mcp-server
Server Details
Fluxink Ink Intelligence
- Status
- Healthy
- Last Tested
- Transport
- Streamable HTTP
- URL
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Tool Definition Quality
Average 4.5/5 across 4 of 4 tools scored.
Each tool has a clearly distinct purpose: show_handwriting_canvas for recognition input, show_style_canvas for style capture, and the internal endpoints are explicitly marked as not for direct agent use. No ambiguity between tools.
All tools follow the consistent pattern 'fluxink-mcp-<verb>-<noun>' with snake_case. Verbs like 'show' and 'synthesize' are semantically appropriate and predictable.
Four tools cover the core functionalities of handwriting recognition and style synthesis without unnecessary clutter. The count is well-scoped for the domain.
The agent-facing tools (show_handwriting_canvas and show_style_canvas) properly initiate workflows, while internal endpoints handle execution. Minor gap: the agent cannot directly retrieve recognized text without widget interaction, but this is by design for the integration.
Available Tools
4 toolsfluxink-mcp-recognize-handwritingARead-onlyInspect
Internal FluxInk handwriting recognition execution endpoint. Invoked ONLY by the FluxInk handwriting canvas widget when the user clicks Recognize. Do NOT call this tool directly from chat. To capture handwriting from the user, call show_handwriting_canvas instead. This endpoint expects a JSON stroke payload that only the widget can produce.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | text | |
| strokes | Yes | JSON stroke payload captured by the widget. | |
| language | No |
Output Schema
| Name | Required | Description |
|---|---|---|
| error | No | |
| result | No | |
| success | Yes |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only and non-destructive behavior. The description adds context about the stroke payload format and internal usage, which is helpful.
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?
Very concise, straight to the point, with essential usage guidance upfront. No unnecessary words.
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 an output schema exists and the tool's purpose is narrow, the description adequately covers when and how to use it, though param details are sparse.
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?
Only the 'strokes' parameter has a brief description; 'mode' and 'language' lack explanation. With only 33% schema coverage, more detail is needed.
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 it is an internal handwriting recognition endpoint invoked only by the widget, with a specific verb and resource. It distinguishes itself from siblings like show_handwriting_canvas.
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?
Explicitly says not to call directly from chat and provides the alternative tool (show_handwriting_canvas) for user interaction.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
fluxink-mcp-show-handwriting-canvasARead-onlyInspect
Open the FluxInk handwriting recognition canvas. The user draws with a stylus, finger, or mouse and the strokes are converted by one of two model families: general recognition for handwriting, math, and chemical formulas, or structure recognition for molecular structures.
Use this when the user explicitly asks to write, draw, sketch, hand write, ink, capture handwriting, hand draw a math equation, hand draw a chemical formula, or hand draw a molecular structure.
Do NOT use this for plain text questions, explanations, or summaries. Do NOT use this for type set math the user typed in chat. Do NOT use this for image text recognition (call recognize_image instead). Do NOT use this for document layout (call create_layout instead). Do NOT use this for capturing the personal handwriting style of the user (call show_style_canvas instead).
Do NOT call again if a FluxInk handwriting canvas is already visible from a prior turn. Instead instruct the user to keep drawing on the existing canvas. Only set force_new=true when the user literally asks for a brand new, fresh, or blank canvas. After invocation, write at most one short acknowledgement line. The canvas itself is the UI.
ALWAYS pass the user's full original chat message verbatim in the prompt argument so it can be prepended to the recognized text when the user sends the result back. Never paraphrase, summarize, or omit it.
| Name | Required | Description | Default |
|---|---|---|---|
| mode | No | Recognition family for the canvas. Use general for text, math, and chemical formulas; use structure only for molecular structures. | general |
| prompt | Yes | REQUIRED. The user's original chat message verbatim (do not paraphrase). This is prepended to the handwritten result in the follow-up message so you can act on the user's original intent. | |
| language | No | Optional text language hint for the backend. | |
| force_new | No | Set true ONLY when the user explicitly asks for a brand new canvas. Otherwise leave false so a previously opened canvas is reused. |
Output Schema
| Name | Required | Description |
|---|---|---|
| mode | No | |
| type | Yes | |
| reuse | No | |
| prompt | No | |
| message | Yes | |
| language | No | |
| apiBaseUrl | No |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations (readOnlyHint=true, destructiveHint=false) are complemented by description detailing that the tool opens a UI canvas, instructs to write at most one acknowledgement line, and that the canvas is the UI. No contradiction; adds context beyond annotations.
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?
Description is detailed but well-structured with clear sections. Every sentence serves a purpose. Slightly long but necessary for correct usage; front-loaded with key 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?
Covers purpose, usage guidelines, parameter details, and behavioral instructions. An output schema exists, so return value explanation is not needed. Complete for the tool's complexity (UI canvas with recognition).
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 coverage is 100%, but description adds meaning: reinforces that 'prompt' must be the user's verbatim message, clarifies mode enum values ('general' for text/math/chem, 'structure' for molecular structures), and explains when to use force_new. Adds significant context beyond 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 opens a handwriting recognition canvas, specifies two model families (general and structure), and distinguishes from siblings by listing what not to use this tool for (e.g., image text, layout, style canvas). It provides a specific verb and resource.
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?
Explicitly states when to use (user requests to write/draw/sketch/handwrite etc.) and when not to use (plain text, image text, layout, style canvas). Also includes guidelines on not invoking again if canvas already visible and when to set force_new=true.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
fluxink-mcp-show-style-canvasARead-onlyInspect
Open the FluxInk natural texture ink style capture canvas. The user draws a few sample characters in a personal handwriting style. The widget then renders the requested text as a PNG spritesheet IN THAT PERSONAL HANDWRITING STYLE.
Use this when the user explicitly asks to render text in a personal handwriting style. Use this when the user wants to generate a handwritten note, card, letter, or journal entry in a personal handwriting style. Use this when the user wants to capture, clone, or sample a personal handwriting style. Use this when the user wants a handwritten look image asset that matches a personal pen script.
Do NOT use this for plain handwriting recognition (call show_handwriting_canvas instead). Do NOT use this for generic decorative fonts or AI generated calligraphy unrelated to the personal writing of the user. Do NOT use this to read text from an existing photo of handwriting. Do NOT use this for document layout (call create_layout instead).
Always pass the COMPLETE text the user wants rendered in the text parameter. Never truncate. Do NOT call again if a FluxInk natural texture ink canvas is already visible from a prior turn. Instead tell the user to update the target text inside the existing widget. Only set force_new=true on an explicit user request for a brand new style canvas.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | The complete text to render in the captured handwriting style. | |
| force_new | No | Set true ONLY when the user explicitly asks for a brand new style canvas. Otherwise leave false so a previously opened canvas is reused. |
Output Schema
| Name | Required | Description |
|---|---|---|
| text | No | |
| type | Yes | |
| reuse | No | |
| message | Yes | |
| apiBaseUrl | No |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate readOnlyHint=true, and the description adds context about user interaction (drawing samples, rendering) and statefulness (reuse existing canvas). It also warns against truncation and repeated calls, though it could detail more about the capture process. No contradiction with annotations.
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 well-structured with a first paragraph for core functionality and bullet points for usage guidelines. It is informative without being overly verbose, though minor tightening could improve 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?
Given the existence of an output schema (not shown), the description need not explain return values. It covers purpose, param guidance, usage restrictions, and behavioral rules, and distinguishes from siblings. For a tool with two parameters and clear annotations, this is fully complete.
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 coverage is 100% with both parameters described. The description adds important usage advice: always pass complete text, and only set force_new=true on explicit request. This goes beyond the schema defaults and descriptions.
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 opens a canvas to capture personal handwriting style and renders text as a PNG spritesheet in that style. It uses a specific verb and resource, and explicitly distinguishes from sibling tools like handwriting recognition and decorative fonts.
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 explicit when-to-use (e.g., for personal handwriting rendering, capturing style) and when-not-to-use (e.g., for plain recognition, decorative fonts, reading from photo). It names alternative tools and includes operational guidance such as never truncating text and not calling again if canvas is visible.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
fluxink-mcp-synthesize-handwriting-styleARead-onlyInspect
Internal FluxInk natural texture ink execution endpoint. Invoked ONLY by the FluxInk style canvas widget when the user clicks Generate. Do NOT call this tool directly from chat. To render text in the personal handwriting style of the user, call show_style_canvas instead. This endpoint requires JSON encoded style strokes captured by the widget.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Text to render with the captured handwriting style. | |
| cell_size | No | ||
| legibility | No | ||
| style_text | No | Optional explicit style text captured from the user sample | |
| stroke_width | No | ||
| style_strokes | Yes | JSON style strokes captured by the widget. |
Output Schema
| Name | Required | Description |
|---|---|---|
| error | No | |
| success | Yes | |
| charCount | No | |
| imageBase64 | No | |
| inferenceTimeMs | No |
Tool Definition Quality
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=true and destructiveHint=false, indicating safe, non-destructive operation. The description adds that this is an execution endpoint requiring JSON style strokes, which is consistent. No contradictions.
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 4 sentences, front-loaded with the critical instruction (do not call directly). Every sentence adds necessary context, with no redundancy.
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 an internal endpoint intended only for widget use, the description is complete enough to prevent misuse. It specifies the requirement (style strokes from widget) and the alternative. The output schema exists to describe the return value, so that aspect is covered.
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 50% (3 of 6 parameters have descriptions). The tool description only mentions the 'style_strokes' parameter, leaving other parameters (text, cell_size, legibility, etc.) undocumented in the description. The description should compensate for the low schema coverage but does not.
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 is an internal endpoint for the FluxInk style canvas widget, and explicitly says not to call it directly from chat. It distinguishes from the sibling tool show_style_canvas, which is the correct alternative for rendering handwriting.
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 gives explicit when-to-use (only by the widget when user clicks Generate) and when-not-to-use (not directly from chat), and provides the alternative tool (show_style_canvas). This is excellent guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
Discussions
No comments yet. Be the first to start the discussion!