Record an atomic claim with its evidence into the project. Each finding has a source kind (arxiv|wiki|curated|web), an optional ref/url, a confidence 0-1, and free-text notes. Findings are the building blocks; export consolidates them into a memo.
AI agents use research_finding_add to create or update resources in Celiums Memory — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Celiums Memory environment.
This tool creates or modifies data reversibly by adding new findings to a project repository. Users can later update, remove, or export these records. It does not irreversibly delete data, execute arbitrary code, move money, or perform other severe actions. Write category is appropriate because the tool's primary function is to store structured information with metadata.
From the tool's definition Tool creates new records ('Record an atomic claim') that are persisted in the project ('into the project'). The description indicates findings are stored as persistent data structures with multiple fields (source kind, ref/url, confidence, notes).
Documented attack patterns abuse exactly the kind of access research_finding_add 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_finding_add:
{
"version": "1",
"default": "deny",
"tools": {
"research_finding_add": {
"limits": [
{
"counter": "research_finding_add_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}research_finding_add stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Record an atomic claim with its evidence into the project. Each finding has a source kind (arxiv|wiki|curated|web), an optional ref/url, a confidence 0-1, and free-text notes. Findings are the building blocks; export consolidates them into a memo. It is categorised as a Write tool in the Celiums Memory MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Celiums Memory MCP server in PolicyLayer and add a rule for research_finding_add: 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_finding_add 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 research_finding_add 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_finding_add. 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_finding_add 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.