Cloudflare Image MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CLOUDFLARE_ENV_FILE | No | Path to an alternative env file containing CLOUDFLARE_ACCOUNT_ID and CLOUDFLARE_API_TOKEN. | |
| CLOUDFLARE_API_TOKEN | No | Cloudflare API token with Workers AI permissions, required in the credentials env file (default: ~/.config/opencode/secrets/cloudflare.env). | |
| CLOUDFLARE_ACCOUNT_ID | No | Cloudflare account ID, required in the credentials env file (default: ~/.config/opencode/secrets/cloudflare.env). | |
| CLOUDFLARE_IMAGE_MCP_ROOT | No | If defined, overrides Path.cwd() as the root directory for output paths and restricts writes to that root. | |
| CLOUDFLARE_CREDENTIALS_PATH | No | Path to an alternative credentials file containing CLOUDFLARE_ACCOUNT_ID and CLOUDFLARE_API_TOKEN. |
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": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageC | Generate an image with Cloudflare Workers AI and save it as a PNG file. |
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 1 tool
With only one tool in the set, there is nothing to confuse it with; its purpose (generate an image and save as PNG) is unambiguous.
The single name follows a clear verb_noun convention (generate_image), which is predictable and readable even without siblings.
A one-tool surface is thin: while image generation is the stated purpose, there is no companion operation such as listing models, retrieving the saved file path, or deleting images, so the set feels borderline under-scoped.
Generation is covered, but the lifecycle dead-ends after creation — an agent cannot list previously generated images, fetch a specific result by ID, or clean up files, which are natural follow-on operations for this domain.