Aiven

- **List and inspect Aiven projects**— Use`aiven_project_list`and`aiven_project_get`to browse projects and view their details. - **Manage Aiven services**— Create, update, or retrieve services with`aiven_service_create`,`aiven_service_update`, and`aiven_service_get`. - **Work with Kafka topics and connectors**— List, create, update, delete topics, produce/consume messages, and manage Kafka Connect connectors. - **Run SQL on PostgreSQL services**— Execute read-only queries with`aiven_pg_read`or write statements with`aiven_pg_write`. - **Deploy and redeploy applications**— Use`aiven_application_deploy`and`aiven_application_redeploy`to manage Dockerized apps on Aiven. - **Search Aiven documentation**— Query official docs in natural language via`aiven_docs_search`(hosted server only). A[Model Context Protocol(MCP) server for the](https://modelcontextprotocol.io/)[Aivencloud data platform. Manage PostgreSQL, Apache Kafka, applications, and other Aiven services directly from AI assistants like Claude, Cursor, and VS Code Copilot. ](https://aiven.io/)[!WARNING]**Use with care.**This MCP server can create, modify, and delete Aiven services and data on your behalf. AI agents may execute destructive actions (dropping databases, deleting services, producing messages) based on their interpretation of your prompts. You are fully responsible for the actions taken through this tool. **Permissions:**Access is governed by the Aiven user permissions associated with the authenticated account. The MCP server can only perform actions that your Aiven user is allowed to do. **AI Agent Security:**AI agents may need access credentials (database connection strings, streaming tokens) to act on your behalf. Review what your agent is doing, especially in production environments. Follow your organization's security policies and do a risk assessment before giving AI agents access to sensitive resources. The MCP server is hosted at`https://mcp.aiven.live/mcp`. Your MCP client will prompt you to authorize on Aiven. ``` `claude mcp add --scope user --transport http aiven-mcp "https://mcp.aiven.live/mcp"` ``` ``` `{ "mcpServers": { "aiven-mcp": { "url": "https://mcp.aiven.live/mcp" } } }` ``` Add to`.vscode/mcp.json`in your workspace: ``` `{ "servers": { "aiven-mcp": { "type": "http", "url": "https://mcp.aiven.live/mcp" } } }` ``` Enable read-only mode by adding`?read_only=true`to the URL. All write operations will be excluded from the MCP: ``` `{ "mcpServers": { "aiven-mcp": { "url": "https://mcp.aiven.live/mcp?read_only=true" } } }` ``` Reduce the tool surface exposed to your AI agent by adding`?services_scope=`to the URL. Useful when you only work with a subset of Aiven services and want to keep the agent's context focused. Combine values with commas.`core`(project/service discovery) is always included implicitly. Valid scopes:`all`,`core`,`pg`,`kafka`,`application`,`integrations`. Use`all`to explicitly load every tool (same as omitting the param).`all`cannot be combined with other scopes. ``` `{ "mcpServers": { "aiven-mcp": { "url": "https://mcp.aiven.live/mcp?services_scope=kafka" } } }` ``` ``` `https://mcp.aiven.live/mcp?services_scope=pg&read_only=true` ``` #### Write Exceptions in Read-Only Mode (Remote) When`read_only=true`, add`?write_allowlist=`to re-enable specific write tools while keeping everything else read-only. Useful when you want mostly-read access but still need to allow one write action, for example creating Kafka topics. Combine multiple tool names with commas. Ignored when`read_only`is not enabled. ``` `https://mcp.aiven.live/mcp?read_only=true&write_allowlist=aiven_kafka_topic_create` ``` ``` `{ "mcpServers": { "aiven-mcp": { "url": "https://mcp.aiven.live/mcp/<marketplace>" } } }` ``` The path segment combines with the query parameters above, for example`https://mcp.aiven.live/mcp/gcp?services_scope=pg&read_only=true`. Run the server locally as a child process of your MCP client. Requires Node.js 18+. You must provide your Aiven API token via the`AIVEN_TOKEN`environment variable.[Create a token here. ``` `claude mcp add --scope user aiven-mcp -e AIVEN_TOKEN=your-token-here -- npx -y mcp-aiven` ``` **Cursor, VS Code**-- add to your MCP client config: ``` `{ "mcpServers": { "aiven-mcp": { "command": "npx", "args": ](https://console.aiven.io/profile/tokens)["-y", "mcp-aiven"], "env": { "AIVEN_TOKEN": "your-token-here" } } } }` ``` - Cursor: Cursor Settings > MCP Servers - VS Code:`.vscode/mcp.json`in your workspace Run a local build of the server (useful for development and testing): ``` `pnpm install && pnpm generate:api-types && pnpm generate && pnpm build && AIVEN_TOKEN="<YOUR_TOKEN>" MCP_TRANSPORT="http" PORT=3000 node dist/index.js` ``` The server listens on port 3000 by default. Connect your MCP client to`http://localhost:3000/mcp`. To point a remote deployment at a custom host (e.g. your local build), set`MCP_HOST`: ``` `MCP_HOST=http://localhost:3000 node dist/index.js` ``` In remote (HTTP) mode,`AIVEN_TOKEN`is not needed. Your MCP client sends your token as a Bearer token with each request. Production HTTP traffic is rate-limited in two layers: Cloudflare enforces a per-client-IP limit (configured in the Cloudflare dashboard), and this server enforces`MCP_HTTP_RATE_LIMIT_*`per bearer token on`POST /mcp`. When`EXTRA_PROTECTION=true`, any mismatch between`MCP_EDGE_AUTH_SECRET`and the value Cloudflare injects as`X-Edge-Auth`causes**every request to return 403**(except`GET /health`). Both values are environment/config on opposite sides of the wire, so the only recovery path is to fix the secret and redeploy or update Cloudflare. - **Cloudflare Transform Rule**— Add a rule that sets`X-Edge-Auth`(and, if used for PG tools,`X-Client-IP`) on traffic to the MCP origin. Note the secret value you configure. - **`MCP_EDGE_AUTH_SECRET`**— Deploy the server with this env var set to the**same**secret as the Transform Rule. Leave`EXTRA_PROTECTION`unset or`false`for now; verify the origin still accepts traffic. - **`EXTRA_PROTECTION=true`**— Enable only after steps 1–2 are live and matched. Confirm a normal MCP request succeeds and direct origin access without`X-Edge-Auth`is rejected. - **Secret rotation**— Update Cloudflare and`MCP_EDGE_AUTH_SECRET`together (or briefly set`EXTRA_PROTECTION=false`), redeploy, then re-enable. Never rotate one side alone while the flag is on. If`EXTRA_PROTECTION=true`at startup and`MCP_EDGE_AUTH_SECRET`is missing, the process exits immediately with an error. While rejections continue, the server logs a misconfig warning at most once every 15 minutes (reset after a request with valid`X-Edge-Auth`), so a secret mismatch is visible in logs without one line per rejected request. See[CONTRIBUTING.mdfor development setup, running locally, and adding new tools. Interact with your AWS environment using natural language to query and manage resources. Requires local AWS credentials. Interact with your AWS environment using natural language. Requires local AWS credentials. A read-only MCP server for retrieving information and diagnosing issues in Kubernetes clusters. Deploy full-stack apps (Postgres, Redis, S3, workers, backups) from Claude or curl. 59 MCP tools An MCP server for managing databases and services on the Tembo Cloud platform. Interact with the Neon serverless Postgres platform MCP-PostgreSQL-Ops is a professional MCP server for PostgreSQL database operations, monitoring, and management. Supports PostgreSQL 12-17 with comprehensive database analysis, performance monitoring, and intelligent maintenance recommendations through natural language queries. Interact with Neon Postgres databases using natural language to manage projects, branches, queries, and migrations via the Neon API. An MCP server for PostgreSQL providing index tuning, explain plans, health checks, and safe SQL execution. An MCP interface for the rails-pg-extras gem, providing PostgreSQL metadata and performance analysis through LLM prompts.](https://github.com/Aiven-Open/mcp-aiven/blob/HEAD/CONTRIBUTING.md)