, VS Code or another host, delete/disable the corresponding named MCP registration in that host's settings and restart/reconnect. If you installed an npm package globally or operate a separate HTTP server, uninstall/stop it with its original deployment method. This does not delete user data or revoke service credentials.
MCP client unregister, stopping hosted processes, package uninstall, OAuth disconnect and token revocation are distinct actions.
A claude mcp remove command is only valid for Claude Code when the local registration actually has that name. Other MCP hosts require their own UI/config cleanup.
Separate credential guidance / limitations: Inite uses `npx @inite/visibility login`, stores token at ~/.config/inite/mcp.json and supports `whoami`. Local token deletion/logout must not be described as proven server-side OAuth revocation; precise revoke UI not established.
Remove client registration · Claude Code only · MCP100 composed guide
claude mcp remove visibility

Official Documentation & Sources

What it does

Local MCP for AI-visibility checks. Some crawler-policy/identity/page-signal checks run without an account; full multi-engine audits and score require sign-in.

Capability: Search & Web
Resource type: MCP Server
Industry: Media & Marketing
Best fit: Audit how major AI assistants and crawler/identity signals perceive a website.

Representative uses

Check crawler policy and identity files
Inspect page-level AI-readable signals
Run full AI visibility audit
Measure brand naming/citation across multiple answer engines

Limitations

Full audit is probabilistic and sample-size dependent.
Some engines do not expose source URLs consistently.
Full audit/sign-in flows use remote services/models.
Exact auth/token storage and retention details need first-party package review.

Reviewed access

Access & risk

Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.

Authentication: Local token/sign-in for full audit.
Permissions: Mostly read/analyze website and answer-engine results.
Data handling: Website content and audit prompts/results are processed locally/remotely depending on check; full audit queries answer engines.
Cost: freemium
Risk and cautions: Read-oriented marketing audit; main risks are data sharing with answer engines and interpreting noisy sample-based scores.

Access scope and cautions

Write actions: None in the reviewed inventory
Sensitive access: Website/business positioning Audit prompts/results Authentication token for full service
Risk level: moderate

FAQ

Based on reviewed evidence as of 2026-10-08. Watchlist tracking is not a recommendation or a security certification.

Which tasks are documented for this implementation?

The reviewed tasks include: Check crawler policy and identity files; Inspect page-level AI-readable signals; Run full AI visibility audit; Measure brand naming/citation across multiple answer engines.

What setup and authentication are documented?

Recorded installation/entrypoint step: npx -y @inite/visibility. Recorded transport: stdio. Recorded environment-variable notes: INITE_TOKEN_FILE (optional auth storage path); INITE_AUTH_URL (optional override). No configuration values are supplied here. Prerequisites: MCP client. These are the documented setup details, not a claim that installation or client compatibility was independently tested. Authentication: Keyless local checks; full audit signs in through INITE auth flow. A demo or keyless description is not independently verified read-only authority. Check the documented tool permissions rather than inferring authority from that label.

Can it modify data or perform write operations?

The reviewed inventory lists no write actions. An empty inventory alone does not establish read-only authority. Recorded permission boundary: Mostly read/analyze website and answer-engine results.

What data-handling boundary should I consider?

Website content and audit prompts/results are processed locally/remotely depending on check; full audit queries answer engines. Recorded sensitive-access context: Website/business positioning; Audit prompts/results; Authentication token for full service.

What limitations and risks should I check before use?

Read-oriented marketing audit; main risks are data sharing with answer engines and interpreting noisy sample-based scores. Full audit is probabilistic and sample-size dependent. Some engines do not expose source URLs consistently. Full audit/sign-in flows use remote services/models. Exact auth/token storage and retention details need first-party package review. Runtime behavior, dependencies and undisclosed vulnerabilities were not independently audited. Documented tool authority and any remote data handling must be checked before installation or use.