| Name | mcp-tavily JSON |
| Version |
0.1.2
JSON |
| download |
| home_page | None |
| Summary | An MCP server for Tavily's search API |
| upload_time | 2024-12-01 18:44:33 |
| maintainer | None |
| docs_url | None |
| author | None |
| requires_python | >=3.10 |
| license | MIT |
| keywords |
http
mcp
llm
automation
|
| VCS |
 |
| bugtrack_url |
|
| requirements |
No requirements were recorded.
|
| Travis-CI |
No Travis.
|
| coveralls test coverage |
No coveralls.
|
# Tavily MCP Server
A Model Context Protocol server that provides AI-powered web search capabilities using Tavily's search API. This server enables LLMs to perform sophisticated web searches, get direct answers to questions, and search recent news articles with AI-extracted relevant content.
### Available Tools
- `tavily_web_search` - Performs comprehensive web searches with AI-powered content extraction.
- `query` (string, required): Search query
- `max_results` (integer, optional): Maximum number of results to return (default: 5, max: 20)
- `search_depth` (string, optional): Either "basic" or "advanced" search depth (default: "basic")
- `tavily_answer_search` - Performs web searches and generates direct answers with supporting evidence.
- `query` (string, required): Search query
- `max_results` (integer, optional): Maximum number of results to return (default: 5, max: 20)
- `search_depth` (string, optional): Either "basic" or "advanced" search depth (default: "advanced")
- `tavily_news_search` - Searches recent news articles with publication dates.
- `query` (string, required): Search query
- `max_results` (integer, optional): Maximum number of results to return (default: 5, max: 20)
- `days` (integer, optional): Number of days back to search (default: 3)
### Prompts
- **tavily_web_search**
- Search the web using Tavily's AI-powered search engine
- Arguments:
- `query` (string, required): Search query
- **tavily_answer_search**
- Search the web and get an AI-generated answer with supporting evidence
- Arguments:
- `query` (string, required): Search query
- **tavily_news_search**
- Search recent news articles with Tavily's news search
- Arguments:
- `query` (string, required): Search query
- `days` (integer, optional): Number of days back to search
## Installation
### Use `pip`
Simply run:
```bash
pip install mcp-tavily
```
or if you have `uv` installed:
```bash
uv pip install mcp-tavily
```
### Build the Server
Clone this repository and build and install the program with your default Python interpreter (recommended).
```bash
git clone https://github.com/modelcontextprotocol/servers.git
cd servers/mcp-tavily
uv build
uv pip install .
```
After installation, you can run it as a script using:
```
python -m mcp_server_tavily
```
## Configuration
### API Key
The server requires a Tavily API key to function. You can obtain one from [Tavily's website](https://tavily.com). The API key can be provided in two ways:
1. As an environment variable:
```bash
export TAVILY_API_KEY=your_api_key_here
```
2. As a command-line argument:
```bash
python -m mcp_server_tavily --api-key=your_api_key_here
```
### Configure for Claude.app
Add to your Claude settings:
<details>
<summary>Using pip installation</summary>
```json
"mcpServers": {
"tavily": {
"command": "python",
"args": ["-m", "mcp_server_tavily"]
},
"env": {
"TAVILY_API_KEY": "your_api_key_here"
}
}
```
</details>
If you see any issue, you may want to use the full path for the Python interpreter you are using. You can do a `which python` to find out the exact path if needed.
Remember to set the TAVILY_API_KEY environment variable or provide it via the --api-key argument.
## Examples
For a regular search:
```
Tell me about Anthropic's newly released MCP protocol
```
To generate a report with explicit exclusions:
```
Tell me about redwood trees. Please use MLA format in markdown syntax and include the URLs in the citations. Exclude Wikipedia sources.
```
To force Claude to use the answer mode function call, be explicit in your ask:
```
I want a concrete answer backed by current web sources: What is the average lifespan of redwood trees?
```
For news, use:
```
Give me the top 10 AI-related news in the last 5 days
```
## Debugging
You can use the MCP inspector to debug the server. For uvx installations:
```
npx @modelcontextprotocol/inspector uvx mcp-server-tavily
```
Or if you've installed the package in a specific directory or are developing on it:
```
cd path/to/servers/src/tavily
npx @modelcontextprotocol/inspector python -m mcp_server_tavily
```
## Contributing
We encourage contributions to help expand and improve mcp-server-tavily. Whether you want to add new search capabilities, enhance existing functionality, or improve documentation, your input is valuable.
For examples of other MCP servers and implementation patterns, see:
https://github.com/modelcontextprotocol/servers
Pull requests are welcome! Feel free to contribute new ideas, bug fixes, or enhancements to make mcp-server-tavily even more powerful and useful.
## License
mcp-server-tavily is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.
Raw data
{
"_id": null,
"home_page": null,
"name": "mcp-tavily",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.10",
"maintainer_email": "Ramiro Salas <ramiro@hextropian.systems>",
"keywords": "http, mcp, llm, automation",
"author": null,
"author_email": "Ramiro Salas <ramiro@hextropian.systems>",
"download_url": "https://files.pythonhosted.org/packages/e3/fa/6b55774afbdc0ed8fa17da8ff101d6a095b5325a57cda5feff2bde87c6fe/mcp_tavily-0.1.2.tar.gz",
"platform": null,
"description": "# Tavily MCP Server\n\nA Model Context Protocol server that provides AI-powered web search capabilities using Tavily's search API. This server enables LLMs to perform sophisticated web searches, get direct answers to questions, and search recent news articles with AI-extracted relevant content.\n\n### Available Tools\n\n- `tavily_web_search` - Performs comprehensive web searches with AI-powered content extraction.\n - `query` (string, required): Search query\n - `max_results` (integer, optional): Maximum number of results to return (default: 5, max: 20)\n - `search_depth` (string, optional): Either \"basic\" or \"advanced\" search depth (default: \"basic\")\n\n- `tavily_answer_search` - Performs web searches and generates direct answers with supporting evidence.\n - `query` (string, required): Search query\n - `max_results` (integer, optional): Maximum number of results to return (default: 5, max: 20)\n - `search_depth` (string, optional): Either \"basic\" or \"advanced\" search depth (default: \"advanced\")\n\n- `tavily_news_search` - Searches recent news articles with publication dates.\n - `query` (string, required): Search query\n - `max_results` (integer, optional): Maximum number of results to return (default: 5, max: 20)\n - `days` (integer, optional): Number of days back to search (default: 3)\n\n### Prompts\n\n- **tavily_web_search**\n - Search the web using Tavily's AI-powered search engine\n - Arguments:\n - `query` (string, required): Search query\n\n- **tavily_answer_search**\n - Search the web and get an AI-generated answer with supporting evidence\n - Arguments:\n - `query` (string, required): Search query\n\n- **tavily_news_search**\n - Search recent news articles with Tavily's news search\n - Arguments:\n - `query` (string, required): Search query\n - `days` (integer, optional): Number of days back to search\n\n## Installation\n\n### Use `pip`\n\nSimply run:\n\n```bash\npip install mcp-tavily\n```\n\nor if you have `uv` installed:\n\n```bash\nuv pip install mcp-tavily\n```\n\n### Build the Server\nClone this repository and build and install the program with your default Python interpreter (recommended).\n\n```bash\ngit clone https://github.com/modelcontextprotocol/servers.git\ncd servers/mcp-tavily\nuv build\nuv pip install .\n```\n\nAfter installation, you can run it as a script using:\n\n```\npython -m mcp_server_tavily\n```\n\n## Configuration\n\n### API Key\n\nThe server requires a Tavily API key to function. You can obtain one from [Tavily's website](https://tavily.com). The API key can be provided in two ways:\n\n1. As an environment variable:\n```bash\nexport TAVILY_API_KEY=your_api_key_here\n```\n\n2. As a command-line argument:\n```bash\npython -m mcp_server_tavily --api-key=your_api_key_here\n```\n\n### Configure for Claude.app\n\nAdd to your Claude settings:\n\n<details>\n<summary>Using pip installation</summary>\n\n```json\n\"mcpServers\": {\n \"tavily\": {\n \"command\": \"python\",\n \"args\": [\"-m\", \"mcp_server_tavily\"]\n },\n \"env\": {\n \"TAVILY_API_KEY\": \"your_api_key_here\"\n }\n}\n```\n</details>\n\nIf you see any issue, you may want to use the full path for the Python interpreter you are using. You can do a `which python` to find out the exact path if needed.\n\nRemember to set the TAVILY_API_KEY environment variable or provide it via the --api-key argument.\n\n## Examples\n\nFor a regular search:\n\n```\nTell me about Anthropic's newly released MCP protocol\n```\n\nTo generate a report with explicit exclusions:\n\n```\nTell me about redwood trees. Please use MLA format in markdown syntax and include the URLs in the citations. Exclude Wikipedia sources.\n```\n\nTo force Claude to use the answer mode function call, be explicit in your ask:\n\n```\nI want a concrete answer backed by current web sources: What is the average lifespan of redwood trees?\n```\n\nFor news, use:\n\n```\nGive me the top 10 AI-related news in the last 5 days\n```\n\n## Debugging\n\nYou can use the MCP inspector to debug the server. For uvx installations:\n\n```\nnpx @modelcontextprotocol/inspector uvx mcp-server-tavily\n```\n\nOr if you've installed the package in a specific directory or are developing on it:\n\n```\ncd path/to/servers/src/tavily\nnpx @modelcontextprotocol/inspector python -m mcp_server_tavily\n```\n\n## Contributing\n\nWe encourage contributions to help expand and improve mcp-server-tavily. Whether you want to add new search capabilities, enhance existing functionality, or improve documentation, your input is valuable.\n\nFor examples of other MCP servers and implementation patterns, see:\nhttps://github.com/modelcontextprotocol/servers\n\nPull requests are welcome! Feel free to contribute new ideas, bug fixes, or enhancements to make mcp-server-tavily even more powerful and useful.\n\n## License\n\nmcp-server-tavily is licensed under the MIT License. This means you are free to use, modify, and distribute the software, subject to the terms and conditions of the MIT License. For more details, please see the LICENSE file in the project repository.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "An MCP server for Tavily's search API",
"version": "0.1.2",
"project_urls": {
"homepage": "https://github.com/RamXX/mcp-tavily",
"issues": "https://github.com/RamXX/mcp-tavily/issues",
"repository": "https://github.com/RamXX/mcp-tavily"
},
"split_keywords": [
"http",
" mcp",
" llm",
" automation"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "6066aa5652f16713ad6303a03bcbc7801ed9d1b83758a13b49727a4dd29dadd7",
"md5": "500b322cf1a1ee4e895625468838115d",
"sha256": "57969d1956e90703f67a311e755a05c4e04bea803cd610eb9cf061488ef75a13"
},
"downloads": -1,
"filename": "mcp_tavily-0.1.2-py3-none-any.whl",
"has_sig": false,
"md5_digest": "500b322cf1a1ee4e895625468838115d",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.10",
"size": 8150,
"upload_time": "2024-12-01T18:44:32",
"upload_time_iso_8601": "2024-12-01T18:44:32.374347Z",
"url": "https://files.pythonhosted.org/packages/60/66/aa5652f16713ad6303a03bcbc7801ed9d1b83758a13b49727a4dd29dadd7/mcp_tavily-0.1.2-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "e3fa6b55774afbdc0ed8fa17da8ff101d6a095b5325a57cda5feff2bde87c6fe",
"md5": "ceaf6352bf1ce745b46336a0f7f89d34",
"sha256": "98cb461e9d94e0cd67ba531525a9b9380c11bbea01782aafd1f02fe64716bb00"
},
"downloads": -1,
"filename": "mcp_tavily-0.1.2.tar.gz",
"has_sig": false,
"md5_digest": "ceaf6352bf1ce745b46336a0f7f89d34",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.10",
"size": 9187,
"upload_time": "2024-12-01T18:44:33",
"upload_time_iso_8601": "2024-12-01T18:44:33.408177Z",
"url": "https://files.pythonhosted.org/packages/e3/fa/6b55774afbdc0ed8fa17da8ff101d6a095b5325a57cda5feff2bde87c6fe/mcp_tavily-0.1.2.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-12-01 18:44:33",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "RamXX",
"github_project": "mcp-tavily",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "mcp-tavily"
}
