get_activity_health
Audit all agent activities for staleness, business outcome alignment, and cross-agent overlap. Shows per-activity run count, quality scores, approval rates, and flags activities that may need retirement or adjustment. Use this to apply first principles: question every activity before optimizing it.
This record as markdown: /tools/com-getfreedomos-freedom-mcp/get-activity-health.md
What get_activity_health does on Freedom Mcp
AI agents call get_activity_health to retrieve information from Freedom Mcp without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
companyId | string | Yes | FreedomOS company id to act within (you must be a member). Required for company-scoped tools. |
company_id | string | — | Company ID to audit. Usually auto-injected from context. |
Parameters from the server's own tool schema.
Why get_activity_health is rated Low
This tool retrieves and analyzes metadata about agent activities without modifying any data. While it performs analysis and flagging, these are informational outputs intended to inform decision-making, not to execute changes. No side effects occur beyond producing a read-only audit report. It falls cleanly into the Read category.
From the tool's definition Tool description uses audit/observational language: 'Audit all agent activities', 'Shows per-activity run count, quality scores, approval rates, and flags activities'. No mutations, writes, deletions, or external operations are performed.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
The rule that runs get_activity_health safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Freedom Mcp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For get_activity_health, this is the rule to start with:
get_activity_health is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Freedom Mcp, apply this rule, and every get_activity_health call is checked against it from then on.
Questions about get_activity_health
Audit all agent activities for staleness, business outcome alignment, and cross-agent overlap. Shows per-activity run count, quality scores, approval rates, and flags activities that may need retirement or adjustment. Use this to apply first principles: question every activity before optimizing it. It is categorised as a Read tool in the Freedom Mcp MCP Server, which means it retrieves data without modifying state.
get_activity_health accepts 2 parameters: companyId, company_id. Required: companyId. The full parameter table on this page comes from the server's own tool schema.
Register the Freedom MCP server in PolicyLayer and add a rule for get_activity_health: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Freedom Mcp. Nothing to install.
get_activity_health is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_activity_health rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_activity_health. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_activity_health is provided by the Freedom MCP server (https://twuluxmoognlwtmaoqgo.supabase.co/functions/v1/freedom-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Freedom, and thousands of servers like it.
This server
Across the catalogue