cavalry-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| CAVALRY_MCP_HOST | No | Bridge host | 127.0.0.1 |
| CAVALRY_MCP_PORT | No | Bridge port — must match PORT in cavalry-bridge.js | 8080 |
| CAVALRY_MCP_TIMEOUT_MS | No | Per-request timeout | 15000 |
| CAVALRY_MCP_ENABLE_RUN_SCRIPT | No | Set to '1' to expose cavalry_run_script. See Security section. |
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 |
|---|---|
| cavalry_pingA | Verify the Cavalry bridge and dispatcher are reachable. Returns the host platform. |
| cavalry_list_layersA | List every layer as {id, type, name}. |
| cavalry_get_selectionA | Get the current layer selection. |
| cavalry_composition_infoB | Get composition resolution, frame range, and FPS. |
| cavalry_get_attributeB | Read an attribute value from a layer. |
| cavalry_bounding_boxA | Get bounding box of a layer. Returns {x, y, width, height, centre, left, right, top, bottom}. |
| cavalry_list_attributesA | List every attribute on a layer with its type, nice name, children and animated flag. Use this INSTEAD of guessing attribute paths — attribute names are not derivable from the UI labels in Cavalry's docs, and a wrong path fails silently on write. |
| cavalry_list_layer_typesA | List every creatable layer type ID. These are the scripting IDs accepted by cavalry_create_layer, which differ from the display names in Cavalry's UI and docs (e.g. 'Shuffle String Manipulator' is created as 'shuffleString'). |
| cavalry_inspect_connectionsA | List a layer's incoming and outgoing attribute connections, plus its animated attributes. Use this to confirm a cavalry_connect actually landed and to discover which input a node type expects. |
| cavalry_create_layerB | Create a layer by type ID (textShape, null, colorPlane, subMesh, stagger, duplicator, …). |
| cavalry_create_primitiveA | Create a basicShape with a generator pre-attached. Prefer this over create_layer + set_generator for primitives. |
| cavalry_set_attributeC | Set one or more attributes on a layer in a single call. |
| cavalry_set_generatorC | Set the generator on a layer. |
| cavalry_selectB | Set the current selection to the given layer IDs. |
| cavalry_delete_layersC | Delete layers by ID. |
| cavalry_duplicateB | Duplicate layers. Restores the prior selection afterward. |
| cavalry_parentC | Parent one or more layers to a target parent. |
| cavalry_add_dynamic_attributeC | Add a dynamic attribute to a layer. |
| cavalry_connectA | Connect one layer's attribute output to another layer's attribute input. Used for procedural/data-driven workflows (e.g. connecting a shape to a duplicator's 'shapes' input, or a noise layer's output to a position attribute). |
| cavalry_keyframeB | Set keyframes on one or more attributes at a given frame. |
| cavalry_magic_easingA | Apply a Magic Easing preset to a keyframe. Linear is NOT a valid Magic Easing preset. |
| cavalry_delete_keyframeB | Delete a keyframe at a specific frame. |
| cavalry_set_frameB | Set the playhead to a specific frame. |
| cavalry_playC | Start playback. |
| cavalry_save_sceneA | Save the current scene. Pass filePath for Save As. |
| cavalry_load_sceneC | Load a scene from disk. |
| cavalry_render_pngB | Render the current frame (or a specific frame) to a PNG file. |
| cavalry_batchA | Run a sequence of operations in one HTTP round-trip (fail-fast, not atomic). Layer IDs from earlier creates are NOT auto-substituted — predict sequential IDs or split into multiple batches. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ZHUYUFAN3-33/cavalry-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server