Base44
Build and edit Base44 apps from an AI assistant, and query data your app's users submit.
TigerData's pg-aiguide gives a coding agent version-accurate PostgreSQL, TimescaleDB and PostGIS guidance.
Opens Agent Studio, where connecting is one click. The connector URL below works in any MCP client.
Paste it into any MCP client. Setup docs
pg-aiguide is TigerData's documentation and expertise server for coding agents. It gives Claude, ChatGPT or any MCP client version-accurate PostgreSQL, TimescaleDB and PostGIS guidance instead of remembered syntax. Two read-only tools search the manuals and fetch curated skills, and ten user-invoked prompts carry schema-design workflows. It connects to no database of yours.
Verified connector
Listed by Anthropic as a partner connector in its Connectors Directory.
Connection checked by Agentman on .
Anthropic states this reflects the level of review a connector received, not a security audit.
Search documentation with hybrid semantic (vector) and keyword (BM25) search. Use semanticWeight to choose keyword-only (0), semantic-only (1), or a blend; mid values fuse rankings with RRF. Supports Tiger Cloud (TimescaleDB), PostgreSQL, and PostGIS.
Retrieve detailed skills for TimescaleDB operations and best practices. ## Available Skills <available_skills> [10 ]{name description}: design-postgis-tables Comprehensive PostGIS spatial table design reference covering geometry types, coordinate systems, spatial indexing, and performance patterns for location-based applications design-postgres-tables "Use this skill for general PostgreSQL table design.\n\n**Trigger when user asks to:**\n- Design PostgreSQL tables, schemas, or data models when creating new tables and when modifying existing ones.\n- Choose data types, constraints, or indexes for PostgreSQL\n- Create user tables, order tables, reference tables, or JSONB schemas\n- Understand PostgreSQL best practices for normalization, constraints, or indexing\n- Design update-heavy, upsert-heavy, or OLTP-style tables\n\n\n**Keywords:** PostgreSQL schema, table design, data types, PRIMARY KEY, FOREIGN KEY, indexes, B-tree, GIN, JSONB, constraints, normalization, identity columns, partitioning, row-level security\n\nComprehensive reference covering data types, indexing strategies, constraints, JSONB patterns, partitioning, and PostgreSQL-specific best practices.\n" find-hypertable-candidates "Use this skill to analyze an existing PostgreSQL database and identify which tables should be converted to Timescale/TimescaleDB hypertables.\n\n**Trigger when user asks to:**\n- Analyze database tables for hypertable conversion potential\n- Identify time-series or event tables in an existing schema\n- Evaluate if a table would benefit from Timescale/TimescaleDB\n- Audit PostgreSQL tables for migration to Timescale/TimescaleDB/TigerData\n- Score or rank tables for hypertable candidacy\n\n\n**Keywords:** hypertable candidate, table analysis, migration assessment, Timescale, TimescaleDB, time-series detection, insert-heavy tables, event logs, audit tables\n\nProvides SQL queries to analyze table statistics, index patterns, and query patterns. Includes scoring criteria (8+ points = good candidate) and pattern recognition for IoT, events, transactions, and sequential data.\n" ghost-database "Use this skill for persistent PostgreSQL storage in agent workflows — spin up databases on demand, test schema migrations safely on forks, and pass databases as assets between agents using Ghost.\n\n**Trigger when user asks to:**\n- Create a new PostgreSQL database quickly\n- Manage database lifecycle in agent workflows\n- Fork a database to test changes safely\n- Run analytics or heavy queries on a fork without impacting the production database\n- Share a database snapshot so others can spin up their own copy\n- Pass a database as an input or output between agents\n- Create a database for agents\n- Need many databases that are billed only when queried\n- Set up the Ghost MCP server or CLI\n\n**Note:** If the Ghost MCP server is already installed, use its tools directly — this skill is for environments without the MCP or as a reference for what's possible.\n\n**Keywords:** Ghost, ghost.build, database, create database, fork database, PostgreSQL, managed Postgres, MCP, agent database, connection string\n" migrate-postgres-tables-to-hypertables "Use this skill to migrate identified PostgreSQL tables to Timescale/TimescaleDB hypertables with optimal configuration and validation.\n\n**Trigger when user asks to:**\n- Migrate or convert PostgreSQL tables to hypertables\n- Execute hypertable migration with minimal downtime\n- Plan blue-green migration for large tables\n- Validate hypertable migration success\n- Configure compression after migration\n\n**Prerequisites:** Tables already identified as candidates (use find-hypertable-candidates first if needed)\n\n**Keywords:** migrate to hypertable, convert table, Timescale, TimescaleDB, blue-green migration, in-place conversion, create_hypertable, migration validation, compression setup\n\nStep-by-step migration planning including: partition column selection, chunk interval calculation, PK/constraint handling, migration execution (in-place vs blue-green), and performance validation queries.\n" pgvector-semantic-search "Use this skill for setting up vector similarity search with pgvector for AI/ML embeddings, RAG applications, or semantic search.\n\n**Trigger when user asks to:**\n- Store or search vector embeddings in PostgreSQL\n- Set up semantic search, similarity search, or nearest neighbor search\n- Create HNSW or IVFFlat indexes for vectors\n- Implement RAG (Retrieval Augmented Generation) with PostgreSQL\n- Optimize pgvector performance, recall, or memory usage\n- Use binary quantization for large vector datasets\n\n**Keywords:** pgvector, embeddings, semantic search, vector similarity, HNSW, IVFFlat, halfvec, cosine distance, nearest neighbor, RAG, LLM, AI search\n\nCovers: halfvec storage, HNSW index configuration (m, ef_construction, ef_search), quantization strategies, filtered search, bulk loading, and performance tuning.\n" postgres "Use this skill for any PostgreSQL database work — table design, indexing, data types, constraints, extensions (pgvector, PostGIS, TimescaleDB), search, and migrations.\n\n**Trigger when user asks to:**\n- Design or modify PostgreSQL tables, schemas, or data models\n- Choose data types, constraints, indexes, or partitioning strategies\n- Work with pgvector embeddings, semantic search, or RAG\n- Set up full-text search, hybrid search, or BM25 ranking\n- Use PostGIS for spatial/geographic data\n- Set up TimescaleDB hypertables for time-series data\n- Migrate tables to hypertables or evaluate migration candidates\n- Plan or execute safe schema migrations with zero downtime\n- Create, fork, or manage databases with Ghost\n\n**Keywords:** PostgreSQL, Postgres, SQL, schema, table design, indexes, constraints, pgvector, PostGIS, TimescaleDB, hypertable, semantic search, hybrid search, BM25, time-series, migration, Ghost\n" postgres-database-migration "Use this skill for planning, testing, and safely executing PostgreSQL schema migrations — especially when working with production data or shared databases.\n\n**Trigger when user asks to:**\n- Test a schema migration before applying it to production\n- Add, remove, or rename columns safely on a live table\n- Change a column's data type without downtime\n- Add or drop indexes, constraints, or foreign keys on large tables\n- Understand which ALTER TABLE operations lock the table\n- Roll back a failed migration\n- Plan a zero-downtime migration strategy\n- Fork a database to test a migration safely\n\n**Keywords:** migration, schema change, ALTER TABLE, add column, drop column, rename column, change type, zero downtime, lock, AccessExclusiveLock, concurrent index, forking, ghost, rollback, backfill, deploy\n\nCovers: lock-level reference for every common DDL operation, safe migration patterns, fork-based testing, zero-downtime column changes, index creation, constraint addition, backfill strategies, pre/post-migration validation, and rollback planning.\n" postgres-hybrid-text-search "Use this skill to implement hybrid search combining BM25 keyword search with semantic vector search using Reciprocal Rank Fusion (RRF).\n\n**Trigger when user asks to:**\n- Combine keyword and semantic search\n- Implement hybrid search or multi-modal retrieval\n- Use BM25/pg_textsearch with pgvector together\n- Implement RRF (Reciprocal Rank Fusion) for search\n- Build search that handles both exact terms and meaning\n\n\n**Keywords:** hybrid search, BM25, pg_textsearch, RRF, reciprocal rank fusion, keyword search, full-text search, reranking, cross-encoder\n\nCovers: pg_textsearch BM25 index setup, parallel query patterns, client-side RRF fusion (Python/TypeScript), weighting strategies, and optional ML reranking.\n" setup-timescaledb-hypertables "Use this skill when creating database schemas or tables for Timescale, TimescaleDB, TigerData, or Tiger Cloud, especially for time-series, IoT, metrics, events, or log data. Use this to improve the performance of any insert-heavy table.\n\n**Trigger when user asks to:**\n- Create or design SQL schemas/tables AND Timescale/TimescaleDB/TigerData/Tiger Cloud is available\n- Set up hypertables, compression, retention policies, or continuous aggregates\n- Configure partition columns, segment_by, order_by, or chunk intervals\n- Optimize time-series database performance or storage\n- Create tables for sensors, metrics, telemetry, events, or transaction logs\n\n**Keywords:** CREATE TABLE, hypertable, Timescale, TimescaleDB, time-series, IoT, metrics, sensor data, compression policy, continuous aggregates, columnstore, retention policy, chunk interval, segment_by, order_by\n\nStep-by-step instructions for hypertable creation, column selection, compression policies, retention, continuous aggregates, and indexes.\n" </available_skills>
Read from the server on 2026-08-18, including each tool's own safety annotations.
source enum covers PostgreSQL 14–18, PostGIS 3.3–3.6 and one Tiger corpus. PostgreSQL 13 and earlier are unreachable, as is every extension without its own corpus — the README lists pgvector documentation as coming soon, so pgvector-semantic-search guidance today rests on the curated skill rather than a searchable manual.ghost-database promotes a separate paid product. One of the ten prompts guides the agent to Ghost, a managed PostgreSQL service at ghost.build with its own CLI and MCP server, quoting a free tier of 100 compute hours and 1TB storage. Useful material, but product guidance for a commercial service rather than neutral PostgreSQL advice — and one of the three prompts Anthropic's listing does not name.search_docs against the versioned manual is the neutral source.get_prompt_template and names a template design_postgres_tables with underscores. Neither is on the live server: there is no such tool, and the real prompt is design-postgres-tables with hyphens. The post also predates the split between this connector and Tiger MCP. The live handshake is authoritative.initialize declares only tools and prompts. resources/list returns JSON-RPC error −32601, method not found — the correct response for an undeclared capability rather than a fault.initialize, tools/list and prompts/list handshake. Every behavioural claim above comes from the server's own schemas and descriptions, or from TigerData's published documentation and source.No. We read both live tool schemas on 2026-08-18 and neither accepts a connection string, a host, a port, a credential, or SQL. The complete set of inputs across both tools is a documentation source, a search query, a result limit, a search weighting, a skill name and a file path. It returns guidance text, and your agent writes the SQL.
Because its product is judgment, not capability. TigerData calls this design an AI Guide and contrasts it with wrappers that hand a model a database connection. Prompts carry the opinionated workflows a senior engineer would apply; the two tools exist to retrieve documentation and skill text underneath them. That inverts the usual connector shape, where prompts are an afterthought.
A tool is invoked by the model on its own initiative; a prompt is invoked by you. Prompts appear in your client as slash commands or a picker, and choosing one injects a curated workflow into the conversation before the model starts work. pg-aiguide's prompts take no arguments at all, so selecting one is the whole interaction. Tools then fetch supporting documentation.
Ten. Anthropic's directory entry advertises seven prompt names, but a live prompts/list call on 2026-08-18 returned ten. The three the listing omits are ghost-database, postgres and postgres-database-migration. The directory undercounts rather than overcounts here, so a reader working from the listing alone would miss the migration workflow and the umbrella router entirely.
No. Our anonymous handshake on 2026-08-18 returned both tool schemas and all ten prompts with no credential attached. The server publishes no RFC 9728 OAuth descriptor at either the root or the endpoint path, both returning HTTP 404. Anthropic's directory records the connector as authless. The only prerequisites are an MCP client and network access.
PostgreSQL 14 through 18, plus PostGIS 3.3 through 3.6 and one combined Tiger Cloud and TimescaleDB corpus. Those ten values are the complete enum on the live search schema, read 2026-08-18. Version is not a separate parameter, so you pick the corpus and the release together. A version absent from that enum cannot be searched at all.
No, and confusing them is the main risk here. Tiger MCP ships inside the Tiger CLI binary, signs in to Tiger Cloud, and exposes tools that run SQL and manage services. pg-aiguide is a separate hosted endpoint carrying only the two documentation and skills tools from that set. This page describes pg-aiguide, which reaches no database of yours.
timescale/pg-aiguide repository (retrieved 2026-08-18, HTTP 200). The exact documentation value in Anthropic's directory entry. The README gave the endpoint, per-client setup, the Agent Skills and plugin routes and the pgvector-coming-soon note. Per the repo-is-more-than-its-README rule we also pulled API.md (parameter reference, the three output shapes, and the statement that view_skill is disabled when deploying as a Claude plugin), CLAUDE.md (the nullable-not-optional convention), mcp.json (the ?disable_mcp_skills=1 variant), NOTICE/LICENSE (Apache 2.0, Timescale d/b/a Tiger Data), .env.sample and ingest/ (corpus provenance: the PostgreSQL manual from postgresql.org, PostGIS from postgis.net, Tiger docs scraped from its sitemap, embedded with text-embedding-3-small at 1536 dimensions), and the skills/ tree — ten directories matching the ten live prompts exactly, and the source for the umbrella-router structure, the DDL lock reference and the Ghost description. Note one field drift: API.md names the view_skill input name where the live schema calls it skill_name. The handshake wins. · retrieved 2026-08-18/index.md). The separation between Tiger MCP and this connector, the thirteen Tiger MCP tools, the statement that db_execute_query runs INSERT, UPDATE, DELETE and DDL, and the grouping of search_docs and view_skill under documentation and skills tools. · retrieved 2026-08-18remote.url, and resolved both blog slugs without guessing. · retrieved 2026-08-18https://mcp.tigerdata.com/docs — initialize returned capabilities for tools and prompts only; tools/list returned two tools with full descriptions, input and output schemas and safety annotations; prompts/list returned ten prompts, none declaring arguments; resources/list and resources/templates/list both returned JSON-RPC error −32601 (2026-08-18). All requests anonymous. Tool schemas committed at docs/marketing/data/tool-schemas/pg-aiguide.tools.json, the prompt sweep at docs/marketing/data/mcp-prompts-probe.json. · retrieved 2026-08-18https://mcp.tigerdata.com/.well-known/oauth-protected-resource and the same path suffixed with the endpoint's /docs segment both returned HTTP 404 with an nginx error body (2026-08-18). No RFC 9728 descriptor exists, consistent with the anonymous handshake and the directory's authless record. https://mcp.tigerdata.com/mcp also returned 404, confirming /docs is the only endpoint path on the host. · retrieved 2026-08-18Connect pg-aiguide once and your agents call these tools on their own: on a schedule, in a workflow, with nobody at the keyboard.