sap_memory_summarize
Free local tool. Creates an LLM-compressed summary memory from tool call patterns. The agent calls this after analyzing search results to persist lessons, patterns, failures, or successes. No x402 charge. SAP MCP execution guidance: Intent: SAP MCP tool workflow. Pricing: free; call directly with...
This record as markdown: /tools/oobe-protocol-labs-sap-mcp-server/sap-memory-summarize.md
What sap_memory_summarize does on Sap
AI agents call sap_memory_summarize to retrieve information from Sap 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 |
|---|---|---|---|
summary | string | Yes | LLM-compressed summary text. Max 4KB. |
category | string | Yes | Tool category (e.g. "jupiter", "adrena", "premium"). |
expiresAt | string | — | ISO 8601 expiry. Null = never expires. |
relevance | number | — | Initial relevance score 0-1. Default 0.8. |
memoryType | string | Yes | Type of memory. |
sourceToolCalls | string | — | JSON array of tool_call IDs that were the source. |
Parameters from the server's own tool schema.
Why sap_memory_summarize is rated Low
Even though sap_memory_summarize only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs sap_memory_summarize safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Sap, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For sap_memory_summarize, this is the rule to start with:
sap_memory_summarize 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 Sap, apply this rule, and every sap_memory_summarize call is checked against it from then on.
Questions about sap_memory_summarize
Free local tool. Creates an LLM-compressed summary memory from tool call patterns. The agent calls this after analyzing search results to persist lessons, patterns, failures, or successes. No x402 charge. SAP MCP execution guidance: Intent: SAP MCP tool workflow. Pricing: free; call directly without x402. Routing: free hosted call; call directly and keep it small/exact when possible. Signer boundary: hosted reads/builders never receive keypair bytes; value-moving results must be finalized locally when signing is required. It is categorised as a Read tool in the Sap MCP Server, which means it retrieves data without modifying state.
sap_memory_summarize accepts 6 parameters: summary, category, expiresAt, relevance, memoryType, sourceToolCalls. Required: summary, category, memoryType. The full parameter table on this page comes from the server's own tool schema.
Register the Sap MCP server in PolicyLayer and add a rule for sap_memory_summarize: 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 Sap. Nothing to install.
sap_memory_summarize 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 sap_memory_summarize 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 sap_memory_summarize. 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.
sap_memory_summarize is provided by the Sap MCP server (https://mcp.sap.oobeprotocol.ai/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Sap, and thousands of servers like it.
This server
Across the catalogue