TakeSix MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TAKESIX_NO_CREDIT | No | Set to 1 in the environment (for the MCP server: in the `env` of its configuration) to leave out the small "Made with TakeSix" link in the bottom right corner of the HTML files produced by the server. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
TakeSix turns an answer into a diagram: at most six blocks per screen, and any block opens into up to six more. Use it when the user asks to explain, map or summarize something with structure (a codebase, an architecture, a plan, a process, a document) and the answer would otherwise be long prose. Call guide once before writing your first diagram, then validate and show.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| prompts | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| guideA | The format and the rules that make a TakeSix diagram readable. Read it once before writing your first diagram in a conversation, then once more with the |
| validateA | Checks a TakeSix document against the format: at most 6 blocks per level, unique ids, links between existing blocks. Lists every problem with its JSON path; on success, one line about the shape of the diagram. |
| showA | Validates a TakeSix document and writes it as one self-contained HTML file (opens in any browser, no network). In apps that support MCP Apps the diagram also opens in the conversation. Returns the file path. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| diagram | Explain a subject as a TakeSix diagram instead of long text |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| TakeSix viewer | Interactive viewer for the diagram shown by `show` |
| format | Every field of a TakeSix document, the validation rules and how links are shown |
| schema | JSON Schema of the TakeSix format 1.0 |
TDQS
Scored across 3 tools
Each tool has a distinct role: guide retrieves format rules, validate checks a document, show renders it. The only soft overlap is that show also validates, so an agent might wonder whether to call validate before show, but the descriptions make the intended pipeline clear.
All three names are single, lowercase verbs (guide, validate, show) with no mixed styles or redundant prefixes. The convention is uniform and easy to predict.
Three tools map exactly to the three-stage workflow of reading rules, checking, and rendering. Nothing is padded and nothing feels missing for such a narrow, DSL-driven purpose.
The lifecycle of authoring a diagram (learn format, validate, output) is fully covered, including an HTML artifact. Minor gap: no way to list or re-open previously generated diagrams, though the returned file path partially mitigates this.