Run a federated knowledge search (research_search v2 — 10 curated public APIs, RRF-fused) and synthesize the top-K results into a careful, citation-bearing analysis using the configured open-source model (CELIUMS_LLM_MODEL, routed via Atlas — never a closed model). Output explicitly distinguishes...
AI agents invoke research_synthesize to trigger actions in Celiums Memory. 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.
This tool actively triggers external operations: it queries 10 curated public APIs (federated search), routes results through an LLM model for synthesis, and writes a log entry to the project session. It is not a simple read/query — it orchestrates external API calls and model inference, with side effects (session logging).
From the tool's definition 'Run a federated knowledge search... and synthesize the top-K results into a careful, citation-bearing analysis using the configured open-source model... routed via Atlas'. Also 'Logs the query into the project session log.'
Documented attack patterns abuse exactly the kind of access research_synthesize 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_synthesize:
{
"version": "1",
"default": "deny",
"tools": {
"research_synthesize": {
"limits": [
{
"counter": "research_synthesize_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}research_synthesize 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.
Run a federated knowledge search (research_search v2 — 10 curated public APIs, RRF-fused) and synthesize the top-K results into a careful, citation-bearing analysis using the configured open-source model (CELIUMS_LLM_MODEL, routed via Atlas — never a closed model). Output explicitly distinguishes well-supported claims from claims it cannot back up with the retrieved evidence. Logs the query into the project session log. It is categorised as a Execute tool in the Celiums Memory MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Celiums Memory MCP server in PolicyLayer and add a rule for research_synthesize: 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_synthesize 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 research_synthesize 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_synthesize. 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_synthesize 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.