Font Design MCP

Overview Schema Source Related Servers Discussions Admin

render_text

Render text to PNG using HarfBuzz, supporting variable font axes, kerning, and size options.

Instructions

Compile the revision, shape with HarfBuzz and return FreeType PNGs. For variable fonts, location maps axis tags to values; omitted axes use defaults. Missing Unicode is reported. Optional same-conditions revision comparison.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "project_id": "<project_id>",
      "text": "<text>"
    },
    "name": "render_text"
  }
}

Input Schema

Name	Required	Default
`dark`	No
`kern`	No
`text`	Yes
`sizes`	No
`width`	No
`detail`	No	summary
`location`	No
`revision`	No
`image_mode`	No	inline
`project_id`	Yes
`compare_revision`	No

Output Schema

Name	Required	Description	Default
`ok`	Yes
`data`	No
`error`	No
`changed`	No
`summary`	Yes
`revision`	No
`warnings`	No
`project_id`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed21 schema fields changedv0.4.3Sep 9, 2026
- removedInput schema / properties / compare_revision / title
```
Removed value: -"Compare Revision"
```
- removedInput schema / properties / dark / title
```
Removed value: -"Dark"
```
- addedInput schema / properties / detail
```
Added value: +{
+  "default": "summary",
+  "enum": [
+    "summary",
+    "positions",
+    "full"
+  ],
+  "type": "string"
+}
```
- addedInput schema / properties / image_mode
```
Added value: +{
+  "default": "inline",
+  "enum": [
+    "inline",
+    "resource"
+  ],
+  "type": "string"
+}
```
- removedInput schema / properties / kern / title
```
Removed value: -"Kern"
```
- addedInput schema / properties / location
```
Added value: +{
+  "maxProperties": 4,
+  "patternProperties": {
+    "^[A-Za-z][A-Za-z0-9]{3}$": {
+      "maximum": 32767,
+      "minimum": -32768,
+      "type": "number"
+    }
+  },
+  "type": "object"
+}
```
- removedInput schema / properties / project_id / title
```
Removed value: -"Project Id"
```
- removedInput schema / properties / revision / title
```
Removed value: -"Revision"
```
- removedInput schema / properties / sizes / title
```
Removed value: -"Sizes"
```
- removedInput schema / properties / text / title
```
Removed value: -"Text"
```
- removedInput schema / properties / width / title
```
Removed value: -"Width"
```
- removedInput schema / title
```
Removed value: -"RenderText"
```
- removedOutput schema / properties / changed / title
```
Removed value: -"Changed"
```
- removedOutput schema / properties / data / title
```
Removed value: -"Data"
```
- removedOutput schema / properties / error / title
```
Removed value: -"Error"
```
- removedOutput schema / properties / ok / title
```
Removed value: -"Ok"
```
- removedOutput schema / properties / project_id / title
```
Removed value: -"Project Id"
```
- removedOutput schema / properties / revision / title
```
Removed value: -"Revision"
```
- removedOutput schema / properties / summary / title
```
Removed value: -"Summary"
```
- removedOutput schema / properties / warnings / title
```
Removed value: -"Warnings"
```
- removedOutput schema / title
```
Removed value: -"Result"
```
First observedv0.1.0Sep 8, 2026

TDQS

B3.4/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations are all false (readOnlyHint, destructiveHint, idempotentHint), providing no safety profile. The description adds some behavioral context: it compiles the revision, shapes with HarfBuzz, returns PNGs, reports missing Unicode, and supports optional comparison. However, it doesn't clarify side effects (e.g., whether compiling modifies state) or error behavior. Given the annotations are uninformative, the description partially compensates but leaves gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the primary action. It efficiently covers key behaviors without excess verbosity. The structure is clean, though it omits crucial parameter details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 11 parameters, no schema descriptions, and an output schema present, the description is far from complete. It fails to explain the meaning of most parameters, their defaults, or relationships. The description covers only a fraction of what an agent needs to correctly invoke the tool, especially given the absence of schema descriptions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain parameters. It only touches on location (axis tags and defaults) and implicitly on compare_revision (same-conditions comparison). The remaining nine parameters (dark, kern, sizes, width, detail, image_mode, revision, project_id, text) are not explained at all. This is a significant gap for an 11-parameter tool.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb (compile, shape, return) and resource (text rendering), and mentions key behaviors like variable font support and missing Unicode reporting. While it doesn't explicitly distinguish from render_glyph, the text-focused purpose is clear and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this tool is for rendering text (as opposed to render_glyph for single glyphs) but provides no explicit when-to-use or when-not-to-use guidance. It mentions an optional comparison feature but doesn't specify conditions for using it. No exclusions or alternatives are named.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.