Surface explicit commitments derived from tracked next steps and dated, attributable source text. Use this when you want to review open, at-risk, overdue, or recently completed follow-through items rather than rely on fuzzy prose search.\n\nIf this is your first memory operation in this conversat...
AI agents call memory_commitments to retrieve information from Munin Memory without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries stored commitment data to display tracked items in various states (open, at-risk, overdue, completed). It is a read-only operation with no side effects on the underlying data. The low severity reflects minimal risk even if misused—an agent could only retrieve information about commitments, not create false ones or delete real ones.
From the tool's definition Tool name includes 'surface' and 'review' of commitments; description states 'when you want to review' existing items. No mention of creation, modification, or deletion of commitments.
Attacks that exploit this kind of access
Surface explicit commitments derived from tracked next steps and dated, attributable source text. Use this when you want to review open, at-risk, overdue, or recently completed follow-through items rather than rely on fuzzy prose search.\n\nIf this is your first memory operation in this conversation, call memory_orient first. It is categorised as a Read tool in the Munin Memory MCP Server, which means it retrieves data without modifying state.
Register the Munin Memory MCP server in PolicyLayer and add a rule for memory_commitments: 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 Munin Memory. Nothing to install.
memory_commitments 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 memory_commitments 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_commitments. 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_commitments is provided by the Munin Memory MCP server (magnus-gille/munin-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →