Skip to main content
Glama
neeraj-somani

Tavily Web Search MCP Server

by neeraj-somani
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 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/AIE8-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: I am implementing polygon API tool in this MCP server.

🏗️ Activity #2:

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

You can find details here!

Answer: langgraph_agent.py file has been implemented for this.

Available Tools

3 tools
get_stock_ohlcA

Get Open, High, Low, Close (OHLC) data for a stock symbol for the last working day or specified date

ParametersJSON Schema
NameRequiredDescriptionDefault
symbolYes
dateNo

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

A3.8/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the tool retrieves data but does not specify whether it requires authentication, has rate limits, what happens if the date is invalid or the symbol doesn't exist, or if it's a read-only operation. This leaves significant gaps in understanding the tool's behavior.

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, well-structured sentence that efficiently conveys the tool's purpose and key usage details without any unnecessary words. It is front-loaded with the main action and resource, making it easy to understand quickly.

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

Completeness4/5

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

Given the tool's moderate complexity (2 parameters, no annotations, but with an output schema), the description is mostly complete. It covers the purpose and basic usage, and the presence of an output schema means return values are documented elsewhere. However, it lacks details on error handling or behavioral constraints, which could be important for robust use.

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

Parameters3/5

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

The description adds some meaning by clarifying that 'date' is optional and defaults to the last working day, which is not evident from the schema alone (schema description coverage is 0%). However, it does not explain the format of the 'symbol' parameter (e.g., ticker format) or the 'date' parameter (e.g., YYYY-MM-DD), leaving room for ambiguity.

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

Purpose5/5

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

The description clearly states the specific action ('Get') and resource ('Open, High, Low, Close (OHLC) data for a stock symbol'), with precise scope ('for the last working day or specified date'). It effectively distinguishes from sibling tools (roll_dice, web_search) by focusing on financial data retrieval rather than random generation or web search.

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

Usage Guidelines4/5

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

The description provides clear context for when to use this tool (to retrieve OHLC data for stocks, either for the last working day or a specified date). However, it does not explicitly state when not to use it or name alternatives for similar financial data queries, which prevents a perfect score.

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

Output Schema

ParametersJSON Schema
NameRequiredDescription
resultYes

TDQS

C2/5.0
Behavior1/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It fails to mention the format of accepted notation, whether the roll is random, any constraints, error behavior, or the return value. This is a significant transparency gap.

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 very short and front-loaded, but it is under-specified. Every sentence is technically earned but the content is insufficient. It is concise at the expense of usefulness.

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?

Despite being a simple tool, the description is incomplete for an agent to use it correctly. It does not explain the expected notation syntax or the number of rolls, and while an output schema exists, the description does not help connect inputs to outputs. The description needs more detail to be functionally complete.

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

Parameters1/5

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 for parameter meaning. It only vaguely references 'notation' and completely ignores the 'num_rolls' parameter. The description provides essentially no semantic information beyond the parameter names.

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

Purpose3/5

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

The description is essentially a restatement of the tool name ('roll dice') with a vague reference to 'given notation'. It communicates the basic action but adds no detail about what notation is or how it differs from other tools. It's minimally clear but not strongly 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?

There is no guidance on when to use this tool versus alternatives, nor any context about suitable scenarios. The description simply states the action without implying any usage conditions or exclusions.

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
    • Changedget_stock_ohlc1 field changed
      • addedInput schema / title
        Added value: +"get_stock_ohlcArguments"
    • 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 observedget_stock_ohlc
    • 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

C2.9/5.0

Scored across 3 tools

Disambiguation5/5

Each tool has a completely distinct purpose with no overlap: get_stock_ohlc retrieves financial data, roll_dice performs a random number generation game, and web_search conducts internet queries. The domains are so different that an agent would never confuse them.

Naming Consistency2/5

The naming is inconsistent with mixed conventions: get_stock_ohlc uses snake_case with a verb_noun pattern, roll_dice uses snake_case but with a verb-only style, and web_search uses snake_case with a noun_verb pattern. There is no predictable naming scheme across the set.

Tool Count2/5

With only 3 tools, the server feels too thin for its apparent scope as a 'Tavily Web Search MCP Server'—web_search aligns with this, but get_stock_ohlc and roll_dice are unrelated utilities that don't fit cohesively. The count is low and the tools lack a unified domain focus.

Completeness2/5

For a web search server, the surface is severely incomplete: web_search covers basic queries, but there are no tools for advanced search features (e.g., filtering, pagination, or result analysis). The inclusion of unrelated tools like get_stock_ohlc and roll_dice creates gaps in the core domain without adding meaningful coverage.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Tavily MCP Server

    RamXX
    A
    license
    Not graded
    quality
    F
    maintenance
    Provides AI-powered web search capabilities using Tavily's search API, enabling LLMs to perform sophisticated web searches, get direct answers to questions, and search recent news articles.
    72
    MIT

  • tavily-mcp

    Seey215
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI assistants to perform real-time web searches, extract data from web pages, map website structures, and crawl websites using the Tavily API.
    49 npm
    MIT

Appeared in Searches