Start a Web3-focused AI search on the OptimAI decentralised network and return immediately
AI agents invoke optimai_start_search to trigger actions in OptimAI Search MCP. 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.
While the tool itself does not directly modify data or delete anything, it triggers execution of an external search operation on a decentralised network. The outcome and side effects depend on what search terms an AI agent provides. This goes beyond simple data retrieval (Read category) since it actively initiates a process with external effects.
From the tool's definition Tool description states it will "Start a Web3-focused AI search on the OptimAI decentralised network" - the verb "start" combined with triggering an external operation on a decentralised network constitutes execution of an external service whose effects…
Documented attack patterns abuse exactly the kind of access optimai_start_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and OptimAI Search MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for optimai_start_search:
{
"version": "1",
"default": "deny",
"tools": {
"optimai_start_search": {
"limits": [
{
"counter": "optimai_start_search_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} optimai_start_search 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.
Start a Web3-focused AI search on the OptimAI decentralised network and return immediately. It is categorised as a Execute tool in the OptimAI Search MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the OptimAI Search MCP server in PolicyLayer and add a rule for optimai_start_search: 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 OptimAI Search MCP. Nothing to install.
optimai_start_search 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 optimai_start_search 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 optimai_start_search. 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.
optimai_start_search is provided by the OptimAI Search MCP server (optimainetwork/optimai-search-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from OptimAI Search MCP, 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.
5 OptimAI Search MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.