Inspect Tidebase agent runs, resolve approval gates, and trigger recovery from your AI assistant.
Inspect Tidebase agent runs, resolve approval gates, and trigger recovery from your AI assistant.
Agent auth and credential brokering for AI agents, with checkpoints, queues, schedules, and approval gates. In your own Postgres.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"tidebase": {
"command": "npx",
"args": ["-y", "@tidebase/sdk"],
"env": {
"TIDEBASE_RUN_ID": "your-value",
"TIDEBASE_API_KEY": "your-value",
"GITHUB_TOKEN": "your-value",
"TIDEBASE_URL": "your-value",
"REVIEW_WEBHOOK_URL": "your-value",
"TIDEBASE_WEBHOOK_SECRET": "your-value",
"VITE_TIDEBASE_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| TIDEBASE_RUN_ID | Configuration value read at startup. | Optional |
| TIDEBASE_API_KEY | Credential the server authenticates with. | Yes |
| GITHUB_TOKEN | Credential the server authenticates with. | Yes |
| TIDEBASE_URL | Endpoint or connection string the server talks to. | Yes |
| REVIEW_WEBHOOK_URL | Endpoint or connection string the server talks to. | Yes |
| TIDEBASE_WEBHOOK_SECRET | Credential the server authenticates with. | Yes |
| VITE_TIDEBASE_API_KEY | Credential the server authenticates with. | Yes |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
MCP server that installs and registers other MCP servers in Cursor, VS Code, or Claude Desktop from npm, PyPI, or a local folder (via npx).
MCP server grounding agents in East African historical sources (historia = history)
It is native (SwiftUI, AppKit, ScreenCaptureKit, AVFoundation), everything runs on your Mac, and it is free: no account, no watermark, no export limits.
Manage GitHub Actions workflows from your AI assistant. List runs, read logs, re-run failed jobs, cancel builds, and trigger deployments without leaving your editor.