Skip to main content
Glama
vinitv

Tavily Web Search MCP Server

by vinitv
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

AI Makerspace: MCP Session Repo for Session 13

This project is a demonstration of the MCP (Model Context Protocol) server, which utilizes the Tavily API for web search capabilities. The server is designed to run in a standard input/output (stdio) transport mode.

Related MCP server: Tavily Web Search MCP Server

Project Overview

The MCP server is set up to handle web search queries using the Tavily API. It is built with the following key components:

  • TavilyClient: A client for interacting with the Tavily API to perform web searches.

Prerequisites

  • Python 3.13 or higher

  • A valid Tavily API key

⚠️NOTE FOR WINDOWS:⚠️

You'll need to install this on the Windows side of your OS.

This will require getting two CLI tool for Powershell, which you can do as follows:

  • winget install astral-sh.uv

  • winget install --id Git.Git -e --source winget

After you have those CLI tools, please open Cursor into Windows.

Then, you can clone the repository using the following command in your Cursor terminal:

git clone https://AI-Maker-Space/AIE7-MCP-Session.git

After that, you can follow from Step 2. below!

Installation

  1. Clone the repository:

    git clone <repository-url>
cd <repository-directory>

  2. Configure environment variables: Copy the .env.sample to .env and add your Tavily API key:

    TAVILY_API_KEY=your_api_key_here

  3. 🏗️ Add a new tool to your MCP Server 🏗️

Create a new tool in the server.py file, that's it!

Running the MCP Server

To start the MCP server, you will need to add the following to your MCP Profile in Cursor:

NOTE: To get to your MCP config. you can use the Command Pallete (CMD/CTRL+SHIFT+P) and select "View: Open MCP Settings" and replace the contents with the JSON blob below.

{
    "mcpServers":  {
        "mcp-server": {
            "command" : "uv",
            "args" : ["--directory", "/PATH/TO/REPOSITORY", "run", "server.py"]
        }
    }
}

The server will start and listen for commands via standard input/output.

Usage

The server provides a web_search tool that can be used to search the web for information about a given query. This is achieved by calling the web_search function with the desired query string.

Activities:

There are a few activities for this assignment!

🏗️ Activity #1:

Choose an API that you enjoy using - and build an MCP server for it!

✅ Answer:

Check server.py

🏗️ Activity #2:

Build a simple LangGraph application that interacts with your MCP Server.

You can find details here!

✅ Answer:

Activity 2

Available Tools

3 tools
repair_costC

Get repair cost estimate for home repairs

ParametersJSON Schema
NameRequiredDescriptionDefault
repair_typeYes
zip_codeYes

TDQS

C2.8/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden for behavioral disclosure. While 'Get' implies a read operation, the description doesn't disclose important behavioral traits like whether this is an estimate vs. actual cost, data source, accuracy limitations, rate limits, authentication needs, or what happens when invalid inputs are provided. This is inadequate for a tool with no annotation coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with zero waste. It's appropriately sized for a simple tool and front-loads the core purpose immediately. Every word earns its place in communicating the essential function.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity (2 required parameters, no annotations, no output schema), the description is incomplete. It doesn't explain what the tool returns, how estimates are calculated, error conditions, or parameter requirements. For a tool with no structured metadata, the description should provide more contextual information to guide proper usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description must compensate by explaining parameter semantics, but it provides no information about the two required parameters (repair_type, zip_code). It doesn't explain what values are expected, formats, constraints, or examples. The description adds no value beyond what the bare schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb ('Get') and resource ('repair cost estimate for home repairs'), making it immediately understandable. It doesn't distinguish from siblings (roll_dice, web_search), but those are unrelated tools, so differentiation isn't needed here.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, limitations, or scenarios where this tool is appropriate versus other approaches. With no annotations to provide context, this leaves the agent with insufficient usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

roll_diceC

Roll the dice with the given notation

ParametersJSON Schema
NameRequiredDescriptionDefault
notationYes
num_rollsNo

TDQS

C2.3/5.0
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, so the description must disclose behavioral traits. It only says 'Roll the dice,' which is a direct restatement of the tool name and adds no depth about random generation, validation, error handling, or return format. This is effectively a tautology with no added transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence with no waste, which is positive. However, it is under-specified: it front-loads little useful information and does not structure any context for the parameters. It cannot be considered 'appropriately sized' because it omits essential detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with two parameters, no output schema, and no annotations, the description is severely inadequate. It does not explain dice notation, the meaning of num_rolls, or any behaviors/limitations. Even the sibling context (web_search) offers no help in situating this tool, making the description insufficient for reliable tool invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. 'Given notation' loosely aligns with the 'notation' parameter but fails to define its format or semantics. The 'num_rolls' parameter is entirely absent from the description, leaving its purpose unexplained. Overall, minimal added meaning beyond the schema titles.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear verb ('Roll') and resource ('dice'), indicating the tool's primary action. However, it does not specify what 'notation' means (e.g., standard dice notation like '2d6'), which leaves some ambiguity. It is distinct from the sibling web_search, but not explicitly differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool vs alternatives. The sibling list includes web_search, but the description gives no context for when dice rolling is appropriate or any exclusions. Users are left to infer usage from the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 3 tool updatesv1.0.0
    • Changedrepair_cost1 field changed
      • addedInput schema / title
        Added value: +"repair_costArguments"
    • Changedroll_dice1 field changed
      • addedInput schema / title
        Added value: +"roll_diceArguments"
    • Changedweb_search1 field changed
      • addedInput schema / title
        Added value: +"web_searchArguments"
  2. 3 tool updates
    • First observedrepair_cost
    • First observedroll_dice
    • First observedweb_search
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

C2.6/5.0

Scored across 3 tools

Disambiguation5/5

The three tools have completely distinct purposes: home repair cost estimation, dice rolling, and web searching. There is no overlap in functionality, and an agent would have no difficulty selecting the correct tool for any given task.

Naming Consistency2/5

The naming is inconsistent with mixed conventions: 'repair_cost' and 'web_search' follow a noun_verb pattern, while 'roll_dice' uses verb_noun. This lack of a predictable naming pattern could cause confusion in automated tool selection.

Tool Count2/5

With only three tools, the server appears severely under-scoped for a 'Tavily Web Search MCP Server', as web search is just one of three unrelated functions. The tools do not form a coherent set for the stated server purpose.

Completeness1/5

For a web search server, the tool surface is severely incomplete, lacking essential operations like advanced search filters, result pagination, or domain-specific searches. The inclusion of unrelated tools (repair_cost, roll_dice) further fragments the domain coverage.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Tavily Web Search MCP Server

    julie-berlin
    F
    license
    C
    quality
    D
    maintenance
    Enables web search capabilities through the Tavily API, allowing users to search the internet for information using natural language queries. Demonstrates MCP server implementation with external API integration.
    3
    -

  • Tavily Web Search MCP Server

    nilay320
    F
    license
    B
    quality
    D
    maintenance
    Enables web search capabilities through the Tavily API. Allows users to search the web for information using natural language queries via the MCP protocol.
    4
    1
    -

  • Tavily Web Search MCP Server

    BQ31X
    F
    license
    Not graded
    quality
    D
    maintenance
    Enables web search capabilities through the Tavily API, allowing users to search the web for information using natural language queries. Demonstrates MCP server implementation with stdio transport mode for integration with LLM applications.
    -