Skip to main content
Glama

Cloud System Manage Tool

system_manage

Monitor platform health, view KPIs and audit logs, and manage global settings, security policies, cache, compute providers, and browser relays.

Instructions

Platform system administration, monitoring, and infrastructure control — KPIs, health checks, audit log, semantic cache, GPU compute providers, browser-relay bridge. Mixed permission tiers: read actions (dashboard_kpis, health, version_check, audit_log, cache_stats) need any authenticated user; write actions marked PLATFORM ADMIN require the user's is_super_admin=true flag (HTTP 403 otherwise). Every write is audit-logged.

When to use: agent monitoring platform health, on-call investigating an incident via audit log, super-admin adjusting platform-wide settings or purging the semantic cache after a model swap. Do NOT use for tenant-level operations — those have dedicated tools (e.g. team_manage).

Read actions:

  • dashboard_kpis — { active_users, runs_today, spend_today_credits, ... }.

  • health — { status: ok|degraded|down, db, cache, queue, providers[] }.

  • version_check — { current, latest, update_available }.

  • audit_log — optional: actor_id, action, entity_type, since, limit (max 100). Cursor-paginated.

  • cache_stats — semantic cache hit/miss/savings since last purge.

Write actions:

  • global_settings (write — PLATFORM ADMIN) — settings object. Replaces platform-wide settings.

  • blacklist (write — PLATFORM ADMIN) — sub-actions: list, add, remove. Affects email/domain blocklists for sign-ups.

  • security_policy (write — PLATFORM ADMIN) — sub-actions: list, save, delete on security policies.

  • cache_purge (DESTRUCTIVE — PLATFORM ADMIN) — purges semantic cache CROSS-TEAM. All teams lose cached LLM responses; first calls after purge will be slower and more expensive.

  • compute (write — PLATFORM ADMIN) — sub-actions on compute provider records (Replicate, Fal.ai, Vast.ai, RunPod).

  • runpod (write — PLATFORM ADMIN, costs real $) — sub-actions on RunPod GPU pods. Spinning up a pod bills the platform Stripe account immediately at the pod's per-minute rate.

  • browser_relay (write — relays through local bridge) — sub-actions for browser automation through the team's connected FleetQ Bridge runner. Requires an active bridge.

Errors: 401, 403 (insufficient role for PLATFORM ADMIN action), 404, 422, 429, 503 (provider down).

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
deadline_msNoOptional: max wall-clock time (ms) the tool may spend. If exceeded during the call, returns a DEADLINE_EXCEEDED error. Minimum 100 ms. Leave unset for no deadline.
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)
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description fully carries the burden. It details permission tiers (any authenticated user for reads, is_super_admin=true for writes), audits logging on writes, and specific behavioral consequences like cache_purge causing cross-team cache loss with performance/cost impacts, and runpod incurring immediate billing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with headers for read/write actions, bullet points, and clear sections. It is longer due to high complexity but every section earns its place. Slight redundancy could be trimmed, but overall efficient for the scope.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (25 parameters, no output schema, nested objects), the description is remarkably complete: it covers all actions, permissions, error codes, and behavioral traits. The only minor omission is not explicitly stating output formats, but that is implied for a system tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, baseline 3. The description adds value by grouping actions into read/write and explaining the meaning of sub-actions beyond enum labels (e.g., 'blacklist' sub-actions list/add/remove). However, many parameter details are already covered in the schema, so the marginal gain is moderate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool as 'Platform system administration, monitoring, and infrastructure control' and lists specific actions (KPIs, health checks, audit log, etc.). It explicitly distinguishes from sibling tools by stating 'Do NOT use for tenant-level operations — those have dedicated tools (e.g. team_manage).'

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit when-to-use examples: 'agent monitoring platform health, on-call investigating an incident via audit log, super-admin adjusting platform-wide settings or purging the semantic cache after a model swap.' It also gives exclusion guidance: 'Do NOT use for tenant-level operations' and points to a specific alternative tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

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