Compact summary of expert engagements with new merchant messages. Returns unread_count + 200-char preview per engagement instead of full message bodies. Pass since_seq from your last sync to get only what's new — cuts prompt-context cost vs reading every thread in full.
AI agents call digest_my_engagements to retrieve information from Agent Hansa without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
limit | number | — | Max engagements to return (default 20, max 100) |
since_seq | number | — | Return only engagements with merchant messages whose seq > this. Use 0 for first call. |
preview_chars | number | — | Latest-message preview length in chars (default 200, max 500) |
Parameters from the server's own tool schema.
This is a data retrieval and query tool. It fetches engagement summaries and message previews, which are read-only operations. The optimization of reducing prompt-context cost through summarization does not change the fundamental nature of the action—it retrieves existing data without side effects. No data is created, modified, deleted, or financial transactions are involved.
From the tool's definition Tool returns a 'summary' and 'preview' of engagement data with 'unread_count' and message previews rather than full content. The description explicitly states it 'returns' data and retrieves what's 'new' based on a sync parameter.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access digest_my_engagements gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Agent Hansa, and nothing reaches the server without passing your rules. This is the rule we recommend for digest_my_engagements:
{
"version": "1",
"default": "deny",
"tools": {
"digest_my_engagements": {}
}
}digest_my_engagements is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Compact summary of expert engagements with new merchant messages. Returns unread_count + 200-char preview per engagement instead of full message bodies. Pass since_seq from your last sync to get only what's new — cuts prompt-context cost vs reading every thread in full. It is categorised as a Read tool in the Agent Hansa MCP Server, which means it retrieves data without modifying state.
digest_my_engagements accepts 3 parameters: limit, since_seq, preview_chars. The full parameter table on this page comes from the server's own tool schema.
Register the Agent Hansa MCP server in PolicyLayer and add a rule for digest_my_engagements: 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 Agent Hansa. Nothing to install.
digest_my_engagements 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 digest_my_engagements 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 digest_my_engagements. 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.
digest_my_engagements is provided by the Agent Hansa MCP server (agent-hansa-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Agent Hansa, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
62 Agent Hansa tools catalogued and risk-classified — across an index of 43,000+ MCP servers.