// MCP TOOL REFERENCE

HARNESS RESEARCH MCP TOOLS

3 tools from the Harness Research MCP MCP Server, categorised by risk level.

View the Harness Research MCP policy →
// ALL 3 HARNESS RESEARCH MCP TOOLS
READ 2 tools
Read harness_search Quick multi-source search without generating a full report. Returns structured results from Tavily, Brave, ... Read harness_status Check the progress of a research task started by harness_research. After calling harness_research, you MUS...
EXECUTE 1 tools
Execute harness_research Start a deep research session: multi-source search (Tavily/Brave/arXiv/PubMed/Tushare) + CRAAP source evalu...

Route Harness Research MCP through PolicyLayer and every one of its 3 tools is checked against your policy before it runs.

CHECK YOUR STACK →

See every tool, the dangerous ones, and the token cost across your stack.

// FAQ
How many tools does the Harness Research MCP MCP server have? +

The Harness Research MCP MCP server exposes 3 tools across 2 categories: Read, Execute.

How do I enforce policies on Harness Research MCP tools? +

Route the Harness Research MCP server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Harness Research MCP tools fall into? +

Harness Research MCP tools are categorised as Read (2), Execute (1). Each category has a recommended default policy.

Enforce policy on every Harness Research MCP tool call.

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.

CHECK YOUR STACK →

Free to start. No card required.

43,000+ MCP servers and 220,000+ tools scanned and risk-classified.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.