Kalodata MCP Server
Provides TikTok Shop market analytics, including category rankings, product rankings, creator performance, and viral video metrics.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Kalodata MCP ServerWhat are the top-selling products on TikTok Shop this week?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Kalodata MCP Server (TikTok Shop Analytics)
Servidor MCP (Model Context Protocol) construído em Python com o SDK oficial (FastMCP v1.x). Funciona como um wrapper completo para a Kalodata Open API, permitindo que assistentes e agentes de IA (como Perplexity AI, Claude, Cursor e outros) realizem pesquisas aprofundadas de mercado, análise de nichos, produtos vencedores, criadores e vídeos virais do TikTok Shop.
📌 O que é este projeto?
Este servidor expõe 8 ferramentas MCP para consulta de dados do TikTok Shop:
category_rank— Ranking de categorias por receita.category_detail— Detalhes completos de uma categoria.product_rank— Ranking dos produtos mais vendidos.product_detail— Detalhes e métricas de um produto.creator_rank— Ranking de criadores/influenciadores.creator_detail— Detalhes e performance de um criador.video_rank— Ranking de vídeos virais de vendas.video_detail— Métricas de um vídeo específico.
Transporte nativo: Streamable HTTP na rota /mcp, compatível com Perplexity AI Custom Remote Connectors.
Related MCP server: TikTok Complete MCP Server
🚀 Setup Local
1. Pré-requisitos
Python 3.10 ou superior.
Chave de API Kalodata (
KALODATA_SECRET_KEY).
2. Ambiente Virtual e Dependências
python -m venv .venv
# Ativar (Windows PowerShell):
.venv\Scripts\Activate.ps1
# Ativar (Linux/macOS):
source .venv/bin/activate
pip install -r requirements.txt3. Configurar .env
cp .env.example .envEdite .env:
KALODATA_SECRET_KEY=sua_chave_aqui
KALODATA_BASE_URL=https://staging.kalodata.com
PORT=8000
HOST=0.0.0.0Nota: Se sua chave for de produção, altere
KALODATA_BASE_URLpara o host fornecido no e-mail de ativação da Kalodata.
🧪 Testes e Validação Local
1. Testar conexão direta com a API Kalodata (sem MCP)
python test_local.py2. Iniciar o servidor MCP
python server.pySaída esperada nos logs:
INFO: Uvicorn running on http://0.0.0.0:8000 (Press CTRL+C to quit)
[kalodata-mcp] Servidor iniciando em http://0.0.0.0:8000/mcp
[kalodata-mcp] Transporte: streamable-http | 8 ferramentas registradas3. Testar o endpoint /mcp via linha de comando
O endpoint correto é /mcp (testado e confirmado localmente com HTTP 200).
Windows (PowerShell):
Invoke-WebRequest -Uri http://localhost:8000/mcp `
-Method POST `
-Headers @{"Accept"="application/json, text/event-stream"; "Content-Type"="application/json"} `
-Body '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}' `
-UseBasicParsing | Select-Object -ExpandProperty ContentLinux/macOS (curl):
curl -s -N \
-H "Accept: application/json, text/event-stream" \
-H "Content-Type: application/json" \
-d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}' \
http://localhost:8000/mcpResposta esperada:
event: message
data: {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":"2024-11-05","serverInfo":{"name":"kalodata","version":"1.29.1"},...}}Importante: O Streamable HTTP exige os dois headers
Accept: application/json, text/event-stream. Sem eles, o servidor retorna 406 Not Acceptable (comportamento correto do protocolo).
4. Testar com MCP Inspector (interface visual)
npx @modelcontextprotocol/inspector python server.py🌐 Deploy Remoto (Render.com)
O projeto já inclui o arquivo render.yaml na raiz, permitindo deploy via Blueprint no Render.
Passo a Passo:
Criar repositório no GitHub e fazer push:
git remote add origin https://github.com/seu-usuario/kalodata-mcp.git git push -u origin masterAcesse dashboard.render.com → New + → Blueprint.
Conecte o repositório. O Render detecta o
render.yamlautomaticamente.Configure as variáveis de ambiente manualmente no painel do Render:
KALODATA_SECRET_KEY: sua chave da Kalodata (rotacionada/nova)KALODATA_BASE_URL:https://staging.kalodata.com(ou URL de produção)
Clique em Apply. O Render fará o build e gerará a URL pública (ex:
https://kalodata-mcp.onrender.com).Teste o deploy:
curl -s -N \ -H "Accept: application/json, text/event-stream" \ -H "Content-Type: application/json" \ -d '{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"test","version":"1.0"}}}' \ https://kalodata-mcp.onrender.com/mcp
🔗 Registrando no Perplexity AI
Acesse Perplexity AI → Configurações da Conta → Conectores.
Clique em "+ Conector personalizado".
Preencha:
Nome:
Kalodata TikTok Shop AnalyticsTipo:
RemotoURL:
https://kalodata-mcp.onrender.com/mcpTransporte:
Streamable HTTPAutenticação:
Nenhuma
Salve. O Perplexity descobrirá automaticamente as 8 ferramentas.
Por que "Nenhuma" autenticação? A chave da Kalodata fica no servidor (variável de ambiente), nunca exposta ao Perplexity.
✅ Checklist de Deploy Manual (Tarefas Fora do Agente)
Estas etapas dependem de contas externas e devem ser executadas por você manualmente:
1. GitHub — Criar repositório
kalodata-mcpno GitHub (pode ser privado).2. Git Push — Rodar
git remote add origin <URL>egit push -u origin master.3. Render — Criar conta em render.com se ainda não tiver.
4. Blueprint — No Render: New + → Blueprint → conectar repositório → detecta
render.yamlautomaticamente.5. Variáveis secretas — No painel do Render, preencher
KALODATA_SECRET_KEYeKALODATA_BASE_URLmanualmente (nunca commite esses valores).6. Aguardar deploy — O Render executa
pip install -r requirements.txtepython server.py. Aguardar status "Live".7. Testar endpoint público — Copiar a URL gerada (ex:
https://kalodata-mcp.onrender.com) e testar o endpoint/mcpcom curl.8. Perplexity — Ir em Configurações → Conectores → + Conector personalizado → Remoto → colar
https://<url>/mcp→ Streamable HTTP → Autenticação: Nenhuma.
🔒 Aviso de Segurança
NUNCA comite o arquivo
.envcom chave real. O.gitignorejá o ignora.NUNCA adicione a chave dentro do
render.yaml— as variáveissync: falsesão inseridas manualmente no dashboard do Render.A chave da Kalodata vive apenas na variável de ambiente do servidor, nunca exposta ao cliente MCP.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
No tool schema history has been recorded yet.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
SEO & marketing toolkit for AI agents: GA4, Search Console, AdSense, GTM, PageSpeed, Trends.
AMZScout Skill + MCP gives AI agents live access to real Amazon marketplace data across 14 Amazon marketplaces. Analyze any ASIN, validate product ideas, research niches, compare competitors, discover profitable keywords, and build data-driven PPC strategies using trusted Amazon insights instead of AI assumptions. Works with Claude, ChatGPT, Cursor, and any other MCP-compatible AI client. To connect, you'll need an AMZScout API plan and authorize your account. Get access and view pricing here: https://learn.amzscout.net/amazon-product-api-for-ai-agents
Real-time Amazon product, seller, and search data for AI agents across 21 marketplaces.
171Teamfight Tactics data & AI coaching for Claude and ChatGPT — 19 tools, built-in Riot key.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables AI assistants to manage TikTok advertising campaigns through the TikTok Ads API. Supports campaign creation, performance analytics, audience management, creative operations, and custom reporting through natural language interactions.48MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI assistants to download TikTok videos without watermarks, analyze creator metrics and audience insights, track trending content and hashtags, and search videos, users, and sounds through RapidAPI integration.-
- AlicenseAqualityCmaintenanceEnables AI assistants to access TikTok organic analytics including video performance, engagement metrics, and profile insights via the TikTok Developer API.544MIT
- AlicenseAqualityBmaintenanceEnables AI assistants to query Amazon search volume trends and growth signals for product research and consumer purchase intent analysis.3MIT
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/walysonbento-byte/kalodata-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server