Install
Add Cascades to VS Code
- Click Add to VS Code (needs VS Code 1.99+ with GitHub Copilot agent mode), or
- create
.vscode/mcp.jsonin your workspace with the JSON below. VS Code's schema isservers, notmcpServers, and declares the transport explicitly. - Run MCP: List Servers from the command palette and start
cascades.
Add to VS Code
Installs with your sandbox key.
Sign in to enable one-click install
Adds Cascades to VS Code with your sandbox key pre-filled.
.vscode/mcp.json
{
"servers": {
"cascades": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@crscreditapi/cascades-mcp-server"
],
"env": {
"CASCADES_API_KEY": "{{API_KEY}}",
"CASCADES_PROD_BASE_URL": "https://cascades.crscreditapi.com"
}
}
}
}Notes
CASCADES_PROD_BASE_URLis the host without/api/v1(https://cascades.crscreditapi.com); the server adds the prefix.- The key needs
workflows:read,workflows:write,executions:read,executions:write. A key missing a scope gets403 insufficient_scopeon the affected tool only. - Sandbox keys can only run in test mode:
execution_mode: "live"is billable, needs a production-approved account, and is rejected for docs-issued keys. - To keep the key out of the workspace file, VS Code supports
"inputs"with"password": trueand${input:cascades_api_key}inenv.
Test with MCP Inspector
Check the key and host before trusting the editor integration: this runs the server with the same environment and lets you call each tool from a browser UI.
Terminal
CASCADES_API_KEY={{API_KEY}} CASCADES_PROD_BASE_URL=https://cascades.crscreditapi.com \
npx @modelcontextprotocol/inspector npx -y @crscreditapi/cascades-mcp-serverWhat you get
| Tool | What it does | Access | REST call |
|---|---|---|---|
| cascades_create_workflow | Create a new cascade (decision workflow) from a JSON definition, owned by the API key's account. | write |
POST
/workflows
|
| cascades_delete_workflow | Delete a cascade (soft-delete). | destructive |
DELETE
/workflows/{id}
|
| cascades_generate_workflow | Build a cascade from a plain-English policy description using the Cascades AI builder, then create it (by default) so it is immediately runnable with cascades_trigger_workflow. | write |
POST
/workflows/generate
|
| cascades_get_execution | Fetch a single cascade execution by id to check its status and results. | read |
GET
/executions/{id}
|
| cascades_get_workflow | Fetch one cascade by id, including its full node graph (`definition`). | read |
GET
/workflows/{id}
|
| cascades_list_test_cases | List the pre-registered sandbox test-case subjects for a cascade โ the synthetic applicants the CRS Testcase Service has authored for that cascade's products (e.g. specific credit-score bands). | read |
GET
/workflows/{id}/test_cases
|
| cascades_list_workflows | List the caller's saved Cascades (decision workflows) โ their id, code, name, use_case, trigger_type, and whether each is active. | read |
GET
/workflows
|
| cascades_trigger_workflow | Run a saved cascade for an applicant โ i.e. start a decision. | write |
POST
/workflows/{id}/trigger
|
| cascades_update_workflow | Update an existing cascade. | write |
PATCH
/workflows/{id}
|