Mermaid MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HTTP_VERIFY | No | Verify SSL certificates (as needed) | |
| GITHUB_TOKEN | No | GitHub personal access token (recommended to avoid rate limits) | |
| PROJECT_ROOT | Yes | Local project root that the server is allowed to access (security boundary) | |
| KROKI_TIMEOUT | No | Kroki request timeout in seconds | 20 |
| KROKI_BASE_URL | Yes | The base URL for the Kroki API (e.g. https://kroki.io) | |
| MAX_FILE_CHARS | No | Max characters to read from a file (prevents huge reads) | 200000 |
| DIAGRAM_OUT_DIR | No | Where to save PNGs (must be inside PROJECT_ROOT) | diagrams |
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 |
|---|---|
| list_filesD | – |
| read_fileD | – |
| render_mermaidD | – |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| generate_mermaid_canonical | Strict unified prompt: generates Mermaid flowcharts using ONLY the canonical style mermaid://styles/blue-flowchart. Supports GitHub repositories, local projects, OR user-provided content. Always renders PNG via render_mermaid. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| blue_flowchart_style | Canonical blue Mermaid flowchart style |
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: list_files enumerates files, read_file retrieves content, and render_mermaid processes Mermaid diagrams. There is no overlap in functionality, making tool selection straightforward for an agent.
All tools follow a consistent verb_noun pattern with snake_case naming (list_files, read_file, render_mermaid). The naming is predictable and readable throughout the set.
With only 3 tools, the set feels minimal for a Mermaid server. While it covers basic operations (list, read, render), it might be too thin for advanced use cases like editing or managing diagrams, though it is reasonable for a lightweight server.
The tools provide core functionality for working with Mermaid files: listing, reading, and rendering. However, there are minor gaps such as no tools for creating, updating, or deleting files, which could limit agent workflows in more complex scenarios.