de en es ja ko ru zh

tavily-pool-mcp

Name: tavily-pool-mcp
Author: yanjin734-ltsm

by yanjin734-ltsm

Overview Schema Source Related Servers Discussions Admin

JavaScript

Remote

tavily-pool-mcp

Un servidor local de Model Context Protocol que expone una herramienta de búsqueda de Tavily y rota entre múltiples claves de API de Tavily.

Características

Expone tavily_search como una herramienta MCP
Rota entre múltiples claves de API de Tavily
Reintenta con otra clave ante errores 401, 403 o 429
Funciona con OpenCode y otros clientes compatibles con MCP

Related MCP server: AIE7-MCP

Requisitos

Node.js 18+
Claves de API de Tavily

Instalación

npm install

Configuración

Establece TAVILY_API_KEYS como una lista separada por espacios, comas o puntos y coma:

export TAVILY_API_KEYS="tvly-dev-key-1 tvly-dev-key-2 tvly-dev-key-3"

En Windows PowerShell:

$env:TAVILY_API_KEYS="tvly-dev-key-1 tvly-dev-key-2 tvly-dev-key-3"

Ejecución

npm start

npm start inicia un servidor MCP stdio, por lo que la terminal esperará la entrada de MCP. Esto es lo esperado.

Configuración de OpenCode

Añade esto a tu opencode.json de OpenCode:

{
  "mcp": {
    "tavily-pool": {
      "type": "local",
      "enabled": true,
      "command": ["node", "C:/path/to/tavily-pool-mcp/src/index.mjs"],
      "environment": {
        "TAVILY_API_KEYS": "{env:TAVILY_API_KEYS}"
      }
    }
  }
}

Herramienta

`tavily_search`

Argumentos:

query: consulta de búsqueda
max_results: 1-20, por defecto 5
search_depth: basic o advanced, por defecto basic
include_answer: booleano, por defecto false
include_raw_content: booleano, por defecto false

Seguridad

No confirmes (commit) claves de API reales. Utiliza variables de entorno o un gestor de secretos.

Licencia

MIT

Available Tools

1 tool

tavily_searchC

Search the web using Tavily. This MCP rotates across multiple API keys.

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes	Search query
`max_results`	No
`search_depth`	No		basic
`include_answer`	No
`include_raw_content`	No

TDQS

C2.9/5.0

Behavior3/5

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

The description mentions a behavioral trait: 'rotates across multiple API keys', which is beyond the (missing) annotations. However, it omits other important details like rate limits, costs, or result format, which would be expected for a search tool.

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 succinct with two sentences. The first sentence clearly states the core purpose, and the second adds a key behavioral detail. No extraneous information is present.

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 5 parameters, no output schema, and no annotations, the description is too minimal. The agent lacks information about return values, pagination, or how to interpret results, making it insufficient for effective use.

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?

The schema coverage is low (20%), with only 'query' having a description. The description adds no information about parameters such as max_results, search_depth, include_answer, or include_raw_content, leaving the agent without guidance on their meaning or usage.

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 verb 'Search' and the resource 'web using Tavily', which is a specific search engine. The purpose is unambiguous, and since there are no sibling tools, differentiation is not required.

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 versus alternatives or when not to use it. The description only implies usage for web searches, but lacks exclusion criteria or context for decision-making.

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 tool updatev0.1.0May 10, 2026
- First observedtavily_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

B3.4/5.0

Scored 2026-05-10 07:20 across 1 tool

Disambiguation5/5

Only one tool exists, so there is no possibility of confusion or overlap.

Naming Consistency5/5

The single tool follows a clear verb_noun pattern (tavily_search), which is consistent and predictable.

Tool Count3/5

One tool is on the low end but reasonable for a focused search service; it is borderline but not inappropriate.

Completeness5/5

The search tool fully covers the server's purpose of web search; no obvious missing operations.

Maintenance

ActivityInactive

ResponsivenessNo issues

Resources

GitHub Repository

Need Help?

Related Servers

Related MCP Connectors

Tavily A
io.github.pipeworx-io
Tavily MCP — wraps the Tavily API (tavily.com)
Search RAG Systems
2
mcp A
ai.llmse
Public MCP server for the LLM Search Engine
Search RAG Systems Developer Tools
102
Keenable Web Search A
ai.keenable.api
Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key.
Research & Data Search Web Scraping
23
SSearch B
cc.ssearch
Free web search for AI agents. No API key required. Hosted MCP in active development.
Search Browser Automation
71

Related MCP Servers

tavily-mcp-proxy
Search Web Scraping
welyfun
A
license
Not graded
quality
F
maintenance
A proxy MCP server for Tavily search and extract APIs with support for multiple API keys, random rotation, and bearer token authentication.
Updated 4 months ago (2026-06-11 15:48 UTC)
MIT
AIE7-MCP
Search RAG Systems
chelsea-zhou
F
license
A
quality
D
maintenance
MCP server that provides web search capabilities using the Tavily API.
Updated a year ago (2025-08-10 04:45 UTC)
3
-
tavily-mcp
Browser Automation Web Scraping Search
BACH-AI-Tools
A
license
B
quality
D
maintenance
MCP server providing search, extract, map, and crawl tools powered by Tavily for real-time web data access.
Updated 10 months ago (2025-12-04 05:37 UTC)
4
11 npm
MIT
Tavily Web Search MCP Server
Search RAG Systems
IamKavy47
F
license
Not graded
quality
C
maintenance
An experimental MCP server that provides web search capabilities using the Tavily API. Still in progress, not production-ready.
Updated 3 months ago (2026-07-12 15:03 UTC)
-

Appeared in Searches

Comparison of Exa MCP Server and Tavily search tools

tavily-pool-mcp

Características

Requisitos

Instalación

Configuración

Ejecución

Configuración de OpenCode

Herramienta

tavily_search

Seguridad

Licencia

Available Tools

TDQS

Tool Schema Changelog

TDQS

Maintenance

Resources

Related MCP Connectors

Related MCP Servers

tavily-mcp-proxy

AIE7-MCP

tavily-mcp

Tavily Web Search MCP Server

Appeared in Searches

`tavily_search`