Delete a source (and its chunks) from a research project.
AI agents call research_source_delete to permanently remove resources in Celiums Memory — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool permanently removes research data and cannot be undone. While the blast radius is scoped to a single research project's source (limiting severity to 'high' rather than 'critical'), the irreversible nature of deletion and inability to recover deleted chunks places it squarely in the Destructive category, which takes precedence over Write operations that merely modify data reversibly.
From the tool's definition Tool description explicitly states 'Delete a source (and its chunks)' — this irreversibly removes data from a research project. The verb 'delete' combined with cascading deletion of associated chunks indicates a non-reversible destructive operation.
Documented attack patterns abuse exactly the kind of access research_source_delete gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Celiums Memory, and nothing reaches the server without passing your rules. This is the rule we recommend for research_source_delete:
{
"version": "1",
"default": "deny",
"hide": [
"research_source_delete"
]
}research_source_delete disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
Delete a source (and its chunks) from a research project. It is categorised as a Destructive tool in the Celiums Memory MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Celiums Memory MCP server in PolicyLayer and add a rule for research_source_delete: 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 Celiums Memory. Nothing to install.
research_source_delete is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the research_source_delete 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 research_source_delete. 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.
research_source_delete is provided by the Celiums Memory MCP server (terrizoaguimor/celiums-memory). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Celiums Memory, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
62 Celiums Memory tools catalogued and risk-classified — across an index of 43,000+ MCP servers.