tool_manage
Manage MCP tools in FleetQ server: list, create, update, delete, activate, deactivate, and test remote servers to control AI agent capabilities.
Instructions
Manage LLM tools (MCP servers, built-in). Actions: list, get (tool_id), create, update, delete, activate, deactivate, probe_remote (url — test remote MCP server). Note: discover_mcp and import_mcp are not available in cloud.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | Action to perform: list, get, create, update, delete, activate, deactivate, probe_remote | |
| status | No | Filter by status: active, disabled | |
| platform_only | No | If true, return only platform-level tools (shared across all teams) | |
| limit | No | Max results to return (default 10, max 100) | |
| tool_id | Yes | The tool UUID | |
| name | Yes | Tool name | |
| description | No | Tool description | |
| type | No | Tool type: mcp_stdio, mcp_http, mcp_bridge, built_in (default: mcp_stdio) | mcp_stdio |
| transport_config | No | Transport configuration (command, args, env for stdio; url, headers for http) | |
| risk_level | No | Risk classification: safe, read, write, destructive | |
| credential_id | No | UUID of a linked Credential to use for this tool (optional; preferred over inline api_key) | |
| network_policy | No | JSON string defining egress rules for Docker sandbox (built_in bash only). Example: {"rules":[{"protocol":"tcp","host":"api.example.com","port":443}],"default_action":"deny"} | |
| clear_credential_id | No | Set true to remove the linked credential from this tool | |
| credential_overrides | No | Key-value pairs of environment variable overrides (e.g. API keys). Values are stored encrypted. |