Morpha

detect_text_regions

Return the OCR text regions detected in a clip's video frames OR a still image asset. Pass either clip (a video..clip filename) or image (an image layer's filename) — not both. Video clips are sampled every 0.3s at upload time; images are OCR'd once. Results are cached in R2 next to the source. Returns { status: 'ready' | 'not-ready', frames: [{ frame, time, words: [{ text, x0, y0, x1, y1, confidence }] }], videoWidth, videoHeight }. For an image there's a single frame (frame 0); videoWidth/videoHeight are the image's pixel dimensions. Each words entry is one detected text line — text may hold several words, the box is axis-aligned, and confidence is 0–100. Coordinates are in the SOURCE pixel space (not canvas space). Use to know where titles / subtitles / lower-thirds are baked into the video or image so the Morpha title + intro graphics can be positioned to not collide.

Input Schema

TableJSON Schema

Name	Required	Description
`clip`	No	Video clip filename (the same value as `video.<id>.clip`). Pass this OR `image`.
`image`	No	Image layer filename (the same value as `image.<id>.filename`). Pass this OR `clip`.
`projectId`	Yes	Project the clip/image belongs to.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

First observedSep 7, 2026

TDQS

A4.5/5.0

Behavior5/5

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

With no annotations, the description carries full behavioral burden and does so thoroughly: sampling cadence (0.3s), image OCR happening once, R2 caching, not-ready status, source-pixel coordinate space, confidence range, and axis-aligned boxes are all disclosed.

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

Conciseness5/5

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

The description is long but densely packed; every clause adds operational detail, return-shape clarification, a coordinate caveat, or a usage rationale. It is front-loaded with the core purpose and input constraint before diving into output details.

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

Completeness5/5

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

Even without a formal output schema, the description fully defines the return shape, field semantics, frame behavior for images, and coordinate space. The only minor omission is retry guidance for 'not-ready', but the overall context is rich enough for an agent to call correctly.

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

Parameters3/5

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 three parameters. The description reinforces clip-vs-image exclusivity and filenames but does not materially add parameter meaning beyond the schema.

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 opens with a specific verb and resource: 'Return the OCR text regions detected in a clip's video frames OR a still image asset.' It distinguishes itself from audio-oriented siblings like transcribe_clip by focusing on OCR text and naming both input forms.

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

Usage Guidelines4/5

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

It gives clear selection constraints ('Pass either clip or image — not both') and an explicit use case ('Use to know where titles / subtitles / lower-thirds are baked into the video or image'). It does not name alternatives to avoid, so it stops short of full when-not guidance.

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

All Morpha tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0

Disambiguation3/5

The tool set has several clusters that overlap conceptually: add_keyframe/add_keyframes/set_keyframes_batch, move_band/move_layer/shift_group/set_group_window, and fade_layer/set_layer_transition/set_layer_visible all target similar actions. However, each tool's description is distinct and detailed enough for an agent to disambiguate after careful reading. The sheer volume of 95 tools still creates meaningful selection risk.

Naming Consistency4/5

Tool names overwhelmingly follow a verb_noun snake_case pattern (add_, remove_, set_, list_, rename_, create_, delete_), which is predictable and readable. Minor inconsistencies exist: plural variants like add_keyframes vs add_keyframe, mixed specificity like remove_keyframe vs remove_color_keyframe, and a few oddballs like reid_project and clip_processing_status. Overall the pattern is strong and helps navigation.

Tool Count2/5

95 tools is far beyond the well-scoped range and will overwhelm agents; even a comprehensive video editor could consolidate keyframe batch operations, overlay/track manipulations, and page/group window controls. Many tools are highly specific (reid_project, safe_zones, move_band) and place burden on the agent to pick among near-synonym verbs. While the broad domain justifies many operations, this count is excessive for a coherent tool surface.

Completeness3/5

The surface covers a broad editing lifecycle: layers, keyframes, text, captions, audio, pages, groups, versions, projects, workspaces, and collections, including batch operations. However, there is no MCP tool to render/export the final MP4 (explicitly delegated to an SDK) and no upload_video tool for bringing in a clip file, leaving major end-to-end gaps. For the stated purpose of building and editing videos, these are significant omissions that force agents to stop short of delivery.

Resources

Need Help?