Gessa MCP Server — Watchlist

MCP100 Assessment

Watchlist / Tracking

Why we’re tracking it

Follow-up value is specific to Gessa stdio mirror of remote tools, resources and prompts: Do package and remote versions stay aligned without claiming local engine logic or authority?

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

Best fit

Generate game-ready 3D, texture and audio assets from agents through Gessa's hosted generation engine.

What we know

Thin stdio proxy for Gessa's remote MCP. It mirrors the authenticated remote tool/resource/prompt surface rather than running generation locally. Official workflow exposes capability discovery, quote-before-run and generation-job creation.

Maintenance / activity evidence

@gessa/mcp-server 1.1.0 published 2026-08-27T23:24:08.543Z

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.
Generation-job authority and account asset access. Writes: Create generation jobs; Consume account generation quota/credits.
Gessa API key.
Sensitive access: Game assets, Reference media, Prompts, API key

Can consume credits and upload proprietary assets; quote-before-run should be preserved.

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

All limitations / Review context

Do package and remote versions stay aligned without claiming local engine logic or authority?

The bounded review of the publisher's documented Gessa stdio mirror of remote tools, resources and prompts 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.

Can consume credits and upload proprietary assets; quote-before-run should be preserved.
Generation-job authority and account asset access.
Gessa API key.
Prompts/reference assets and generated content are processed remotely by Gessa.
Reviewed write actions: Create generation jobs; Consume account generation quota/credits
Sensitive access: Game assets, Reference media, Prompts, API key
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.
All engine logic is remote; local package is only a proxy.
Generation costs/limits depend on Gessa service.
Uploads/prompts/assets leave the local machine.
Live remote tool surface can change with MCP API version.

Original activity observations

@gessa/mcp-server 1.1.0 published 2026-08-27T23:24:08.543Z

Technical identity

npm/@gessa/mcp-server

Exact implementation source: https://www.npmjs.com/package/@gessa/mcp-server ↗
Reviewed resource type: Gateway
Package identity: npm:@gessa/mcp-server
Service endpoint: https://api.gessa.ai/mcp/rpc

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 ↗
@gessa/mcp-server
Recorded package identity, distribution or download evidence.
Includes references whose attribution is not established.
Evidence source ↗
gessa.ai/assets/for-agents/
Source material retained for this review.
Includes references whose attribution is not established.
Evidence source ↗
gessa.ai/developers/
Source material retained for this review.
Includes references whose attribution is not established.

Setup · Watchlist

Gateway setup

Publisher instructions.

Source evidence observed Oct 14, 2026.

Additional setup details required — see the specific gaps below.

Install / connect
Publisher instructions
GESSA_API_KEY required; GESSA_API_URL defaults https://api.gessa.ai; local stdio bridges hosted /mcp/rpc.
publisher documented install or connect · Publisher instructions
npx -y @gessa/mcp-server

Configure / authenticate

MCP100 setup guide

GESSA_API_KEY required by local stdio forwarding proxy; remote Gessa API actually serves tools at /mcp/rpc.

claude desktop or cursor mcpServers json · MCP100 composed guide

{
  "mcpServers": {
    "gessa": {
      "args": [
        "-y",
        "@gessa/mcp-server"
      ],
      "command": "npx",
      "env": {
        "GESSA_API_KEY": "YOUR_GESSA_API_KEY",
        "GESSA_API_URL": "https://api.gessa.ai"
      }
    }
  }
}

Check connection
Suggested check
With GESSA_API_KEY configured, verify remote proxy exposes the published tool/resource list. Successful process startup alone does not prove account authentication.
Remove / uninstall / revoke
MCP100 setup guide
If you added this integration to Claude Code under the registration name `gessa`, run `claude mcp remove gessa` 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: `GESSA_API_KEY` authenticates the published stdio proxy to /mcp/rpc. Package README gives no issue/revoke endpoint; no safe exact revocation command confirmed. Remove client entry separately and manage key with Gessa issuer.
Remove client registration · Claude Code only · MCP100 composed guide
claude mcp remove gessa

Official Documentation & Sources

What it does

Thin stdio proxy for Gessa's remote MCP. It mirrors the authenticated remote tool/resource/prompt surface rather than running generation locally. Official workflow exposes capability discovery, quote-before-run and generation-job creation.

Capability: Design & Creative
Resource type: Gateway
Industry: Sports & Entertainment
Best fit: Generate game-ready 3D, texture and audio assets from agents through Gessa's hosted generation engine.

Representative uses

Discover available asset-generation pipelines
Quote generation job before starting
Generate 3D models/textures/audio
Poll/retrieve generated game assets

Limitations

All engine logic is remote; local package is only a proxy.
Generation costs/limits depend on Gessa service.
Uploads/prompts/assets leave the local machine.
Live remote tool surface can change with MCP API version.

Reviewed access

Access & risk

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

Authentication: Gessa API key.
Permissions: Generation-job authority and account asset access.
Data handling: Prompts/reference assets and generated content are processed remotely by Gessa.
Cost: usage_based
Risk and cautions: Can consume credits and upload proprietary assets; quote-before-run should be preserved.

Access scope and cautions

Write actions: Create generation jobs Consume account generation quota/credits
Sensitive access: Game assets Reference media Prompts API key
Risk level: high

FAQ

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

Which implementation does this page cover?

Thin stdio proxy for Gessa's remote MCP. It mirrors the authenticated remote tool/resource/prompt surface rather than running generation locally. Official workflow exposes capability discovery, quote-before-run and generation-job creation.

What setup and authentication are documented?

Recorded installation/entrypoint step: npx -y @gessa/mcp-server. Recorded endpoint: https://api.gessa.ai/mcp/rpc. Recorded transport: stdio, streamable_http. Recorded environment-variable notes: GESSA_API_KEY; GESSA_API_URL (optional, default https://api.gessa.ai). 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: Bearer Gessa API key; anonymous onboarding endpoint can mint a key.

Can it modify data or perform write operations?

Documented write actions include: Create generation jobs; Consume account generation quota/credits. Recorded permission boundary: Generation-job authority and account asset access.

What data-handling boundary should I consider?

Prompts/reference assets and generated content are processed remotely by Gessa. Recorded sensitive-access context: Game assets; Reference media; Prompts; API key.

What limitations and risks should I check before use?

Can consume credits and upload proprietary assets; quote-before-run should be preserved. All engine logic is remote; local package is only a proxy. Generation costs/limits depend on Gessa service. Uploads/prompts/assets leave the local machine. Live remote tool surface can change with MCP API version. 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.

What cost model is recorded?

The reviewed cost model is usage based. This classification does not establish current prices, quotas or the cost of every downstream operation. Check the applicable service terms before authorizing paid actions.

Why we’re tracking it

Best fit

What we know

Maintenance / activity evidence

Verification gaps / watch-outs

Original activity observations

Evidence & Sources

Gateway setup

Install / connect

Configure / authenticate

Check connection

Remove / uninstall / revoke

Official Documentation & Sources

What it does

Representative uses

Limitations

Access & risk

Access scope and cautions

FAQ