//001
Import API Docs, Auto-Generate Connectors
Import OpenAPI spec files (YAML, JSON, or URL), and the system auto-parses interface definitions, generating complete connectors with all Actions in one go.
Create System Integrations Through Conversation
[n.01/03]> Connector Platform
Connectors are the core of FIM One. A connector represents an external system's interface — Agent reads and writes data through connectors, and the platform auto-handles authentication and request management.
[n.02/03]> Capabilities
//002
Create Connectors via AI Conversation
No standard API docs? No problem. In the Action editor's built-in AI panel, describe your interface needs in natural language: Describe requirements → AI generates Action configuration Suggest modifications → AI iterates and optimizes Supports completing the entire connector creation through conversation
//003
Leverage Community System Adapters (MCP Integration)
Native support for Model Context Protocol (MCP). Connect any MCP Server as Agent tools. Third-party MCP ecosystem works out of the box.
//004
Database Connectors
Direct SQL access to PostgreSQL, MySQL, Oracle, SQL Server, and Chinese domestic databases (DM, KingbaseES, GBase, Highgo). Schema introspection, AI-powered annotation, read-only query execution, and encrypted credentials at rest.
//005
Connector Progressive Disclosure
A single ConnectorMetaTool replaces per-action tools. The system prompt receives lightweight stubs only (name + one-line description, ~30 tokens per connector vs ~250 tokens per action). Agent calls discover(connector) to load full action schema on demand.
//006
Import / Export / Fork
Share connector templates as JSON files. Clone and customize existing connectors to quickly bootstrap new integrations without starting from scratch.
//007
Semantic Schema Annotations
Extend connector schema fields with semantic_tag, description, and pii flags. Annotations are surfaced in LLM tool descriptions, enabling the model to understand field semantics and handle sensitive data appropriately.
//008
Per-User Credentials with Encryption
Dedicated connector_credentials table with Fernet encryption. Each user can store their own credentials for shared connectors. The allow_fallback flag controls whether the connector's default credentials are used when user-specific credentials are absent.
//009
Connector Toggle
Suspend and resume connectors without deleting them. Temporarily disable a connector to prevent Agent from using it, then re-enable when ready, no reconfiguration needed.
//010
Automatic Credential Handling
Connectors support multiple authentication methods, automatically injected at runtime: Bearer Token API Key (Custom Header) Basic Auth (Username + Password) Token Exchange (e.g., Feishu tenant_access_token) OAuth 2.0
[n.03/03]> Related
/ Related Platform Capabilities /
// [#connect]// [#orchestrate]// [#review]// [#connect]// [#orchestrate]// [#review]// [#connect]// [#orchestrate]// [#review]
// [#connect]// [#orchestrate]// [#review]// [#connect]// [#orchestrate]// [#review]// [#connect]// [#orchestrate]// [#review]
Two ways to run