Tavily Web Search MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TAVILY_API_KEY | Yes | Your Tavily API key |
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| web_searchC | Search the web for information about the given query |
| roll_diceC | Roll the dice with the given notation |
| get_exchange_rateB | Get the latest exchange rates from provided base currency code (ISO 4217) to all other supported currencies |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool has a clearly distinct and non-overlapping purpose: get_exchange_rate handles currency conversion, roll_dice performs random dice rolls, and web_search conducts internet searches. There is no ambiguity in their functions, making it easy for an agent to select the correct tool for each task.
The naming conventions are mixed and not fully consistent. get_exchange_rate and web_search follow a verb_noun pattern, but roll_dice uses a verb_noun format without an underscore. While all names are readable, the deviation in roll_dice breaks a consistent pattern, leading to a moderate score.
With only 3 tools, the count feels too thin for a server labeled 'Tavily Web Search MCP Server', as it suggests a broader scope than just web search. The inclusion of unrelated tools like get_exchange_rate and roll_dice makes the set seem incomplete or mismatched, lacking focus on a cohesive domain.
There are significant gaps in the tool surface for the implied domain of web search. While web_search is present, there are no complementary tools for refining searches, handling results, or managing search history. The unrelated tools (exchange rates and dice) do not contribute to a coherent workflow, leaving the core functionality underdeveloped.