Skip to main content
Glama

Server Details

Shared canvas for AI-assisted product design, visual feedback and interactive prototypes. Browser sign-in (OAuth) required. Website: https://enhancelabs.ai. Docs: https://app.enhancelabs.ai/docs.

Ownership verified
Status
Healthy
Uptime
100.0% over the last 24 hours
OAuth
Works in Glama
Last Tested
Transport
Streamable HTTP · MCP 2025-11-25
URL
ChatGPT
–
Claude
–

TDQS

A4/5.0

Scored across 8 tools

Disambiguation4/5

The canvas tools (edit, render, write_html) have clearly distinct purposes, and the capability tools (search, catalogue, describe, query, mutate) are well-differentiated by their retrieval versus execution roles. However, there is some overlap between the specific canvas_edit and the generic capability_mutate for mutating canvas state, which could lead to hesitation in tool selection.

Naming Consistency5/5

All tool names follow a predictable prefix_action pattern: canvas_ for domain-specific operations and capability_ for generic capability operations. The actions are verbs (edit, render, write_html, catalogue, describe, mutate, query, search), with only minor length variation in write_html that does not break the pattern.

Tool Count5/5

Eight tools is well within the ideal range. The set cleanly separates three domain-specific canvas operations from five generic capability discovery and invocation tools, with each tool serving a distinct role and no obvious redundancy.

Completeness4/5

The surface covers canvas creation (write_html), modification (edit), visual inspection (render), and generic capability discovery/invocation (search, describe, catalogue, query, mutate). Explicit delete/remove operations and direct canvas listing are missing, though these may be reachable through the generic capability tools, leaving minor gaps.

Available Tools

8 tools
canvas_editEdit existing canvas contentA
Destructive
Inspect

Apply text, styles, rename, duplicate or move edits together in one atomic mutation. Use ids from the input version and the latest successful read or write version; no intermediate read is required just to advance a version. Keep the complete selection URL. Read only the missing subtree when ids are unknown. Returns a compact committed receipt; render after the requested changes are complete.

Inputs: edits (required), canvas (required), baseVersion (required), clientToken. Returns: object

canvas_renderReview canvas pixelsAInspect

Render the version returned by a successful read or write and inspect its native PNG. Target the affected screen/node; a blank canvas does not need a pre-render. For a selection link use one node inside the selection. Review after a meaningful visual change, and repeat only after further changes or a real discrepancy.

Inputs: canvas (required), expectedVersion (required), scale, target, +2 more. Returns: object

canvas_write_htmlDesign editable canvas contentA
Destructive
Inspect

Create a populated screen or visual group from safe HTML/CSS. For multiple screens, publish the first populated screen before authoring the next, then publish each subsequent screen separately so the user can see and steer progress. Prepare only what that screen needs; do not prepare the whole set before the first write. Returns the committed version and root node without an extra read or render. If starting state is unknown, call capability_query with {"capability":"canvas.read","input":{"canvasId":""}}. When nodeCount is 0, use targetNodeId "root" and the returned version. Use flex, padding, gap, concrete inline CSS and layer-name. Give important rows/cards/buttons explicit dimensions; avoid implicit stretch, margins, grid, tables and inline badge backgrounds. Include real content, not an empty shell. Reuse a returned version for subsequent edits; read a targeted subtree only when its ids or structure are unknown. Use canvas_edit for small changes, then canvas_render once at a useful review point. The schema here is executable; no search or describe is required.

Inputs: html (required), canvas (required), baseVersion (required), targetNodeId (required), +3 more. Returns: object

capability_catalogueScan every Enhance capabilityA
Read-onlyIdempotent
Inspect

Return the complete bounded capability inventory when the task is broad, uncertain, or capability_search does not find the right words. Call capability_describe with one exact id before invoking it.

Inputs: no named parameters.

capability_describeLoad one Enhance capability contractA
Read-onlyIdempotent
Inspect

Load the exact input schema, example, preconditions, result guidance, recovery, and next steps for one id returned by capability_search or capability_catalogue.

Inputs: capability (required). Returns: object

capability_mutateRun a discovered Enhance mutationA
Destructive
Inspect

Run one state-changing capability using an available complete contract. Respect its preconditions and reuse clientToken only when retrying the identical mutation.

Inputs: capability (required), input, clientToken. Returns: object

capability_queryRun a discovered Enhance queryA
Read-onlyIdempotent
Inspect

Run one read-only capability using an available complete contract. Search or describe only when the contract is missing.

Inputs: capability (required), input. Returns: object

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Servers

    • A
      license
      Not graded
      quality
      C
      maintenance
      Remote MCP server that lets AI assistants read tracked competitive intelligence — competitor news, reviews, website changes, social posts and ads — and act on it by managing projects, competitors, battle cards, reports and canvases. Every answer carries a source and a date, and write actions only publish when explicitly shared.
      MIT
    • A
      license
      A
      quality
      D
      maintenance
      Enables brand visibility monitoring across major AI platforms like ChatGPT, Claude, Gemini, and Perplexity. It allows users to track visibility scores, analyze competitor data, and receive actionable insights to improve AI-generated brand recommendations.
      16
      9 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Browse IndustryLens's published competitive-intelligence reports and head-to-head competitor comparisons from any AI agent — real, source-backed data.
      MIT
    Try in Browser

    Glama MCP Gateway

    Add one secure layer between your agents and this server.

    Resources