Store conversation in memory for future reference. USE THIS TOOL: At the END of every conversation after fully answering the user. WHAT TO STORE: 1) User's question or request, 2) Your solution or explanation, 3) Important decisions made, 4) Key insights discovered. HOW TO USE: Put the entire con...
Risk signalsBulk/mass operation — affects multiple targets
Part of the Core server.
Free to start. No card required.
AI agents invoke memory_ingest to trigger processes or run actions in Core. Execute operations can have side effects beyond the immediate call -- triggering builds, sending notifications, or starting workflows. Rate limits and argument validation are essential to prevent runaway execution.
memory_ingest can trigger processes with real-world consequences. An uncontrolled agent might start dozens of builds, send mass notifications, or kick off expensive compute jobs. PolicyLayer enforces rate limits and validates arguments to keep execution within safe bounds.
Execute tools trigger processes. Rate-limit and validate arguments to prevent unintended side effects.
{
"version": "1",
"default": "deny",
"tools": {
"memory_ingest": {
"limits": [
{
"counter": "memory_ingest_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}See the full Core policy for all 9 tools.
These attack patterns abuse exactly the kind of access memory_ingest gives an agent. Each links to the full case and the policy that stops it:
Other execute tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
Store conversation in memory for future reference. USE THIS TOOL: At the END of every conversation after fully answering the user. WHAT TO STORE: 1) User's question or request, 2) Your solution or explanation, 3) Important decisions made, 4) Key insights discovered. HOW TO USE: Put the entire conversation summary in the 'message' field. IMPORTANT: You MUST provide a sessionId - if you don't have one, call initialize_conversation_session tool FIRST to obtain it at the start of the conversation, then use that SAME sessionId for all memory_ingest calls. Optionally add spaceIds array to organize by project. Returns: Success confirmation with storage ID.. It is categorised as a Execute tool in the Core MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Core MCP server in PolicyLayer and add a rule for memory_ingest: 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 Core. Nothing to install.
memory_ingest is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the memory_ingest 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 memory_ingest. 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.
memory_ingest is provided by the Core MCP server (@transcend-io/mcp-server-core). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 9 Core tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.