List the sources attached to a research project (id, kind, name, uri, bytes, chunk_count, status, added_at). All local to the user.
AI agents call research_source_list to retrieve information from Celiums 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 displays metadata about research project sources without creating, modifying, deleting, or executing any operations. It is scoped to user-local data, presenting no destructive, financial, or code execution risks. The low severity reflects that source listing poses minimal security risk—it is purely informational querying of existing project attachments.
From the tool's definition Tool description explicitly states it 'List the sources' with retrieval of metadata fields (id, kind, name, uri, bytes, chunk_count, status, added_at).
Documented attack patterns abuse exactly the kind of access research_source_list 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_list:
{
"version": "1",
"default": "deny",
"tools": {
"research_source_list": {}
}
}research_source_list is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
List the sources attached to a research project (id, kind, name, uri, bytes, chunk_count, status, added_at). All local to the user. It is categorised as a Read tool in the Celiums Memory MCP Server, which means it retrieves data without modifying state.
Register the Celiums Memory MCP server in PolicyLayer and add a rule for research_source_list: 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_list 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 research_source_list 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_list. 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_list 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.