MCP Sunucuları

Model Context Protocol sunucuları için açık kayıt. AI agent'larınız için doğru araçları, kaynakları ve prompt'ları kategori, taşıma yöntemi veya kullanım alanına göre bulun.

Sunucular

187

Araçlar

493

Kategoriler

11

Katkıda bulunanlar

164

187 sunucu

Sıralama
Google Security MCPGoogle

Google's official collection of Model Context Protocol servers that expose Google's security products to MCP clients. Provides access to Google SecOps (Chronicle) for SIEM search and case management, Google Threat Intelligence for indicator and malware lookups, and Security Command Center for cloud posture and findings. Lets security agents investigate alerts, enrich indicators of compromise, and triage vulnerabilities directly from natural language.

0
Grafana Tempo MCPGrafana Labs

A Model Context Protocol server for Grafana Tempo that lets AI assistants query and analyze distributed tracing data. Agents can search traces with TraceQL, fetch a trace by ID, and inspect spans to investigate latency and errors across services during incident analysis.

0
GrowthBook MCP ServerGrowthBook

GrowthBook's official MCP server for working with feature flags, experiments, and metrics so agents can safely support product experimentation workflows.

0
Harness MCP ServerHarness

Harness' official MCP server for connecting agents to software delivery workflows, including deployment pipelines, services, environments, and delivery insights.

0
Honeycomb MCP ServerHoneycomb

Honeycomb's MCP server that lets AI assistants query and analyze observability data, including events, traces, alerts (triggers), and boards. Agents can run queries against datasets, inspect columns and schemas, and cross-reference production behavior with the codebase to investigate incidents. Connects to Honeycomb via API key or OAuth.

0
Infisical MCP ServerInfisical

Infisical's official MCP server for its open-source secret management platform. Lets AI agents list projects and environments and create, read, update, and delete secrets and folders through controlled tools, so assistants can help manage application configuration without exposing raw credentials in code. Authenticates using a machine identity.

0
InfluxDB MCP ServerInfluxData

InfluxData's MCP server connects agents to InfluxDB 3 for SQL queries, schema exploration, and time-series database operations.

0
JetBrains MCP ServerJetBrains

JetBrains' official MCP server for working with IntelliJ-based IDEs and Android Studio, enabling agents to inspect projects and use IDE-aware development capabilities.

0
JFrog MCP ServerJFrog

JFrog's MCP server lets agents work with Platform services for artifact repositories, build information, release lifecycle management, and software supply-chain workflows.

0
Kagi MCP ServerKagi Search

Official MCP server backed by the Kagi API. Exposes Kagi's high-quality search and summarization tools to MCP-compatible clients, including web search and the Universal Summarizer for pages and videos. Useful for research workflows that want ad-free, privacy-respecting results with concise summaries. Requires a Kagi API key.

0
MarkItDown MCPMicrosoft

Microsoft's MarkItDown MCP integration converts documents from HTTP, file, and data URIs into Markdown for agent-ready analysis and retrieval.

0
MCP for UnityCoplay

MCP server that bridges AI assistants with the Unity Editor. Gives an LLM tools to create and modify GameObjects, edit scripts, manage assets and scenes, read the console, and run tests, enabling AI-driven game development workflows directly inside Unity. Works with clients such as Claude, Cursor, VS Code, and other MCP-compatible tools.

0
MCP Toolbox for DatabasesGoogle APIs

Google's MCP Toolbox provides secure, ready-made and custom tools for database queries, schema operations, and semantic search in agent workflows.

0
Medusa MCP ServerMedusa

Medusa's MCP integration connects agents to commerce data and administrative operations for storefront, catalog, order, and customer workflows.

0
Meilisearch MCP ServerMeilisearch

Official MCP server for Meilisearch, the open-source, lightning-fast search engine. Enables MCP-compatible clients to manage search indexes, add and update documents, run searches, and adjust index settings through natural language. Useful for building and debugging search experiences and for letting agents query application data stored in Meilisearch.

0
Metabase MCP ServerMetabase

Metabase's built-in MCP server that lets AI clients connect directly to a Metabase instance, scoped to the connecting user's permissions. Enables agents to discover databases and models, run queries, and retrieve results and dashboards so teams can ask questions of their business intelligence data in natural language.

0
Microsoft Learn MCP ServerMicrosoft Learn

Microsoft's official MCP server and CLI for giving agents current, trusted Microsoft Learn documentation and code samples during development and troubleshooting.

0
MindsDB MCP ServerMindsDB

MindsDB's MCP integration gives agents access to AI workflows, data integrations, and automation capabilities through the MindHub platform.

0
MotherDuck MCP ServerMotherDuck

Official MCP server for DuckDB and MotherDuck. Lets AI assistants run SQL analytics directly against local DuckDB files, in-memory databases, S3-hosted data, and MotherDuck cloud warehouses. Supports read and write queries, browsing database catalogs, and switching between connections on the fly, making it well suited for conversational data exploration and lightweight analytics.

0
n8n MCP ServerRomuald Czlonkowski

Popular community MCP server that gives AI assistants deep knowledge of n8n's workflow automation nodes, their properties, and operations, and can connect to a live n8n instance to create and manage workflows. Helps agents design, validate, and deploy automations correctly by exposing node documentation, validation, and workflow management tools.

0
Octopus Deploy MCP ServerOctopus Deploy

Octopus Deploy's official MCP server helps agents inspect, query, and diagnose deployment infrastructure, projects, releases, and environments.

0

Skills ve MCP sunucuları

aralarındaki fark nedir?

Skills“ne yapılacağı”

Bir Skill; talimatları, örnek prompt'u ve önerilen modelleri paketleyerek agent'ın görevi tutarlı şekilde yapmasını sağlar. Skills yeni bağlantılar değil, bilgi ekler.

MCP sunucuları“nasıl bağlanılacağı”

Bir MCP sunucusu, gerçek sistemlere (veritabanları, API'ler ve dosyalar) bir taşıma yöntemi üzerinden bağlanarak agent'a yeni yetenekler kazandırır. MCP görev talimatları değil, bağlantılar ve eylemler ekler.

Kısa kural: modelin bir görevi iyi yapması gerekiyorsa Skill, bir araca veya sisteme erişmesi gerekiyorsa MCP sunucusu kullanın. Birlikte çalışabilirler; Skill, MCP sunucusunun sunduğu araçlardan yararlanabilir.

Bir MCP sunucusu mu geliştirdiniz?

Açık kaynaklı ve topluluk tarafından sürdürülen kayda ekleyin.

GitHub üzerinden gönder