Gency MCP — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow-up value is specific to Gency OAuth-based product image generation: Do MCP OAuth and separate REST integration keys keep account identity and generation billing distinct?

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

Best fit

Create AI product imagery through the Gency service.

What we know

Gency AI product image generation - MCP server for Claude, Codex, Cursor, VS Code Exact operational authority remains unverified from first-party package documentation and must not be inferred. Source-derived feature labels are preliminary; obtain official runtime/tool evidence before applying uncertain fields.

Maintenance / activity evidence

@gency-ai/gency-mcp 0.6.0 published 2026-07-30T02:54:39.908Z

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

Verification gaps / watch-outs

Installation and comprehensive security have not been independently audited.
Permissions not yet verified. Complete write authority is not verified.
Authentication not yet verified.
Sensitive access: Product images, Creative prompts

Authority is not fully established. Do not treat unknown writes/auth as read-only or absent.

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

All limitations / Review context

Do MCP OAuth and separate REST integration keys keep account identity and generation billing distinct?

The bounded review of the publisher's documented Gency OAuth-based product image generation 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.

Authority is not fully established. Do not treat unknown writes/auth as read-only or absent.
Sensitive access: Product images, Creative prompts
Complete write authority is not verified.
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.
repositoryIdentity: no confirmed package-to-repository binding
authentication: exact official auth and credential handling
writeActions: exact exposed tool mutation authority
dataHandling: provider destinations, retention and egress
cost: plans, pay-per-call charges, and payment authorization details
transport and actual executable entry point
Generation costs, input image retention, publishing behavior and exact permissions unverified
Do not apply unverified auth, permissions, transport, lifecycle or write actions; preserve any better existing profile values.

Original activity observations

@gency-ai/gency-mcp 0.6.0 published 2026-07-30T02:54:39.908Z

Technical identity

npm/@gency-ai/gency-mcp

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

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 ↗
@gency-ai/gency-mcp
Recorded package identity, distribution or download evidence.
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 via `npx -y @gency-ai/gency-mcp login`, tokens in ~/.gency/tokens.json; publisher logout: `npx -y @gency-ai/gency-mcp logout`. No API-key authentication.
publisher documented install or connect · Publisher instructions
npx -y @gency-ai/gency-mcp login
publisher documented install or connect · Claude Code only · Publisher instructions
claude mcp add gency -- npx -y @gency-ai/gency-mcp
Configure / authenticate
MCP100 setup guide
Publisher login is required before server use: npx -y @gency-ai/gency-mcp login; complete OAuth2 PKCE in browser. MCP does not use Gency REST API key.
Check connection
Suggested check
After OAuth login, inspect MCP tools and call the publisher auth_status tool (read-only), not a paid image generation.
Remove / uninstall / revoke
MCP100 setup guide
After completing `npx -y @gency-ai/gency-mcp login` and checking read-only auth_status, use `claude mcp remove gency` only when registered under `gency`. Then run publisher `npx -y @gency-ai/gency-mcp logout` to remove local OAuth tokens. Logging out does not prove remote grant revocation.
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: Gency MCP supports OAuth only; `npx -y @gency-ai/gency-mcp logout` removes ~/.gency/tokens.json. This is not a proven remote OAuth grant revocation. REST developer API keys are separate, not for this MCP.
Local session logout · separate from client removal / provider revocation · Publisher instructions
npx -y @gency-ai/gency-mcp logout

Official Documentation & Sources

What it does

Gency AI product image generation - MCP server for Claude, Codex, Cursor, VS Code Exact operational authority remains unverified from first-party package documentation and must not be inferred. Source-derived feature labels are preliminary; obtain official runtime/tool evidence before applying uncertain fields.

Capability: Design & Creative
Resource type: MCP Server
Industry: Retail & E-commerce, Media & Marketing
Best fit: Create AI product imagery through the Gency service.

Representative uses

Generate product image assets
Prepare ecommerce visuals

Limitations

Generation costs, input image retention, publishing behavior and exact permissions unverified
Do not apply unverified auth, permissions, transport, lifecycle or write actions; preserve any better existing profile values.

Reviewed access

Access & risk

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

Authentication: Not documented in the reviewed sources
Permissions: Not documented in the reviewed sources
Data handling: Not documented in the reviewed sources
Cost: Not documented in the reviewed sources
Risk and cautions: Authority is not fully established. Do not treat unknown writes/auth as read-only or absent.

Access scope and cautions

Write actions: Not verified
Sensitive access: Product images Creative prompts

The reviewed evidence does not establish the complete write authority of this MCP. Consult the unresolved evidence before granting write access.

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 available discovery description lists: Generate product image assets; Prepare ecommerce visuals. These descriptions do not establish a fully verified tool inventory.

Can it modify data or perform write operations?

Not verified. The available evidence does not establish the complete write authority.

What data-handling boundary should I consider?

Recorded sensitive-access context: Product images; Creative prompts.

What limitations and risks should I check before use?

Authority is not fully established. Do not treat unknown writes/auth as read-only or absent. Generation costs, input image retention, publishing behavior and exact permissions unverified. 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.