Tavily MCP research
Use mcp__tavily-mcp__tavily_research for deep, multi-source synthesis.
When to use
- The user asks for comprehensive research, analysis, or a report.
- The answer needs synthesis across multiple sources, not just search results.
- The task is a comparison, market landscape, literature review, or strategic analysis.
For quick facts, use tavily-mcp-search. For known source URLs, use tavily-mcp-extract.
Parameters
| Parameter |
Use |
input |
Full research question or task. Include scope, region, timeframe, and comparison criteria when known. |
model |
mini, pro, or auto. Use auto by default, mini for narrow tasks, and pro for broad or high-stakes analysis. |
Model selection
| Model |
Best for |
mini |
Focused, single-topic research where speed matters. |
pro |
Multi-angle comparisons, market analysis, literature reviews, or broad reports. |
auto |
Default when the appropriate depth is unclear. |
Patterns
Focused research
Use mini for a narrow question such as what a product does, a single policy change, or a concise technology summary.
Comparative research
Use pro when comparing companies, technologies, markets, tools, regulations, or strategies.
Scoped report
Put constraints directly in input: geography, date range, audience, output format, and decision criteria.
Tips
- Research is for synthesis; do not use it when a search result or extracted page is enough.
- Ask clarifying questions first if the research scope is too broad to produce a useful report.
- Include the user's decision context in
input so the report is actionable.
- Expect research to take longer than search.
1---2name: tavily-mcp-research3description: Conduct comprehensive AI-powered research with citations through the local Tavily MCP server. Use this skill when the user wants deep research, a detailed report, comparison, market analysis, literature review, or says "research", "investigate", "analyze in depth", "compare X vs Y", or "what does the market look like for". Produces synthesized analysis grounded in web sources. For quick fact-finding, use tavily-mcp-search instead.4---56# Tavily MCP research78Use `mcp__tavily-mcp__tavily_research` for deep, multi-source synthesis.910## When to use1112- The user asks for comprehensive research, analysis, or a report.13- The answer needs synthesis across multiple sources, not just search results.14- The task is a comparison, market landscape, literature review, or strategic analysis.1516For quick facts, use `tavily-mcp-search`. For known source URLs, use `tavily-mcp-extract`.1718## Parameters1920| Parameter | Use |21| --- | --- |22| `input` | Full research question or task. Include scope, region, timeframe, and comparison criteria when known. |23| `model` | `mini`, `pro`, or `auto`. Use `auto` by default, `mini` for narrow tasks, and `pro` for broad or high-stakes analysis. |2425## Model selection2627| Model | Best for |28| --- | --- |29| `mini` | Focused, single-topic research where speed matters. |30| `pro` | Multi-angle comparisons, market analysis, literature reviews, or broad reports. |31| `auto` | Default when the appropriate depth is unclear. |3233## Patterns3435### Focused research3637Use `mini` for a narrow question such as what a product does, a single policy change, or a concise technology summary.3839### Comparative research4041Use `pro` when comparing companies, technologies, markets, tools, regulations, or strategies.4243### Scoped report4445Put constraints directly in `input`: geography, date range, audience, output format, and decision criteria.4647## Tips4849- Research is for synthesis; do not use it when a search result or extracted page is enough.50- Ask clarifying questions first if the research scope is too broad to produce a useful report.51- Include the user's decision context in `input` so the report is actionable.52- Expect research to take longer than search.
minhngoc25a