Gumlet (BYOK)
Read your Gumlet hosted videos, workspaces, folders, playlists, image sources and streaming usage with your own API key
Rule of thirds, leading lines, symmetry — plus exact computed grid coordinates
Unify Dynamics LLC
Real questions, and the tools your agent calls to answer them.
rule_inforule_listrule_for_scenariothirds_grid_coordinatesleading_lines_typessymmetry_typesnegative_space_tipsframing_techniquescomposition_glossaryCompomap is a fully local, hand-curated photo composition reference. rule_info explains one of ten composition principles in full — description, when to use it, common mistakes; rule_list shows all ten. rule_for_scenario suggests 1-3 relevant rules for a described scene. thirds_grid_coordinates is real computed geometry: give an aspect ratio, optionally a canvas size in pixels, a subject-position category, and a grid type (rule-of-thirds at exact 1/3 and 2/3 lines, or the golden-ratio 'phi grid' at 1/phi and 1-1/phi, phi = 1.6180339887...), and it returns the exact grid-line coordinates, all four intersection 'power points', and a recommended subject x/y position. leading_lines_types, symmetry_types, negative_space_tips and framing_techniques are focused deep-dive references. composition_glossary defines vanishing point, foreground/midground/background, headroom, look room, rule of odds, power points, visual weight and depth of field. Keyless; fully local; zero upstream calls; nothing stored.
Sources: Hand-curated from well-established, widely taught general photography/visual-arts composition principles, plus real computed geometry (exact thirds and golden-ratio/phi-grid math) for the grid-coordinates tool; fully local, zero upstream calls
The publisher, Unify Dynamics LLC, states that tool inputs are processed in memory and not retained.
9 tools, grouped by job. Every one is read-only or compute-only.
https://compomap.connectorbay.com/mcpRead your Gumlet hosted videos, workspaces, folders, playlists, image sources and streaming usage with your own API key
Read your Synthesia AI videos and their render status, templates with variables and credit balance with your own API key
Read your Tavus video AI conversations, PALs (agents), faces, voices, knowledge documents, guardrails and objectives with your own API key
Read your Imgix sources, assets in the Asset Manager and analytics report files with your own Management API key
Read your Shotstack render status, saved templates, hosted assets, ingested source files and generation model list with your own API key
Read your Placid templates, template collections, fonts and generated images, PDFs and videos (status and file URLs) with your own project API token
"When should I use the rule of thirds vs leading lines?", "where exactly do the thirds-grid lines fall on a 16:9 photo?", "what composition rule fits a scene with a long road?" — a practical composition reference that pairs hand-curated guidance with real computed grid geometry, not just a description of where things "roughly" go.
rule_info explains one of ten composition principles in full — rule of thirds, leading lines, framing, symmetry,
negative space, golden ratio, fill the frame, diagonal lines and the rule of odds, patterns and repetition, and
color/tonal contrast — with a description, when to use it, and common mistakes; rule_list shows all ten at a
glance. rule_for_scenario suggests 1-3 relevant rules for a plain-language description of a scene or goal.
thirds_grid_coordinates is the connector's core computed tool: give an aspect ratio (16:9, 4:3, 1:1,
9:16, or a raw WIDTHxHEIGHT), optionally an exact canvas size in pixels, a subject-position category
(top_left, top_right, bottom_left, bottom_right, top_third, bottom_third, left_third, right_third,
center), and a grid type — and it returns the exact vertical/horizontal grid-line coordinates, all four
intersection "power points," and a recommended subject x/y position. The rule-of-thirds grid sits at exactly 1/3
and 2/3 of the frame; the golden-ratio ("phi grid") variant sits at 1/φ and 1 − 1/φ (φ ≈ 1.6180339887), the
standard construction used across photography and design — both are real, checkable arithmetic on the aspect ratio
and canvas size you give it.
leading_lines_types, symmetry_types, negative_space_tips and framing_techniques are focused deep-dive
references for those four rules specifically. composition_glossary defines the surrounding vocabulary —
vanishing point, foreground/midground/background, headroom, look room, rule of odds, power points, visual weight,
depth of field.
Not a substitute for looking at the actual scene in front of you. Composition "rules" here are well-established general guidelines used across photography and visual arts, not laws — plenty of excellent photos break every one of them on purpose. The grid-coordinate math is exact for the aspect ratio and canvas size you provide, but where a subject actually belongs in any specific photo is always a judgment call informed by the scene, not something a formula can decide for you.
Effective 24 September 2026. Unify Dynamics LLC ("we", "us"), Menlo Park, California.
What Compomap is. Compomap is a connector (an MCP server and REST API) that AI assistants and personal agents call on your behalf for a hand-curated photo composition reference and a computed grid-coordinate calculator. You interact with your assistant; the assistant sends us only the arguments needed for that one lookup or computation.
What we receive. The arguments of each tool call — a composition rule name, a described scene, or an aspect ratio/canvas size/subject position for the grid calculator — the technical headers needed to serve the request (an IP address or a client identifier supplied by the assistant, and a Pro API key if you have one), and standard server logs.
Everything is answered from bundled, hand-curated reference data or computed locally, and nothing is stored. No request is forwarded to any third party — there is no upstream call at all, live or otherwise — and no query is logged in request bodies, recorded, or used to train anything.
What we do not receive or store. We do not receive your conversation with the assistant or your name, and we do not build a profile from your queries: each request is answered independently and nothing carries over between requests. Rate-limit counters (a client identifier and timestamps) are held in memory for at most 24 hours. Hosting-provider access logs, which contain IP addresses and request paths but not request bodies, are retained for up to 30 days for security and abuse prevention.
Sub-processors. None — the entire reference is bundled with the server and every computation runs locally. Hosting: Vercel (United States regions).
Legal bases and your rights. Our processing is necessary to provide the service you request through your assistant. Because we store no personal data beyond short-lived logs, requests to access, correct or delete personal data are usually satisfied automatically; you can still contact agent@connectorbay.com and we will respond within 30 days. We do not sell or share personal information and do not use your data to train models.
Children. Compomap is a general-audience service operated by the adult using the assistant.
Changes. We will post changes here with a new effective date.
Effective 24 September 2026. These terms govern use of the Compomap connector ("the Service") operated by Unify Dynamics LLC ("we", "us").
Email agent@connectorbay.com. We answer within two business days.
https://compomap.connectorbay.com/mcphttps://compomap.connectorbay.com/openapi.jsonWhen you report a problem, include the question you asked your agent, roughly when, and which agent you used (for example Claude, ChatGPT or Gemini). Never send us passwords, account numbers or ID numbers. Photo Composition never asks for them.