gemini-diagram-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HOST | No | HTTP server bind host | 0.0.0.0 |
| PORT | No | HTTP server bind port | 3000 |
| OUTPUT_DIR | No | Output directory for generated images | ./data/out |
| OIDC_ISSUER | No | OIDC issuer URL (required for oidc mode) | |
| ALLOWED_HOSTS | No | Comma-separated allowed host headers | |
| INLINE_IMAGES | No | Include base64 image data in tool responses | 0 |
| MCP_AUTH_MODE | No | Auth mode: token, oidc, none | token |
| OIDC_AUDIENCE | No | Expected token audience(s) | |
| OIDC_JWKS_URI | No | Override JWKS URI (skips discovery) | |
| GOOGLE_API_KEY | No | Backward-compatible alias | |
| MCP_AUTH_TOKEN | No | Static bearer token(s) | |
| MCP_AUTH_TOKENS | No | Comma-separated multiple tokens | |
| PUBLIC_BASE_URL | No | Base URL for download links | http://localhost:$PORT |
| MCP_MAX_SESSIONS | No | Maximum concurrent sessions | 100 |
| VERTEX_AI_API_KEY | No | Vertex AI API key (preferred) | |
| GOOGLE_CLOUD_API_KEY | No | Backward-compatible alias | |
| MCP_ALLOW_QUERY_TOKEN | No | Allow ?token=... query param auth | 1 (token mode) |
| VERTEX_AI_IMAGE_MODEL | No | Model for image generation | gemini-3-pro-image-preview |
| MCP_SESSION_TIMEOUT_MIN | No | Session timeout in minutes | 30 |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageA | Generate a diagram, chart, or visualization using Gemini. Intelligently detects type from prompt and asks clarifying questions when uncertain. Supports: chart, comparison, flow, architecture, timeline, hierarchy, matrix, hero, visualization. |
| refine_imageA | Refine the last generated image with modifications |
| prepare_imageA | Get guidance before generating an image. Call this FIRST to understand supported parameters, get prompt recommendations, and receive a polished prompt. This avoids rejected generations and wasted API calls. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: prepare for guidance, generate for creation, and refine for modification. There is no overlap in functionality, making it easy for an agent to select the right tool.
All tool names follow the same verb_noun pattern with underscores: prepare_image, generate_image, refine_image. This consistent naming convention makes the tool set predictable and easy to navigate.
With only three tools, the server is well-scoped for its purpose of diagram generation. Each tool covers an essential step in the workflow without unnecessary bloat, and the count is appropriate for a focused utility.
The tool set covers the full generation lifecycle: prepare, generate, and refine. This provides a complete workflow for users, and there are no obvious missing operations that would cause agent failures.