Quick multi-source search without generating a full report. Returns structured results from Tavily, Brave, arXiv, and PubMed. Completes in seconds.
AI agents call harness_search to retrieve information from Harness Research MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a search and aggregation tool that queries external data sources and returns results. It has no side effects—it does not create, modify, delete, execute code, or commit financial transactions. The operation is read-only retrieval of information from public research and search APIs. Severity is low because misuse would only expose publicly available information, not cause damage.
From the tool's definition Tool description states it 'Returns structured results' from multiple search sources (Tavily, Brave, arXiv, PubMed) and performs 'Quick multi-source search.' It retrieves and aggregates data without modifying or deleting anything.
Documented attack patterns abuse exactly the kind of access harness_search gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Harness Research MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for harness_search:
{
"version": "1",
"default": "deny",
"tools": {
"harness_search": {}
}
}harness_search 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.
Quick multi-source search without generating a full report. Returns structured results from Tavily, Brave, arXiv, and PubMed. Completes in seconds. It is categorised as a Read tool in the Harness Research MCP MCP Server, which means it retrieves data without modifying state.
Register the Harness Research MCP server in PolicyLayer and add a rule for harness_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 Harness Research MCP. Nothing to install.
harness_search 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 harness_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 harness_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.
harness_search is provided by the Harness Research MCP server (nimo1987/harness-research). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Harness Research 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.
3 Harness Research MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.