Harness Research MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KIMI_API_KEY | No | Kimi LLM API key. Required if OPENROUTER_API_KEY is not set. | |
| NCBI_API_KEY | No | Optional API key for PubMed academic paper search. | |
| BRAVE_API_KEY | No | Brave search API key. Required if TAVILY_API_KEY is not set. | |
| TUSHARE_TOKEN | No | Optional token for Chinese A-share financial data. | |
| TAVILY_API_KEY | No | Tavily search API key. Required if BRAVE_API_KEY is not set. | |
| OPENROUTER_API_KEY | No | OpenRouter LLM API key. Required if KIMI_API_KEY is not set. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| harness_researchA | Start a deep research session: multi-source search (Tavily/Brave/arXiv/PubMed/Tushare) + CRAAP source evaluation + cross-verification → professional HTML/DOCX/PDF report. IMPORTANT: This tool returns IMMEDIATELY with a task_id. The research runs in the background and takes ~8-12 minutes. After calling this tool, you MUST poll harness_status with the returned task_id every 30-60 seconds until status is "completed" or "failed". Do NOT wait idle — poll actively. Workflow:
Driven by affordable models like Kimi K2.5 (~$0.01/run). |
| harness_searchA | Quick multi-source search without generating a full report. Returns structured results from Tavily, Brave, arXiv, and PubMed. Completes in seconds. |
| harness_statusA | Check the progress of a research task started by harness_research. After calling harness_research, you MUST poll this tool with the returned task_id every 30-60 seconds.
If no task_id is provided, lists all tasks. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/Nimo1987/harness-research'
If you have feedback or need assistance with the MCP directory API, please join our Discord server