Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
CAVALRY_MCP_HOSTNoBridge host127.0.0.1
CAVALRY_MCP_PORTNoBridge port — must match PORT in cavalry-bridge.js8080
CAVALRY_MCP_TIMEOUT_MSNoPer-request timeout15000
CAVALRY_MCP_ENABLE_RUN_SCRIPTNoSet to '1' to expose cavalry_run_script. See Security section.

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
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

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

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