Run a Web3-focused AI search on the OptimAI decentralised network.
AI agents invoke optimai_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.
The tool actively triggers an external operation on a decentralised network rather than simply retrieving pre-existing data. It initiates a search job/process on an external system, making it Execute rather than Read. Misuse could result in unintended queries being dispatched to the network, but blast radius is moderate since no data is modified or deleted.
From the tool's definition "Run a Web3-focused AI search on the OptimAI decentralised network"
Documented attack patterns abuse exactly the kind of access optimai_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_search:
{
"version": "1",
"default": "deny",
"tools": {
"optimai_search": {
"limits": [
{
"counter": "optimai_search_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}optimai_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.
Run a Web3-focused AI search on the OptimAI decentralised network. 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_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_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_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_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_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.