Required to run the fountain pen ink MCP server, supporting ink search, color matching, and recommendation features.
Used for installation, building, and running the fountain pen ink MCP server and its dependencies.
Used for type definitions and implementation of the fountain pen ink MCP server's features.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Fountain Pen Ink MCP Server find inks similar to a deep navy blue"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
A Model Context Protocol (MCP) server that provides LLMs with specialized knowledge about fountain pen inks, enabling intelligent ink search, color matching, and recommendations. Read my article about creating this server.
This MCP server provides the following tools for LLMs:
search_inks_by_name: Fuzzy search for inks by name or manufacturer
search_inks_by_color: Find inks similar to any given color using RGB matching
get_inks_by_maker: List all inks from a specific manufacturer
get_ink_details: Get comprehensive information about a specific ink
analyze_color: Analyze any color and find the closest matching inks
get_color_palette: Generate sophisticated themed ink palettes with color theory support
13 predefined themes (warm, cool, earth, ocean, autumn, spring, summer, winter, pastel, vibrant, monochrome, sunset, forest)
Color harmony generation (complementary, analogous, triadic, split-complementary)
Custom hex color palettes
Related MCP server: MCP Color Converter
git clone https://github.com/ewilderj/inks-mcp.git
cd inks-mcp
npm install
npm run build
# List tools and run a sample query
npm run tools:list
npm run client -- --tool search_inks_by_name --args '{"query":"sailor blue","max_results":5}'Node.js 18 or higher
npm or yarn
# Clone the project
git clone https://github.com/ewilderj/inks-mcp.git
cd inks-mcp
# Install dependencies
npm install
# Build the project
npm run build# Run once
npm start
# Development mode with auto-rebuild
npm run dev
# Watch mode for development
npm run watchAdd this server to your MCP client configuration:
{
"servers": {
"fountain-pen-ink-server": {
"type": "stdio",
"command": "node",
"args": ["<path-to-project>/dist/index.js"]
}
}
}A small script is included to exercise any tool from the command line:
# List tools
npm run tools:list
# Call a tool with inline JSON args
npm run client -- --tool search_inks_by_name --args '{"query":"sailor blue","max_results":5}'
# Call with arguments from a file
npm run client -- --tool get_color_palette --args-file examples/palette.complementary.json
# Change output mode (auto | content | raw)
npm run client -- --tool search_inks_by_color --args '{"color":"#2E5984"}' --output contentScript options:
--list List available tools
--tool <name> Tool name to call
--args '<json>' Inline JSON arguments
--args-file <path> JSON file with arguments
--server <path> Path to compiled server (default: dist/index.js)
--timeout <ms> Timeout in milliseconds (default: 10000)
--output <mode> Output mode: auto | content | raw (default: auto)
Search for fountain pen inks using fuzzy text matching.
Parameters: query (string), max_results (number, optional)
Example input:
{ "query": "sailor blue", "max_results": 10 }Example prompt:
Find inks matching "sailor blue"; limit to 10 results.
Find inks similar to a given color using RGB color space matching.
Parameters: color (hex string), max_results (number, optional)
Example input:
{ "color": "#2E5984", "max_results": 15 }Example prompt:
Find inks similar to color #2E5984; up to 15 results.
Get complete information about a specific ink.
Parameters: ink_id (string)
Example input:
{ "ink_id": "diamine-oxblood" }Example prompt:
Show info for "diamine-oxblood".
List all inks from a specific manufacturer.
Parameters: maker (string), max_results (number, optional)
Example input:
{ "maker": "diamine", "max_results": 25 }Example prompt:
List Diamine inks; limit 25.
Analyze a color and provide fountain pen ink context.
Parameters: color (hex string), max_results (number, optional)
Example input:
{ "color": "#2E5984", "max_results": 7 }Example prompt:
Analyze #2E5984 and show the top 7 closest inks.
Generate a themed or harmony-based palette of fountain pen inks with color theory support.
Parameters: theme (string), palette_size (number, optional), harmony (string, optional)
Supported Themes:
Classic: warm, cool, earth, ocean, autumn, spring
Seasonal: summer, winter
Mood: pastel, vibrant, monochrome
Atmospheric: sunset, forest
Harmony Rules: complementary, analogous, triadic, split-complementary
Example input:
{ "theme": "sunset", "palette_size": 4 }Example prompt:
Generate a 4‑ink palette for the "sunset" theme.
For more examples, see examples/USAGE.md.
The server uses two main data files:
ink-colors.json: Contains RGB color values and basic ink information
search.json: Contains metadata including manufacturers, scan dates, and searchable names
All ink data links back to Wilder Writes for detailed information and images.
inks-mcp/
├── src/
│ ├── index.ts # Main MCP server implementation
│ ├── types.ts # TypeScript type definitions
│ └── utils.ts # Utility functions for color matching
├── data/
│ ├── ink-colors.json # RGB color data
│ └── search.json # Search metadata
├── dist/ # Compiled JavaScript (generated)npm run build: Compile TypeScript to JavaScript
npm run start: Run the compiled server
npm run dev: Build and run in one command
npm run watch: Watch for changes and rebuild automatically
npm run client: Run the generic CLI client
npm run tools:list: List available tools via the CLI client
Run the comprehensive test suite to validate all functionality:
npm test
# Run individual test categories
cd test
node test-enhanced-palette.js # Palette generation features
node test-mcp-palette.js # MCP protocol compliance
node test-schema.js # Tool schema validation
node test-harmony-direct.js # Color harmony algorithmsFor manual, ad‑hoc testing, use the CLI client documented above.
The test suite covers:
✅ 13 predefined themes + 4 harmony rules
✅ Custom color palette generation
✅ MCP protocol compliance
✅ Error handling and validation
✅ Color space conversions (BGR→RGB, RGB↔HSL)
The server uses Euclidean distance in RGB color space to find similar inks:
distance = √[(r₁-r₂)² + (g₁-g₂)² + (b₁-b₂)²]Future improvements may include:
LAB color space for better perceptual accuracy
Weighted color components for fountain pen ink characteristics
Semantic color descriptions
Fork the repository
Create a feature branch
Make your changes
Add tests if applicable
Submit a pull request
This project is licensed under the GNU General Public License v3.0 (GPL-3.0). See the LICENSE file for details.
Wilder Writes - Source of ink data and detailed ink information
Model Context Protocol - MCP documentation and examples
Analyze a color and provide ink knowledge context
| Name | Required | Description | Default |
|---|---|---|---|
| color | Yes | Hex color code (e.g., "#FF5733") | |
| max_results | No | Maximum number of closest inks to return (default: 5) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions 'provide ink knowledge context', but does not explain what this includes (e.g., types of information, format, limitations like rate limits or authentication needs). For a tool with no annotations, this leaves significant gaps in understanding its behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's function. It is appropriately sized and front-loaded with the core purpose, though it could be more structured with additional details. No wasted words, but brevity limits completeness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool has no annotations and no output schema, the description is incomplete. It lacks details on what 'ink knowledge context' means, the format of results, or how it differs from sibling tools. For a tool with 2 parameters and no structured output information, this leaves the agent with insufficient context to use it effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, so the input schema fully documents the parameters 'color' and 'max_results'. The description does not add any meaning beyond the schema, such as explaining how 'ink knowledge context' relates to these parameters. Baseline is 3 as the schema handles the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool 'analyze a color and provide ink knowledge context', which gives a vague purpose. It specifies the verb 'analyze' and resource 'color', but lacks specificity on what 'ink knowledge context' entails or how it differs from sibling tools like 'search_inks_by_color'. This makes it adequate but unclear in scope.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus alternatives such as 'search_inks_by_color' or 'get_ink_details'. The description implies usage for color analysis with ink context but does not specify scenarios, exclusions, or comparisons to sibling tools, leaving the agent without clear direction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generate a themed or harmony-based palette of inks. Supports three modes: 1) Predefined themes (warm, cool, earth, ocean, autumn, spring, summer, winter, pastel, vibrant, monochrome, sunset, forest), 2) Custom hex color lists (comma-separated), 3) Color harmony generation from a base hex color.
| Name | Required | Description | Default |
|---|---|---|---|
| theme | Yes | Theme name (e.g., "warm", "ocean"), comma-separated hex colors (e.g., "#FF0000,#00FF00"), or single hex color for harmony generation (e.g., "#FF0000"). | |
| palette_size | No | Number of inks in the palette (default: 5) | |
| harmony | No | Color harmony rule to apply when theme is a single hex color. Options: "complementary", "analogous", "triadic", "split-complementary". Requires theme to be a valid hex color. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It describes what the tool does (generates palettes) but lacks behavioral details such as output format, error handling, rate limits, or authentication needs. This is a significant gap for a tool with no annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is appropriately sized and front-loaded, with a clear opening sentence followed by a concise list of three modes. Every sentence earns its place by directly explaining functionality without redundancy or unnecessary details.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of three operational modes and no annotations or output schema, the description is incomplete. It lacks information on return values, error conditions, and behavioral constraints, which are crucial for an AI agent to use the tool effectively without structured output guidance.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds value by summarizing the three modes (predefined themes, custom hex lists, harmony generation), which helps contextualize the 'theme' parameter, but it does not provide additional syntax or format details beyond the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with specific verbs ('generate a themed or harmony-based palette of inks') and distinguishes it from siblings by focusing on palette generation rather than analysis, details, or search. It explicitly lists three supported modes, making the functionality unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage by detailing the three modes, but it does not explicitly state when to use this tool versus alternatives like 'analyze_color' or 'search_inks_by_color'. No exclusions or prerequisites are mentioned, leaving some ambiguity in tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Get complete information about a specific ink
| Name | Required | Description | Default |
|---|---|---|---|
| ink_id | Yes | The unique identifier for the ink |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It states the action is to 'Get' information, implying a read-only operation, but doesn't specify aspects like authentication requirements, rate limits, error handling, or what 'complete information' entails (e.g., fields returned). This is a significant gap for a tool with zero annotation coverage.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without unnecessary words. It is appropriately sized for a simple tool, though it could be slightly more informative without losing conciseness.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations and no output schema, the description is incomplete. It doesn't explain what 'complete information' includes (e.g., properties like color, maker, or viscosity), nor does it cover behavioral aspects like response format or potential errors. This leaves the agent with insufficient context to use the tool effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with the 'ink_id' parameter clearly documented as 'The unique identifier for the ink'. The description adds no additional meaning beyond this, such as format examples or constraints. Given the high schema coverage, a baseline score of 3 is appropriate as the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb ('Get') and resource ('complete information about a specific ink'), making the purpose understandable. However, it doesn't explicitly differentiate from sibling tools like 'get_inks_by_maker' or 'search_inks_by_name', which might also retrieve ink information but with different scopes or filters.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites like needing an ink_id, nor does it contrast with siblings such as 'get_inks_by_maker' for batch retrieval or 'search_inks_by_name' for fuzzy matching. This leaves the agent without context for tool selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List all inks from a specific manufacturer
| Name | Required | Description | Default |
|---|---|---|---|
| maker | Yes | Manufacturer name (e.g., "sailor", "diamine") | |
| max_results | No | Maximum number of results to return (default: 50) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden for behavioral disclosure but only states the basic function. It doesn't mention whether this is a read-only operation, what format results are returned in, whether there are rate limits, authentication requirements, or any error conditions. For a tool with no annotation coverage, this leaves significant behavioral questions unanswered.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that gets straight to the point with zero wasted words. It's appropriately sized for a simple listing tool and front-loads the essential information.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no annotations and no output schema, the description is insufficiently complete. It doesn't explain what format the results will be in, whether there's pagination, what happens when no inks are found for a manufacturer, or any error handling. The context signals show this is a simple tool, but the description should still address basic behavioral expectations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, so both parameters are already documented in the schema. The description mentions 'from a specific manufacturer' which aligns with the 'maker' parameter, but adds no additional semantic context beyond what the schema already provides. This meets the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'List' and resource 'inks from a specific manufacturer', making the purpose immediately understandable. However, it doesn't distinguish this tool from sibling tools like 'search_inks_by_name' or 'search_inks_by_color' - all could potentially list inks, just with different filtering criteria.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. With sibling tools like 'search_inks_by_name', 'search_inks_by_color', and 'get_ink_details' available, there's no indication of when this manufacturer-focused listing is preferred over other search methods or when it might be inappropriate.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find inks similar to a given color using RGB matching
| Name | Required | Description | Default |
|---|---|---|---|
| color | Yes | Hex color code (e.g., "#FF5733") | |
| max_results | No | Maximum number of results to return (default: 20) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool finds inks 'similar to a given color using RGB matching', which implies a read-only search operation, but does not disclose details like how similarity is calculated, whether results are sorted, potential rate limits, or error handling. For a tool with no annotation coverage, this leaves significant gaps in understanding its behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's function without any wasted words. It is front-loaded with the core purpose, making it easy to understand at a glance.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity of a search tool with no annotations and no output schema, the description is incomplete. It does not explain what the return values might include (e.g., ink names, similarity scores), how results are structured, or any limitations. This leaves the agent with insufficient context to fully utilize the tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema description coverage is 100%, with clear descriptions for both parameters ('color' as a hex code and 'max_results' with a default). The description adds minimal value beyond the schema by mentioning 'RGB matching', which hints at the algorithm but does not provide additional syntax or format details. This meets the baseline for high schema coverage.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose with a specific verb ('Find') and resource ('inks similar to a given color'), and mentions the method ('RGB matching'). It distinguishes from siblings like 'search_inks_by_name' by focusing on color matching rather than name search. However, it doesn't explicitly differentiate from 'analyze_color' or 'get_color_palette', which might involve color-related operations.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives like 'get_inks_by_maker' or 'search_inks_by_name'. It lacks context about scenarios where color-based search is preferred over other methods, and does not mention any prerequisites or exclusions for usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search for fountain pen inks by name using fuzzy matching
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Search term for ink name | |
| max_results | No | Maximum number of results to return (default: 20) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions 'fuzzy matching' but doesn't explain how it works, what the output format is, or any limitations like rate limits or authentication needs. For a search tool with no annotations, this is a significant gap in transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, efficient sentence that directly states the tool's purpose without any wasted words. It's appropriately sized and front-loaded, making it easy for an agent to parse quickly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the lack of annotations and no output schema, the description is incomplete. It doesn't explain what the search results look like, how fuzzy matching behaves, or any error conditions. For a search tool with two parameters and no structured output, more context is needed to be fully helpful.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage, with clear documentation for both parameters ('query' and 'max_results'). The description adds no additional parameter details beyond what the schema provides, such as examples or constraints. Baseline 3 is appropriate when the schema does the heavy lifting.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: 'Search for fountain pen inks by name using fuzzy matching.' It specifies the verb (search), resource (fountain pen inks), and method (fuzzy matching by name). However, it doesn't explicitly differentiate from sibling tools like 'search_inks_by_color' or 'get_inks_by_maker', which is why it's not a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like 'search_inks_by_color' or 'get_ink_details', nor does it specify any prerequisites or exclusions. This leaves the agent without clear usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
analyze_colorget_color_paletteget_ink_detailsget_inks_by_makersearch_inks_by_colorsearch_inks_by_nameScored across 6 tools
Each tool has a clearly distinct purpose with no overlap: analyze_color provides color context, get_color_palette generates palettes, get_ink_details retrieves specific ink info, get_inks_by_maker lists by manufacturer, search_inks_by_color matches by RGB, and search_inks_by_name searches by name. The descriptions clearly differentiate their functions, making misselection unlikely.
All tool names follow a consistent verb_noun pattern with snake_case: analyze_color, get_color_palette, get_ink_details, get_inks_by_maker, search_inks_by_color, and search_inks_by_name. The verbs (analyze, get, search) are appropriately chosen for their actions, and the naming is predictable throughout the set.
With 6 tools, this server is well-scoped for its fountain pen ink domain. Each tool earns its place by covering distinct aspects like color analysis, palette generation, ink details, manufacturer listings, and color/name searches. The count is neither too sparse nor bloated, fitting typical MCP server ranges.
The tool set provides strong coverage for ink exploration and color matching, including search, details, and palette generation. Minor gaps exist, such as no explicit tools for updating ink data or managing user collections, but agents can work around these with the available tools for core workflows like finding and analyzing inks.
Search, inspect, recommend, and explain rated AI tools through Agent Radar.
Persistent memory and knowledge management for AI agents with semantic search and 50+ tools.
Independent directory of agentic AI tools — search, compare & recommend via MCP. Read-only.
The media memory layer for AI agents and their humans. Your AI client gets 29 tools to search your collection, add items, update ratings, preview music, and find patterns across everything you've read, watched, and listened to.
