Build temporal and semantic graphs for MAGMA multi-graph memory. Run after indexing documents.
AI agents invoke build_graphs to trigger actions in ClawMem. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool executes a graph-building algorithm on indexed data, which is an active computational process whose effects depend on the indexed documents provided. While it doesn't delete data (not Destructive), it constructs new structures and transforms existing data (beyond simple Read operations).
From the tool's definition Tool description states "Build temporal and semantic graphs for MAGMA multi-graph memory" and "Run after indexing documents" — this is a computational operation that constructs data structures and transforms indexed data into graph representations.
Documented attack patterns abuse exactly the kind of access build_graphs gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ClawMem, and nothing reaches the server without passing your rules. This is the rule we recommend for build_graphs:
{
"version": "1",
"default": "deny",
"tools": {
"build_graphs": {
"limits": [
{
"counter": "build_graphs_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}build_graphs stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Build temporal and semantic graphs for MAGMA multi-graph memory. Run after indexing documents. It is categorised as a Execute tool in the ClawMem MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ClawMem MCP server in PolicyLayer and add a rule for build_graphs: 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 ClawMem. Nothing to install.
build_graphs 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 build_graphs 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 build_graphs. 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.
build_graphs is provided by the ClawMem MCP server (yoloshii/clawmem). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 30 ClawMem tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
30 ClawMem tools catalogued and risk-classified — across an index of 42,500+ MCP servers.