PostgreSQL documentation and best-practice MCP server from Timescale that gives Claude semantic and keyword search across PostgreSQL, TimescaleDB, and PostGIS docs.
The hosted MCP endpoint is documentation-focused and read-only, but generated SQL and migration advice still needs human review before execution., Documentation search results can influence schema design, indexes, retention policies, and extension setup, so test generated SQL in development first., Self-hosted deployments need database credentials and embedding configuration; keep those scoped to the docs database, not production application data., The package can expose stdio and HTTP transports; bind local HTTP deployments only where intended and protect any non-local endpoint.
Privacy notes
Queries sent to the hosted MCP endpoint may reveal database names, schema intent, performance problems, product plans, or internal architecture details., Self-hosted semantic search can send queries or documentation chunks to the configured embedding provider unless a local compatible endpoint is used., Tool outputs can contain excerpts from PostgreSQL, TimescaleDB, Tiger Cloud, or PostGIS documentation that are then included in the model context., Do not include customer data, credentials, production connection strings, or private incident details when a generalized documentation query is enough.
Author
Timescale
Submitted by
oktofeesh1
Claim status
unclaimed
Last verified
2026-06-05
Decision playbook
Review trust signals before you adopt
Signals are present but mixed. Use the checklist below to confirm the source and operational safety for your environment.
Compare context
Selected
0
Current score
63
Baseline
—
Delta
No baseline selected
No major trust-signal divergence detected in the current selection.
Source and provenance checks
Needs review
Confirm ownership and provenance before trusting install instructions.
Source link availableRequired
Open the canonical repository and verify ownership.
Done
Source provenance statusRequired
Marked as source-backed.
Done
Metadata reviewed
No reviewed flag detected in metadata.
Pending
Safety and privacy checks
Complete
Validate risk disclosures before installation or API wiring.
Safety notes presentRequired
Review the listed safety guidance before running commands.
Done
Privacy notes presentRequired
Review data handling notes before connecting accounts or secrets.
Done
Trust level risk gateRequired
Trust level does not block evaluation.
Done
Package and install checks
Needs review
Check package metadata and artifact integrity signals.
Install payload available
Install or copy payload is available for review.
Done
Package verification flag
No package verification flag provided.
Pending
Checksum metadata
No checksum provided for downloaded artifact.
Pending
Compare-driven decision checks
Needs review
Use compare context to validate trade-offs before adoption.
Compare tray has multiple entries
Add at least one more entry to compare trust differences.
4 safety and 4 privacy notes across 4 risk areas. Review closely: credentials & tokens, network access.
4 areas
SafetyNetwork accessThe hosted MCP endpoint is documentation-focused and read-only, but generated SQL and migration advice still needs human review before execution.
SafetyData retentionDocumentation search results can influence schema design, indexes, retention policies, and extension setup, so test generated SQL in development first.
SafetyCredentials & tokensSelf-hosted deployments need database credentials and embedding configuration; keep those scoped to the docs database, not production application data.
SafetyNetwork accessThe package can expose stdio and HTTP transports; bind local HTTP deployments only where intended and protect any non-local endpoint.
PrivacyNetwork accessQueries sent to the hosted MCP endpoint may reveal database names, schema intent, performance problems, product plans, or internal architecture details.
PrivacyNetwork accessSelf-hosted semantic search can send queries or documentation chunks to the configured embedding provider unless a local compatible endpoint is used.
PrivacyGeneralTool outputs can contain excerpts from PostgreSQL, TimescaleDB, Tiger Cloud, or PostGIS documentation that are then included in the model context.
PrivacyCredentials & tokensDo not include customer data, credentials, production connection strings, or private incident details when a generalized documentation query is enough.
Safety notes
The hosted MCP endpoint is documentation-focused and read-only, but generated SQL and migration advice still needs human review before execution.
Documentation search results can influence schema design, indexes, retention policies, and extension setup, so test generated SQL in development first.
Self-hosted deployments need database credentials and embedding configuration; keep those scoped to the docs database, not production application data.
The package can expose stdio and HTTP transports; bind local HTTP deployments only where intended and protect any non-local endpoint.
Privacy notes
Queries sent to the hosted MCP endpoint may reveal database names, schema intent, performance problems, product plans, or internal architecture details.
Self-hosted semantic search can send queries or documentation chunks to the configured embedding provider unless a local compatible endpoint is used.
Tool outputs can contain excerpts from PostgreSQL, TimescaleDB, Tiger Cloud, or PostGIS documentation that are then included in the model context.
Do not include customer data, credentials, production connection strings, or private incident details when a generalized documentation query is enough.
Prerequisites
An MCP-compatible client that supports remote HTTP MCP servers.
Network access to `mcp.tigerdata.com`.
PostgreSQL, TimescaleDB, Tiger Cloud, or PostGIS questions where documentation grounding is useful.
Optional self-hosting dependencies if running the package locally, including a populated Postgres docs database and embedding provider key.
pg-aiguide is a Timescale-maintained MCP server for grounding PostgreSQL work in
versioned documentation and curated best-practice skills. It supports a hosted
remote endpoint at https://mcp.tigerdata.com/docs, a Claude Code plugin path,
and a packaged @tigerdata/pg-aiguide server for local or self-hosted use.
The MCP API documents a search_docs tool for semantic, keyword, or hybrid
search across PostgreSQL manual versions, Tiger Cloud and TimescaleDB docs, and
PostGIS docs. The API also documents view_skill for curated PostgreSQL and
TimescaleDB skills when the deployment has skills enabled.
These sources were reviewed on 2026-06-05. Prefer the live repository,
README, API documentation, mcp.json, package metadata, and hosted endpoint for
current transport options, supported documentation sources, and setup commands.
Features
Hosted remote MCP endpoint for documentation search.
Packaged MCP server with stdio and HTTP entrypoints.
Semantic, keyword, and hybrid search modes through search_docs.
PostgreSQL manual coverage by version, including modern supported releases.
Tiger Cloud and TimescaleDB documentation search through the tiger source.
PostGIS documentation search for supported PostGIS versions.
Optional curated skills through view_skill when skills are enabled.
Claude Code plugin installation path for users who prefer plugin-managed setup.
Installation
For Claude Code clients that support remote HTTP MCP servers:
claude mcp add --transport http pg-aiguide https://mcp.tigerdata.com/docs
The repository also documents a Claude Code plugin path:
claude plugin marketplace add timescale/pg-aiguide
claude plugin install pg@aiguide
Restart the MCP client after adding the remote endpoint or plugin.
Use Cases
Ask Claude to check the current PostgreSQL manual before writing schema DDL.
Compare indexing approaches for a query pattern using version-aware docs.
Ground TimescaleDB hypertable, compression, retention, and continuous aggregate advice.
Search PostGIS docs before adding spatial columns, indexes, or functions.
Retrieve curated PostgreSQL best-practice skills for schema design and performance work.
Safety and Privacy
pg-aiguide is documentation-oriented, but it can still shape migration and
database-design recommendations. Review generated DDL, indexes, constraints,
extension setup, retention policies, and operational commands before applying
them to a real database.
When using the hosted endpoint, keep prompts focused on generalized docs
questions instead of private schema names, customer identifiers, credentials, or
incident details. When self-hosting, protect the docs database credentials and
review whether embedding requests are sent to an external provider or a local
OpenAI-compatible endpoint.
Duplicate Check
Existing entries cover PostgreSQL database access, generic database MCP
toolboxes, and hosted vendor services. No timescale/pg-aiguide,
@tigerdata/pg-aiguide, or mcp.tigerdata.com/docs entry was found in
content/mcp.
Show that pg-aiguide MCP Server is listed on HeyClaude. Paste this Markdown into your README — it renders the badge and links back to this page.
[](https://heyclau.de/entry/mcp/pg-aiguide-mcp-server)
How it compares
pg-aiguide MCP Server side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
PostgreSQL documentation and best-practice MCP server from Timescale that gives Claude semantic and keyword search across PostgreSQL, TimescaleDB, and PostGIS docs.
Third-party MCP server for searching Apple Developer Documentation, framework APIs, Swift and Objective-C references, sample code, platform compatibility, documentation updates, and WWDC session data.
Official Brave Search MCP server for giving Claude web, local, place, image, video, news, LLM context, and summarizer search tools backed by the Brave Search API.
✓The hosted MCP endpoint is documentation-focused and read-only, but generated SQL and migration advice still needs human review before execution.
Documentation search results can influence schema design, indexes, retention policies, and extension setup, so test generated SQL in development first.
Self-hosted deployments need database credentials and embedding configuration; keep those scoped to the docs database, not production application data.
The package can expose stdio and HTTP transports; bind local HTTP deployments only where intended and protect any non-local endpoint.
✓This is a third-party MCP server, not an official Apple project.
The server retrieves public documentation and metadata, but user queries can still reveal private project context to the MCP client, model provider, logs, and network services.
Documentation answers should be checked against the live Apple documentation before shipping platform-specific, beta, deprecated, or compatibility-sensitive code.
Use `@latest` intentionally when you want the newest package; pin a version when reproducible builds or locked team tooling are required.
✓Brave Search MCP uses BRAVE_API_KEY from the MCP client environment or command-line options.
The server defaults to stdio transport in version 2.x and can also run an HTTP transport when explicitly configured.
Tools can send web, news, image, video, local, place, and LLM-context queries to the Brave Search API.
Local and place tools may use location strings, coordinates, postal codes, or optional location headers.
Summarizer workflows depend on summary keys returned by web search and should be checked against cited source URLs.
API usage may be metered or plan-limited, especially for Pro-only local search capabilities and extra snippets.
✓Context+ can inspect source files, build AST and embedding indexes, run static analysis, create memory graph nodes, and propose code changes.
The `propose_commit` tool is designed to write code after validation and creates shadow restore points before saving.
Static analysis tools may invoke local compilers, linters, or language tools depending on the repository.
Runtime caches and memory graph data can persist source-derived embeddings and relationships after the MCP session ends.
External embedding providers can receive source-derived text, identifiers, prompts, and cluster-labeling context.
Privacy notes
✓Queries sent to the hosted MCP endpoint may reveal database names, schema intent, performance problems, product plans, or internal architecture details.
Self-hosted semantic search can send queries or documentation chunks to the configured embedding provider unless a local compatible endpoint is used.
Tool outputs can contain excerpts from PostgreSQL, TimescaleDB, Tiger Cloud, or PostGIS documentation that are then included in the model context.
Do not include customer data, credentials, production connection strings, or private incident details when a generalized documentation query is enough.
✓Prompts and tool calls may include framework names, API choices, platform targets, WWDC interests, sample-code requests, app architecture details, feature plans, and compatibility constraints.
MCP client logs and model transcripts can retain documentation queries and returned API text outside Apple's documentation site.
Avoid sending proprietary source code, unreleased product names, customer requirements, private bundle identifiers, or internal roadmap details when a public documentation lookup is enough.
✓Search queries, location parameters, result filters, language settings, freshness windows, and optional headers may reveal user intent, location, research topics, or sensitive business context.
BRAVE_API_KEY should stay out of prompts, issues, logs, screenshots, and committed files.
Returned snippets, summaries, search results, local-business metadata, images, videos, and news items can include third-party copyrighted or sensitive content.
HTTP transport should be bound and exposed carefully so the API key and search tools are not reachable by untrusted clients.
✓Source code, file paths, symbol names, comments, identifiers, embeddings, memory nodes, relations, prompts, API keys, static-analysis output, proposed diffs, and tool results may be visible to the MCP client and model provider.
Proprietary codebases can expose internal architecture, feature maps, naming conventions, secrets accidentally present in code, and product plans.
Keep API keys and provider base URLs out of committed MCP configs, logs, screenshots, and shared prompts.
Review `.mcp_data` and generated restore-point data before sharing workspaces or artifacts.
Prerequisites
An MCP-compatible client that supports remote HTTP MCP servers.
Network access to `mcp.tigerdata.com`.
PostgreSQL, TimescaleDB, Tiger Cloud, or PostGIS questions where documentation grounding is useful.
Optional self-hosting dependencies if running the package locally, including a populated Postgres docs database and embedding provider key.
Node.js and npx available for running the npm package.
An MCP client that supports stdio servers, such as Claude Code, Claude Desktop, Cursor, VS Code, Windsurf, Zed, or Cline.
Network access to retrieve public Apple Developer Documentation, sample-code, and WWDC metadata.
Agreement on whether user prompts may include private project names, unreleased app details, or proprietary API usage questions.
Brave Search API account and API key.
Node.js and npm available in the MCP client runtime.
API plan review for web, local, extra snippets, summarizer, and LLM context usage.
Tool whitelist or blacklist if the client should expose only selected search tools.
Node.js and npx available to the MCP client runtime.
A repository or workspace you are authorized to index and expose to an MCP client.
Ollama embedding model available, or an approved OpenAI-compatible embedding provider and API key.
Static analysis tools installed if you want Context+ to run native linters or compilers.
Install
claude mcp add --transport http pg-aiguide https://mcp.tigerdata.com/docs
claude mcp add apple-docs -- npx -y @kimsungwhee/apple-docs-mcp@latest