# pg-aiguide MCP server > Search PostgreSQL, TimescaleDB and PostGIS docs and load Postgres best-practice skills for schema design and migrations. - Listing: https://mcp.tc/i/pg-aiguide - Connect: use the server's own URL `https://mcp.tigerdata.com/docs` (no sign-in); clients connect to it directly. The listing link is a page, not an MCP endpoint. - Type: remote (Streamable HTTP) - Auth: none - Category: [Docs & Knowledge](https://mcp.tc/c/docs-knowledge) - Vendor: Tiger Data (Timescale) - Homepage: - Repository: - Package: npm `@tigerdata/pg-aiguide` ## About pg-aiguide gives coding assistants version-aware documentation search across PostgreSQL, Tiger Cloud (TimescaleDB) and PostGIS. Search combines keyword (BM25) and semantic vector ranking, and the weighting is adjustable. It also serves curated skills for table design, hypertables, pgvector, hybrid text search, schema exploration and safe migrations. It runs as a hosted streamable-http endpoint at https://mcp.tigerdata.com/docs. No sign-in or API key is needed. The same project is also published as an npm package and container image, and as a Claude Code plugin. ## What it can do - Search PostgreSQL, TimescaleDB and PostGIS documentation - Switch between keyword-only, semantic-only or blended search - Load Postgres table design best-practice skills - Find tables that should become TimescaleDB hypertables - Plan and test PostgreSQL schema migrations - Set up pgvector and hybrid BM25 plus vector search ## Tools (2) - `search_docs`: Hybrid keyword and semantic search over Tiger Cloud, PostgreSQL and PostGIS documentation. (read-only) - `view_skill`: Retrieve a named skill with TimescaleDB and PostgreSQL best practices. (read-only) ## Example prompts - "Create a Postgres schema for users with unique emails, using pg-aiguide." - "Search the PostgreSQL docs for how NULLS NOT DISTINCT works." - "Which of my tables should be converted to TimescaleDB hypertables?" - "How do I set up hybrid BM25 and vector search in Postgres?" ## Install ### Claude Code 1. Run this in a terminal, in your project folder: ```bash claude mcp add --transport http pg-aiguide https://mcp.tigerdata.com/docs ``` 2. Start Claude Code and type `/mcp`. **pg-aiguide** should show as connected. Add `--scope user` to make it available in every project, not just this one. ### Claude Desktop 1. Open **Settings → Connectors** and click **Add custom connector**. 2. Name it **pg-aiguide** and paste this URL: ```url https://mcp.tigerdata.com/docs ``` 3. Click **Add**. Its tools appear in the chat’s tools menu. Claude Desktop’s JSON config file only starts local servers. Remote servers go through Connectors, and connectors you add on claude.ai show up here too. ### claude.ai 1. Open the connector form on claude.ai. This button fills in the name and URL for you: [Add to claude.ai]() (opens connector settings) 2. Check that the URL reads `https://mcp.tigerdata.com/docs` and click **Add**. 3. Turn it on in a chat from the tools menu. Free plans allow one custom connector. On Team and Enterprise plans an owner adds it under **Organization settings → Connectors**. ### ChatGPT 1. On chatgpt.com, open **Settings → Security and login** and turn on **Developer mode**. 2. Go to `chatgpt.com/plugins` and click **+** to create an app for a remote MCP server. 3. Paste `https://mcp.tigerdata.com/docs` as the server URL and choose **No authentication**. Developer mode is available on the web for Plus, Pro, Business, Enterprise and Education accounts. ### Cursor [Add to Cursor]() (opens Cursor) Or add it by hand to `~/.cursor/mcp.json` (all projects) or `.cursor/mcp.json` (this project): `mcp.json`: ```json { "mcpServers": { "pg-aiguide": { "url": "https://mcp.tigerdata.com/docs" } } } ``` ### VS Code [Install in VS Code]() (opens VS Code) Or from a terminal: ```bash code --add-mcp '{"name":"pg-aiguide","type":"http","url":"https://mcp.tigerdata.com/docs"}' ``` Or commit it to the repo in `.vscode/mcp.json`: `.vscode/mcp.json`: ```json { "servers": { "pg-aiguide": { "type": "http", "url": "https://mcp.tigerdata.com/docs" } } } ``` ### Devin Desktop 1. Add it to `~/.config/devin/mcp_config.json` (macOS and Linux) or `%APPDATA%\devin\mcp_config.json` (Windows): `mcp_config.json`: ```json { "mcpServers": { "pg-aiguide": { "serverUrl": "https://mcp.tigerdata.com/docs" } } } ``` 2. Refresh the MCP server list in Cascade. Devin Desktop is the new name for Windsurf. It reads `serverUrl` (or `url`) for remote servers. ### Codex ```bash codex mcp add pg-aiguide --url https://mcp.tigerdata.com/docs ``` Or edit `~/.codex/config.toml` directly: `config.toml`: ```toml [mcp_servers.pg-aiguide] url = "https://mcp.tigerdata.com/docs" ``` ### Gemini CLI ```bash gemini mcp add --transport http pg-aiguide https://mcp.tigerdata.com/docs ``` This adds it to the current project. Add `-s user` to use it everywhere. ### Any client Most clients accept this shape. Some name the URL field differently: `serverUrl` in Devin Desktop, `httpUrl` in Gemini CLI’s settings file. ```json { "mcpServers": { "pg-aiguide": { "type": "http", "url": "https://mcp.tigerdata.com/docs" } } } ``` Zed puts servers under `context_servers` in its settings. Cline needs `"type": "streamableHttp"`, or it assumes SSE. Client only starts local servers? Bridge it with `npx -y mcp-remote https://mcp.tigerdata.com/docs`. ## Details - Server version: 1.0.0 - MCP protocol version: 2025-11-25 - Last checked: 2026-10-03 (reachable) - Listed: 2026-10-03 - Updated: 2026-10-04 --- Source: https://mcp.tc/i/pg-aiguide (mcp.tc is an independent directory, not affiliated with this server's publisher). Corrections: https://mcp.tc/report