Skip to main content
Glama

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
NameRequiredDescriptionDefault
actionYesAction to perform: list, get, create, update, delete, activate, deactivate, probe_remote
statusNoFilter by status: active, disabled
platform_onlyNoIf true, return only platform-level tools (shared across all teams)
limitNoMax results to return (default 10, max 100)
tool_idYesThe tool UUID
nameYesTool name
descriptionNoTool description
typeNoTool type: mcp_stdio, mcp_http, mcp_bridge, built_in (default: mcp_stdio)mcp_stdio
transport_configNoTransport configuration (command, args, env for stdio; url, headers for http)
risk_levelNoRisk classification: safe, read, write, destructive
credential_idNoUUID of a linked Credential to use for this tool (optional; preferred over inline api_key)
network_policyNoJSON 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_idNoSet true to remove the linked credential from this tool
credential_overridesNoKey-value pairs of environment variable overrides (e.g. API keys). Values are stored encrypted.

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/escapeboy/agent-fleet-o'

If you have feedback or need assistance with the MCP directory API, please join our Discord server