motionspec
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| motion_catalogA | Returns the catalog of verified motion primitives (names, purpose, parameter schemas, defaults) plus the authoring rules for writing a MotionSpec. Call this FIRST, then write the spec yourself, check it with motion_validate and compile it with motion_compile. Free motion check: https://motionspec.dev/motion-check · paid Motion Report (9 USD, one-time): https://motionspec.dev/pricing?src=mcp-motion_catalog#p-report. |
| motion_validateA | Checks a MotionSpec against the schema, the primitive allow-list, parameter bounds and injection rules. Fail-closed: returns ok=false with precise errors. Returns {ok, errors, warnings, deprecations, catalogVersion}. IMPORTANT: warnings[] carries the WCAG 2.2.2 / reduced-motion findings and can be non-empty while ok=true — a spec that compiles is not automatically accessible. Use to pre-check a spec before compiling. |
| motion_compileA | Validates (fail-closed) and deterministically compiles a MotionSpec into vanilla-GSAP JavaScript and CSS, with prefers-reduced-motion enabled by default and a performance-budget report. Same spec always yields identical code. Returns {ok:true, js, css, warnings, report, catalogVersion} or {ok:false, errors, catalogVersion}; css may be null when no CSS is emitted. Read warnings before shipping: explicitly disabling reduced-motion or loop pause controls can compile with accessibility warnings. Does not write files or execute the emitted code. |
| motion_auditA | Static motion-a11y checker: fetches a URL's HTML + linked stylesheets (up to 12 sheets, 2 MB per response, 8 s timeout) and scans the CSS for (1) animation/transition that moves without an effective (cascade-aware) prefers-reduced-motion guard, (2) animated non-transform/opacity properties, (3) infinite animations with no pause path, (4) /autoplay >5s. Colour/opacity-only transitions are not motion (WCAG 2.3.3). Uses scoring v2. Same engine and scoring as the free site check at https://motionspec.dev/motion-check. Returns structuredContent {ok, url, status, score, scoring, scoring_doc, findings, groups, summary, badge, disclosures, coverage} plus a Markdown report in text content, or {ok:false, error} with isError:true on failure. Read status first: pages without CSS motion return status 'not-measurable' with score null; runtime motion such as WAAPI/GSAP/WebGL is not audited. Loading indicators are reported as 'review', not as violations; verify them manually. The 'reduced-motion-safe' badge requires a measurable page with zero findings and no detected runtime motion library. Does network I/O (openWorldHint). |
| motion_statsA | Summary of routing/compile telemetry (counts per outcome). Escalation clusters indicate which new primitive the catalog needs next. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 5 tools
Each tool targets a distinct stage: catalog (discover primitives/rules), validate (schema/allow-list check of a spec), compile (emit JS/CSS), audit (scan a live URL's CSS), and stats (telemetry). The validate/compile overlap is explicitly disambiguated in the descriptions (pre-check before compiling), and audit vs validate are clearly separated by input type (URL vs spec).
All names use a consistent motion_ prefix with snake_case suffixes and action-oriented suffixes (validate, compile, audit). Minor deviation: catalog and stats are nominal rather than verb-style, but the pattern remains predictable overall.
Five tools map cleanly onto the author-observe pipeline (discover, validate, compile, audit, telemetry) with no filler tools. This is well within the ideal 3-15 range and each tool earns its place.
The surface covers the full spec lifecycle from primitive discovery through validation, compilation, and post-hoc auditing, with sensible fail-closed outputs. Minor gaps exist: no tool writes or applies the compiled output, and runtime motion (WAAPI/GSAP) is acknowledged as unaudited, which agents must work around manually.