Skip to main content
Glama

system_manage

Administer and monitor FleetQ MCP server systems by managing KPIs, health checks, security policies, audit logs, cache, and global settings.

Instructions

System administration and monitoring. Actions: dashboard_kpis, health, version_check, audit_log, global_settings, blacklist, security_policy, cache_stats, cache_purge, compute, runpod, browser_relay (relay browser actions to local bridge agent).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
actionYesAction to perform: dashboard_kpis, health, version_check, audit_log, global_settings, blacklist, security_policy, cache_stats, cache_purge, compute, runpod, browser_relay
forceNoBypass the cache and fetch the latest version from GitHub immediately.
subject_typeNoFilter by subject type (e.g. experiment, agent, approval)
ocsf_class_uidNoFilter by OCSF class UID (e.g. 3002 = API Activity, 3001 = Account Change, 3006 = Financial Activity, 1001 = Process Activity, 4002 = HTTP Activity)
limitNoMax results to return (default 20, max 100)
settingsYesKey-value pairs to update. Allowed keys: assistant_llm_provider, assistant_llm_model, default_llm_provider, default_llm_model, budget_cap_credits, rate_limit_rpm, outbound_rate_limit, experiment_timeout_seconds, weekly_digest_enabled, audit_retention_days
operationYeslist: get all blacklist entries | add: add a new entry | remove: remove an entry by id
typeNoRequired for add. Type of entry to block.
valueNoRequired for add/remove. The value to block (e.g. "spam@example.com") or the entry UUID to remove.
reasonNoOptional reason for add operations. Stored for audit purposes.
policyNoRequired for update. Policy fields to set.
providerNoFilter by provider (e.g. "anthropic"). Omit to purge all.
modelNoFilter by model (e.g. "claude-sonnet-4-5-20250929"). Omit to purge all.
expired_onlyNoWhen true, only purge entries past their expiry date.
api_keyNoAPI key for credential_save
endpoint_idNoProvider endpoint/model identifier (required for health_check and run)
inputNoInput payload for run
use_syncNoUse synchronous mode for run (default: true)
timeout_secondsNoMax wait time in seconds for run (default: 90)
job_idNoJob ID returned by endpoint_run async mode (required for endpoint_status)
pod_idNoPod ID for pod_status or pod_stop
pod_configNoPod configuration for pod_create (imageName, gpuTypeIds, gpuCount, env, etc.)
toolNoBrowserMCP tool name (required for call_tool)
paramsNoTool parameters for BrowserMCP (optional for call_tool)

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