image-gen-server

Provides an MCP server (via fastmcp) that takes text prompts (intended for Cursor IDE integration) and calls an upstream image generation service (即梦AI) to generate images. It supports downloading/saving generated images to a specified folder (including configurable width/height and sampling strength) and generates multiple images per request.

Evaluated Mar 30, 2026 (22d ago)
Repo ↗ Ai Ml mcp image-generation cursor-integration python fastmcp local-server
⚙ Agent Friendliness
43
/ 100
Can an agent use this?
🔒 Security
36
/ 100
Is it safe for agents?
⚡ Reliability
29
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
70
Documentation
55
Error Messages
0
Auth Simplicity
25
Rate Limits
10

🔒 Security

TLS Enforcement
70
Auth Strength
35
Scope Granularity
20
Dep. Hygiene
50
Secret Handling
10

Security posture is partially dependent on upstream communication and how proxy/jimeng is implemented (not included here). The README instructs embedding a session_id (JIMENG_API_TOKEN) directly into server.py, which is risky for secret exposure and accidental commits/logging. Filesystem write location is configurable via save_folder, implying potential path/traversal risks if not validated. No rate-limit, audit logging, or operational hardening details are provided.

⚡ Reliability

Uptime/SLA
0
Version Stability
40
Breaking Changes
30
Error Recovery
45
AF Security Reliability

Best When

You want local, agent-driven image generation tightly integrated with Cursor via MCP and are comfortable running a local Python process that holds an upstream session token.

Avoid When

You need strict compliance controls, centralized auth management, or you cannot trust local execution/logging/outputs involving third-party session tokens and generated files.

Use Cases

  • Generate product or brand images from text prompts inside Cursor
  • Create website/banner imagery from textual descriptions
  • Automate image generation and local saving for quick iteration during development
  • Use an MCP-enabled agent workflow to request and retrieve image outputs

Not For

  • Production-grade deployments that require robust operational controls and documented SLAs
  • Use cases needing a public, stable REST/SDK API surface for external clients
  • Environments that cannot handle storing or supplying third-party API session tokens
  • High-security environments without hardening of token handling, filesystem access, and logging

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Static upstream session token (JIMENG_API_TOKEN) configured in server.py
OAuth: No Scopes: No

The README indicates the upstream credential is a session_id cookie value placed directly into server.py as JIMENG_API_TOKEN (with support for multiple tokens). No OAuth flow or per-scope auth is described.

Pricing

Free tier: No
Requires CC: No

Pricing is not described for this MCP server itself; it likely incurs upstream image-generation service costs based on 即梦AI usage.

Agent Metadata

Pagination
none
Idempotent
False
Retry Guidance
Not documented

Known Gotchas

  • Windows path/escaping issues are explicitly called out (slashes, path containing Chinese characters).
  • Cursor integration may show transient states (e.g., 'No tools found') if the server fails to start correctly.
  • The MCP server black window may remain running; the README notes the pop-up/terminal behavior is not resolved.

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for image-gen-server.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-03-30.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered