# `io.github.timescale/pg-aiguide` on Anlyon Radar

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by Anlyon Radar. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://radar.anlyon.com/servers/io.github.timescale/pg-aiguide
- JSON: https://radar.anlyon.com/api/v1/servers/io.github.timescale/pg-aiguide
- Version: 0.6.1 (active)
- Publisher: io.github.timescale (GitHub account)
- Runs: remote (streamable-http), local (npm,oci)
- Sign-in to list tools: none
- Repository: https://github.com/timescale/pg-aiguide
- Metadata from the official MCP Registry, synced 2026-10-21T18:50:44.907Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Comprehensive PostgreSQL documentation and best practices, including ecosystem tools
```

Scanned 2026-11-20T16:17:40.636Z over streamable-http.

**3 tools: 1 change things and 2 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 1 | ask |
| Only reads | read | 2 | allow |

## Exfil surface

3 private-data -> untrusted-input -> outbound paths in this server alone. Denying 1 outbound tool breaks every one: `mcp__pg-aiguide__get_context`.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | `mcp__pg-aiguide__get_context` `mcp__pg-aiguide__search_docs` `mcp__pg-aiguide__view_skill` |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__pg-aiguide__get_context` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__pg-aiguide__get_context` |

| Private data | Untrusted input | Outbound |
| --- | --- | --- |
| `mcp__pg-aiguide__get_context` | `mcp__pg-aiguide__get_context` | `mcp__pg-aiguide__get_context` |
| `mcp__pg-aiguide__search_docs` | `mcp__pg-aiguide__get_context` | `mcp__pg-aiguide__get_context` |
| `mcp__pg-aiguide__view_skill` | `mcp__pg-aiguide__get_context` | `mcp__pg-aiguide__get_context` |

## Findings

- **info** Long descriptions in `view_skill` ([long-description](https://radar.anlyon.com/methodology#long-description))

```untrusted-server-text
The description is 9,654 characters long, over the 2,000 this check looks for.

description ends: "..., mcv_agg, lttb, asap_smooth, rollup, two-step aggregation\n" </available_skills>"
```

- **warn** Annotations that disagree with the tool in `get_context` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "get_context" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"idempotentHint":true}; The name "get_context" says "get": a word for reading.
```


## Changes things (1)

Creates or changes something that can be changed back. Claude Code: ask.

### `get_context`

- The name "get_context" says "get": a word for reading.
- The description's first verb is "open": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag private-data: The description's first sentence says "doc": it reads documents.
- Tag untrusted-input: The input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Opens any part of the docs (a section or a whole page) as markdown, with links to move around it. Use it on a search_docs hit before answering from it: a hit is one chunk, and often a fragment (a table row without the header that says which column is which plan, one step of a procedure). Pass the hit's chunk_id to get the whole section it is in.

Every result is a node in the page's outline. parent_id goes one level up (to the enclosing section, then the page); children lists the sections one level down; previous_id / next_id move to the neighbouring sections. Pass any of those ids back in. It also takes a docs URL, e.g. a link in the text; a #fragment opens that section. Text over 20,000 characters (a whole Postgres reference page, a long page) comes back in parts: you get the part holding the chunk you passed, and part / part_count say which.
```

## Only reads (2)

Looks things up and changes nothing. Claude Code: allow.

### `search_docs`

- The name "search_docs" says "search": a word for reading.
- Tag private-data: The name "search_docs" says "search" and "doc": it reads documents.

Description, as the server wrote it:

```untrusted-server-text
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.

A hit is one chunk of a page, often part of a larger section: a table row without its header, one step of a procedure. Before answering from a hit, read it in context: get_context with the hit's chunk_id returns the whole section it is in, and from there its parent section, the page and the page's outline. For exact figures (limits, prices, plan features) prefer keyword-heavy searches (semanticWeight 0–0.3) that use the words the docs would use.
```

### `view_skill`

- The name "view_skill" says "view": a word for reading.
- Tag private-data: The description's first sentence says "retrieve" and "db": it reads databases.
- Findings: info long-description

Description, as the server wrote it:

```untrusted-server-text
Retrieve detailed skills for TimescaleDB operations and best practices.

## Available Skills

<available_skills>
[11	]{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"
  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,… [5654 more characters not shown]
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `pg-aiguide`:

```json
{
  "permissions": {
    "allow": [
      "mcp__pg-aiguide__search_docs",
      "mcp__pg-aiguide__view_skill"
    ],
    "ask": [
      "mcp__pg-aiguide__get_context"
    ],
    "deny": []
  }
}
```

Capability tags behind the rules (a read tagged outbound is asked about):

- `mcp__pg-aiguide__search_docs`: private-data
- `mcp__pg-aiguide__view_skill`: private-data
- `mcp__pg-aiguide__get_context`: private-data, untrusted-input, outbound

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T19:12:06.058Z, unchanged since 2026-11-13T12:10:37.913Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://radar.anlyon.com/methodology#remote-posture

| Fact | Observed |
| --- | --- |
| Reachable | `yes` |
| HTTP status of an anonymous initialize | `200` |
| tools/list served without credentials | `yes` |
| Tools that change things, listed without credentials | `1` |
| Protocol version | `2025-06-18` |
| WWW-Authenticate on 401 | `not observed` |
| resource_metadata in WWW-Authenticate | `none` |
| RFC 9728 protected resource metadata | `none` |
| Authorization servers | `none` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `not observed` |
| Client ID metadata documents | `not observed` |

- **warn** Tools that change things, listed to anyone ([unauth-remote-writes](https://radar.anlyon.com/methodology#unauth-remote-writes))

```untrusted-server-text
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

https://mcp.tigerdata.com/docs: tools/list returned 3 tools to an anonymous client, including get_context (write)
```

Posture changes:

- 2026-11-13T12:10:37.913Z: Tools that change things, listed without credentials `0` -> `1`
