You can connect one or more MCP servers to an AI agent to extend its capabilities. Once connected, the agent can use the tools, resources, and prompts exposed by the selected MCP server at runtime...
MCP resources are read-only files from Celigo file storage that an MCP server exposes to your agent. When you add resources to an agent, the agent can read those files at runtime to ground its dec...
MCP resources are read-only files from Celigo file storage that you expose to AI agents through an MCP server. When an agent is connected to an MCP server with resources configured, it can list av...
Use the Celigo Platform MCP or the Celigo CLI to manage your integrator.io account without the UI. Both tools operate on the same resources as the REST API. This article explains what each tool do...
Tools participate in ILM the same way flows and integrations do. Use ILM to move tool changes safely between environments, such as sandbox, staging, and production. Tool definitions, dependencies,...
You can now call reusable tools directly from flows using the Tool import step with full error visibility and retry support, allowing you to reuse shared logic across integrations without rebuildi...
The Access tab replaces the Access token tab. You can use this tab to manage how users and clients authenticate with an MCP server. You can select Celigo as the built-in identity provider, or conf...
Connect AI tools like Claude (desktop), Cursor (desktop), or any MCP-compatible client to Celigo in minutes using built-in OAuth without any custom authentication setup required. Celigo uses your ...
This article explains adding users, viewing access, removing access, and granting access to all MCP servers. When an MCP server uses Celigo as the identity provider, you control which users can co...
MCP prompts are reusable, server-defined message templates that resolve into a sequence of chat messages. You can use prompts to standardize how the model receives instructions and reuse that patt...