Compress a raw session dump into structured short-term, medium-term, and long-term memory. Stateless — we never store your data. Send your existing memory files (if any) plus the new session dump, get back updated structured memory. First 5 compressions free, then $0.03 USDC via x402. Args: ...
Part of the Agent Infrastructure MCP server. Enforce policies on this tool with Intercept, the open-source MCP proxy.
AI agents use compress_memory to create or modify resources in Agent Infrastructure. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call compress_memory repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Agent Infrastructure.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
tools:
compress_memory:
rules:
- action: allow
rate_limit:
max: 30
window: 60See the full Agent Infrastructure policy for all 6 tools.
Agents calling write-class tools like compress_memory have been implicated in these attack patterns. Read the full case and prevention policy for each:
Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.
Compress a raw session dump into structured short-term, medium-term, and long-term memory. Stateless — we never store your data. Send your existing memory files (if any) plus the new session dump, get back updated structured memory. First 5 compressions free, then $0.03 USDC via x402. Args: agent_id: Your unique agent identifier (used for free tier tracking only) session_dump: Raw session content — conversation logs, decisions, observations, anything from this work session existing_memory: Your current memory from a previous compression. Include short_term, medium_term, long_term fields. Omit on first use. session_metadata: Optional info about the session — task_type, duration_minutes, tools_used. It is categorised as a Write tool in the Agent Infrastructure MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Add a rule in your Intercept YAML policy under the tools section for compress_memory. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the Agent Infrastructure MCP server.
compress_memory is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the compress_memory rule in your Intercept 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 Intercept policy for compress_memory. 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.
compress_memory is provided by the Agent Infrastructure MCP server (getkin/agent-infrastructure). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.