convez.ai
MCP ServerIntegração & APIsIntermediário
TrophySecure

Exa MCP Server

TrophySecure/exa-mcp-server

Proxy MCP HTTP da Exa com autenticação Apify e modelo pay-per-event

Ver no GitHub
InicialPluginScore · de 0 a 100

Proxy HTTP para o MCP Server hospedado da Exa, expondo um endpoint streamable que permite clientes MCP se conectarem via URL da Apify com autenticação Bearer. Integra as capacidades de busca e análise da Exa no protocolo Model Context Protocol.

Instalação

$npx convez-ai TrophySecure/exa-mcp-server

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
0
Forks
0
Acompanhando
0
Saúde
28%
Último commit
há 5 meses
Versão
—
Issues abertas
0
Contribuidores
1

Casos de uso

  • Conectar agentes Claude às capacidades de busca web da Exa via MCP
  • Integrar busca e análise de código do Exa em workflows de IA
  • Monetizar chamadas de ferramentas Exa com modelo pay-per-event

Veredito

MCP server bem estruturado que simplifica a integração da Exa com clientes MCP através da infraestrutura Apify. Adequado para quem precisa conectar busca e análise de código em agents Claude, com modelo de cobrança transparente por evento.

README

A tradução para o português deste README ainda está na fila.

Exa Mcp Server

Exa MCP Server

HTTP MCP proxy to Exa's hosted MCP server at https://mcp.exa.ai/mcp. This Actor exposes a streamable HTTP endpoint so MCP clients can connect using an Apify-hosted URL with Bearer auth.

How to use

This server uses mcp-remote to connect to Exa and supports optional EXA_API_KEY (appended to the URL as exaApiKey).

Connection URL

MCP clients can connect to this server at:

https://mcp-servers--exa-mcp-server.apify.actor/mcp

Client Configuration

Use this configuration in your MCP client (replace your-apify-token with your token from Apify Console):

{ "mcpServers": { "exa": { "type": "http", "url": "https://mcp-servers--exa-mcp-server.apify.actor/mcp", "headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" } } } }

Optionally set EXA_API_KEY as an Actor environment variable to use your Exa key.

Pay per event

This Actor uses the Pay Per Event (PPE) model. Exa tool calls map to events defined in .actor/pay_per_event.json such as exa-get-code-context, exa-web-search, etc. Unknown tools fall back to tool-request.

To charge users, define events in JSON format and save them on the Apify platform. Here is an example schema with the tool-request event:

Event charging is performed in src/billing.ts based on the MCP method and tool name.

To set up the PPE model: in Actor Monetization settings, choose Pay per event and paste the content of .actor/pay_per_event.json.

Credits and links

Getting started

For complete information see this article. To run the Actor use the following command:

$apify run

Deploy to Apify

Connect Git repository to Apify

If you've created a Git repository for the project, you can easily connect to Apify:

  1. Go to Actor creation page
  2. Click on Link Git Repository button

Push project on your local machine to Apify

You can also deploy the project on your local machine to Apify without the need for the Git repository.

  1. Log in to Apify. You will need to provide your Apify API Token to complete this action.
$apify login
  1. Deploy your Actor. This command will deploy and build the Actor on the Apify Platform. You can find your newly created Actor under Actors -> My Actors.
$apify push

Documentation reference

To learn more about Apify and Actors, take a look at the following resources:

Ver o original no GitHub

Bom para

Relacionados