PromptShuttle
Remote ActivePrompt management, LLM routing, agent coordination, tool call to webhook proxy
https://app.promptshuttle.com/api/mcp
Website
Connect to this Server
This is a remote MCP server — no local installation needed. Point your MCP client at:
https://app.promptshuttle.com/api/mcp Tools (7)
modify_tool
Modifies an existing function-calling tool. Only fields that are explicitly provided will be updated (partial update). Returns the updated tool.
Input Schema
{
"type": "object",
"properties": {
"toolId": {
"description": "Tool ID (ObjectId)",
"type": "string"
},
"name": {
"description": "New tool name",
"type": [
"string",
"null"
],
"default": null
},
"description": {
"description": "New tool description",
"type": [
"string",
"null"
],
"default": null
},
"toolType": {
"description": "New tool type: External, Virtual, Agent, CritiqueLoop, or Mcp",
"type": [
"string",
"null"
],
"default": null
},
"parametersJson": {
"description": "JSON string of parameters schema",
"type": [
"string",
"null"
],
"default": null
},
"webUrl": {
"description": "REST endpoint URL (External tools)",
"type": [
"string",
"null"
],
"default": null
},
"virtualToolId": {
"description": "Provider-native tool ID (Virtual tools)",
"type": [
"string",
"null"
],
"default": null
},
"agentTemplateId": {
"description": "PromptTemplate ID for agent (Agent tools)",
"type": [
"string",
"null"
],
"default": null
},
"maxAgentDepth": {
"description": "Max recursion depth (Agent tools)",
"type": [
"integer",
"null"
],
"default": null
},
"producerFlowId": {
"description": "Producer flow ID (CritiqueLoop tools)",
"type": [
"string",
"null"
],
"default": null
},
"criticFlowId": {
"description": "Critic flow ID (CritiqueLoop tools)",
"type": [
"string",
"null"
],
"default": null
},
"maxLoopIterations": {
"description": "Max loop iterations (CritiqueLoop tools)",
"type": [
"integer",
"null"
],
"default": null
}
},
"required": [
"toolId"
]
}
list_flows
Lists all flows in the tenant.
Input Schema
{
"type": "object",
"properties": {}
}
list_tools
Lists all function-calling tools in the tenant. Returns ID, name, description, tool type, and type-specific summary fields.
Input Schema
{
"type": "object",
"properties": {}
}
list_runs
Lists recent ShuttleRequests (LLM invocations) for debugging. Optionally filter by flow name. Returns up to 50 recent runs.
Input Schema
{
"type": "object",
"properties": {
"flowName": {
"description": "Filter by flow name (optional)",
"type": [
"string",
"null"
],
"default": null
},
"limit": {
"description": "Max results to return (default 20, max 50)",
"type": "integer",
"default": 20
}
}
}
get_flow
Gets full flow details including prompt templates from the active version. Falls back to the latest version if no version is activated. Use environment parameter to specify which environment's active version to retrieve. If omitted and the flow has exactly one environment, it is auto-selected.
Input Schema
{
"type": "object",
"properties": {
"flowIdOrName": {
"description": "Flow ID (ObjectId) or Name",
"type": "string"
},
"environment": {
"description": "Environment name (omit to auto-select when only one exists)",
"type": "string",
"default": ""
}
},
"required": [
"flowIdOrName"
]
}
update_flow_template
Updates a template's prompt text, response schema, and/or tool assignments in the active or latest version. If the version is locked, automatically forks it first (the fork is a draft — activate it via the UI or API). Falls back to the latest version if no version is activated. Returns confirmation with version ID and whether a fork was created.
Input Schema
{
"type": "object",
"properties": {
"flowIdOrName": {
"description": "Flow ID (ObjectId) or Name",
"type": "string"
},
"newPromptText": {
"description": "New prompt text for the system template",
"type": "string"
},
"templateName": {
"description": "Template name within the version (default: main)",
"type": "string",
"default": "main"
},
"environment": {
"description": "Environment name (omit to auto-select when only one exists)",
"type": "string",
"default": ""
},
"newUserPromptText": {
"description": "New user template text (rendered as a user message after system prompt). Pass empty string to clear.",
"type": [
"string",
"null"
],
"default": null
},
"responseSchemaJson": {
"description": "JSON string of response schema for structured outputs. Pass empty string to clear.",
"type": [
"string",
"null"
],
"default": null
},
"toolIdsJson": {
"description": "JSON array of tool ID strings to assign (e.g. '[\"id1\",\"id2\"]'). Use list_tools to find IDs. Pass '[]' to clear all tools. Omit to leave unchanged.",
"type": [
"string",
"null"
],
"default": null
}
},
"required": [
"flowIdOrName",
"newPromptText"
]
}
create_tool
Creates a new function-calling tool in the tenant. Provide name, description, parameters, toolType, and type-specific fields. toolType: External (REST endpoint), Virtual (provider-native like web_search), Agent (sub-agent), CritiqueLoop (producer+critic loop), Mcp (external MCP server). Returns the created tool with its ID.
Input Schema
{
"type": "object",
"properties": {
"name": {
"description": "Tool name",
"type": "string"
},
"description": {
"description": "Tool description",
"type": "string"
},
"toolType": {
"description": "Tool type: External, Virtual, Agent, CritiqueLoop, or Mcp",
"type": "string",
"default": "External"
},
"parametersJson": {
"description": "JSON string of parameters schema (ToolParameter object with type and properties array)",
"type": [
"string",
"null"
],
"default": null
},
"webUrl": {
"description": "REST endpoint URL (External tools)",
"type": [
"string",
"null"
],
"default": null
},
"virtualToolId": {
"description": "Provider-native tool ID e.g. web_search (Virtual tools)",
"type": [
"string",
"null"
],
"default": null
},
"agentTemplateId": {
"description": "PromptTemplate ID for agent (Agent tools)",
"type": [
"string",
"null"
],
"default": null
},
"maxAgentDepth": {
"description": "Max recursion depth (Agent tools)",
"type": [
"integer",
"null"
],
"default": null
},
"producerFlowId": {
"description": "Producer flow ID (CritiqueLoop tools)",
"type": [
"string",
"null"
],
"default": null
},
"criticFlowId": {
"description": "Critic flow ID (CritiqueLoop tools)",
"type": [
"string",
"null"
],
"default": null
},
"maxLoopIterations": {
"description": "Max loop iterations (CritiqueLoop tools)",
"type": [
"integer",
"null"
],
"default": null
}
},
"required": [
"name",
"description"
]
}
Get Verified
Add this HTML snippet to your website or README. Once verified, your server listing will receive a 'Verified' badge.
<a href="https://revuo.ai/mcp/promptshuttle">Listed on Revuo</a>