image-gen-mcp
by ramzpat
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | Host or interface to bind to. Defaults to 127.0.0.1 locally; deployment sets 0.0.0.0. | |
| PORT | No | Port to listen on. Defaults to 8080 locally; deployment sets 8000. | |
| ALLOWED_EMAILS | No | Optional comma-separated allowlist to narrow the proxy's allowlist for image generation. | |
| GEMINI_API_KEY | Yes | Your Google AI Studio API key for the Gemini image model. | |
| IMAGE_MCP_MODEL | No | Default model to use, e.g. gemini-2.5-flash-image. | |
| IMAGE_MCP_TOKEN | No | Static bearer token for local token auth. Required when IMAGE_MCP_TRUST_PROXY_HEADERS is not set. | |
| IMAGE_MCP_GCS_BUCKET | No | Cloud Storage bucket used for storing images larger than IMAGE_MCP_INLINE_MAX_BYTES. Required for 2K/4K image sizes. | |
| IMAGE_MCP_MAX_PROMPT | No | Maximum number of characters allowed in an image generation prompt. | |
| IMAGE_MCP_RATE_PER_HOUR | No | Maximum number of image generation requests allowed per hour per instance. | |
| IMAGE_MCP_ALLOWED_MODELS | No | Comma-separated list of models that callers may select. | |
| IMAGE_MCP_MAX_CONCURRENCY | No | Maximum number of concurrent image generation requests per instance. | |
| IMAGE_MCP_INLINE_MAX_BYTES | No | Maximum image size in bytes returned inline before the image is uploaded to Cloud Storage. Default is 1500000 (1.5 MB). | |
| IMAGE_MCP_TRUST_PROXY_HEADERS | No | Set to 1 when running behind mcp-oauth-proxy. The server reads user identity from X-Auth-* headers instead of requiring its own token. Never enable on a routable port. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ramzpat/image-gen-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server