Server facts
CentralMind Gateway MCP Server
Project
- Author
- centralmind
- Repository
- github.com/centralmind/gateway
- Website
- centralmind.ai
- License
- Apache-2.0
- Category
- Databases
Tech
- Runtime / language
- goGo
- Transports
- stdio
- Remote available
- No
- Authentication
- Not specified
Activity
- GitHub stars
- 547
- Last commit
- Data as of
Tags
- Database Api
- Observability
- Openapi
- Pii Redaction
- Sql
Overview
CentralMind Gateway provides an API layer between structured databases and AI applications. It can expose data through MCP, including SSE, or through REST with generated Swagger documentation and an OpenAPI 3.1 specification. The README also describes direct SQL access. Supported databases include PostgreSQL, MySQL, ClickHouse, Snowflake, BigQuery, Oracle, SQLite, and other listed connectors. During discovery, a language model examines schema information and sampled data to produce an API configuration based on a prompt. The README explicitly limits this model use to discovery, separating API generation from the later serving stage. Developers can inspect the resulting YAML configuration before launching the API.
Security and operational features are configurable through plugins. The project describes API-key and OAuth options, sensitive-data redaction using regex or Microsoft Presidio, Lua-based row-level controls, and OpenTelemetry integration for tracing and auditing. Caching options include time-based and LRU strategies. Generation can use several hosted AI providers or configurable local model endpoints. Deployment choices include a binary, Docker, and Kubernetes, with a Docker quick start showing a PostgreSQL connection string and an SSE endpoint on port 9090. MCP methods come from the generated configuration, so the README does not establish a fixed tool catalog. Some authentication and write-related items also appear on the roadmap, making configuration review important rather than assuming every protection is enabled automatically.
Install & configure
Requirements
- Docker
- A reachable PostgreSQL database for this example
docker run --platform linux/amd64 -p 9090:9090 ghcr.io/centralmind/gateway:v0.2.18 start --connection-string 'postgres://db-user:db-password@db-host/db-name?sslmode=require'Replace the database connection placeholder. This README quick start exposes SSE at port 9090 and REST at the root. Custom discovery uses an AI provider and generates gateway.yaml; a separate stdio setup is also documented.
Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.
A supported configuration example is not available for this client and transport. Check the client documentation for its connection flow; do not substitute an undocumented JSON format.
Read the Claude Desktop setup guideConfig file · Project: .cursor/mcp.json
User: ~/.cursor/mcp.json
The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"gateway": {
"url": "http://localhost:9090/sse"
}
}
}Config file · Workspace: .vscode/mcp.json
For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.
A supported configuration example is not available for this client and transport. Check the client documentation for its connection flow; do not substitute an undocumented JSON format.
Read the VS Code setup guideConfig file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json
Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json
Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"gateway": {
"serverUrl": "http://localhost:9090/sse"
}
}
}Config file · Project scope: .mcp.json at the repository root
The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.
{
"mcpServers": {
"gateway": {
"type": "sse",
"url": "http://localhost:9090/sse"
}
}
}Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.
Tools
No individual tool names were confirmed in the source material. Check the repository for its current tool list.
Names, permissions, and defaults can change. Check the current upstream documentation before granting access.
Use cases
- Expose a database to an assistant through MCP
- Generate a REST API from schema and sampled data
- Add configurable sensitive-data redaction to data access
- Trace database-backed agent requests with OpenTelemetry
Strengths
- Offers MCP and REST access from one API layer
- Supports multiple structured database backends
- Includes configurable redaction, row-level controls, and tracing
Limitations
- API discovery requires a configured AI provider
- Methods and protections depend on generated YAML and plugin configuration
- Some security and write enhancements remain on the roadmap
Frequently asked questions
Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.