io.github.timescale/pg-aiguide is an MCP server published by io.github.timescale, hosted at mcp.tigerdata.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 3 tools, including search_docs, view_skill, get_context.
Comprehensive PostgreSQL documentation and best practices, including ecosystem tools
2 connections through 5 shared values. Tap any node.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
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.
| Parameter | Type | Description |
|---|---|---|
| limit * | any | The maximum number of matches to return. Defaults to 20. |
| query * | string | The search query. Used for BM25 when keyword or hybrid search applies, and for the embedding when semantic or hybrid search applies. |
| source * | string | The documentation source to search. "tiger" for Tiger Cloud and TimescaleDB, "postgres" for PostgreSQL, "postgis" for PostGIS spatial extension. Specific versions provided with _X.X suffixes. |
| semanticWeight * | any | Controls the balance between semantic and keyword search. 0 = keyword only, 0.5 = equal mix, 1 = semantic only. Default is 0.7 (favor semantic search). |
{
"name": "search_docs",
"title": "Search Documentation",
"description": "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.\n\nA 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.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"source",
"query",
"limit",
"semanticWeight"
],
"properties": {
"limit": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991
},
{
"type": "null"
}
],
"description": "The maximum number of matches to return. Defaults to 20."
},
"query": {
"type": "string",
"description": "The search query. Used for BM25 when keyword or hybrid search applies, and for the embedding when semantic or hybrid search applies."
},
"source": {
"enum": [
"tiger",
"postgres_14",
"postgres_15",
"postgres_16",
"postgres_17",
"postgres_18",
"postgis_3.3",
"postgis_3.4",
"postgis_3.5",
"postgis_3.6"
],
"type": "string",
"description": "The documentation source to search. \"tiger\" for Tiger Cloud and TimescaleDB, \"postgres\" for PostgreSQL, \"postgis\" for PostGIS spatial extension. Specific versions provided with _X.X suffixes."
},
"semanticWeight": {
"anyOf": [
{
"type": "number",
"maximum": 1,
"minimum": 0,
"multipleOf": 0.1
},
{
"type": "null"
}
],
"description": "Controls the balance between semantic and keyword search. 0 = keyword only, 0.5 = equal mix, 1 = semantic only. Default is 0.7 (favor semantic search)."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"results"
],
"properties": {
"results": {
"type": "array",
"items": {
"anyOf": [
{
"type": "object",
"required": [
"id",
"content",
"metadata",
"chunk_id",
"section_id",
"page_id",
"headings",
"url",
"distance"
],
"properties": {
"id": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The unique identifier of the documentation entry."
},
"url": {
"type": [
"string",
"null"
],
"description": "Link to the section on the docs site."
},
"content": {
"type": "string",
"description": "The content of the documentation entry."
},
"page_id": {
"type": "string",
"description": "Id of the page this chunk is on (get_context: the page and its outline)."
},
"chunk_id": {
"type": "string",
"description": "Id of this chunk. Pass it to get_context to read the whole section the chunk is in."
},
"distance": {
"type": "number",
"description": "The distance score indicating the relevance of the entry to the query. Lower values indicate higher relevance."
},
"headings": {
"type": "array",
"items": {
"type": "string"
},
"description": "Heading path of the section, page title first."
},
"metadata": {
"type": "string",
"description": "Additional metadata about the documentation entry, as a JSON encoded string."
},
"section_id": {
"type": "string",
"description": "Id of the section this chunk is part of (get_context)."
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"id",
"content",
"metadata",
"chunk_id",
"section_id",
"page_id",
"headings",
"url",
"score"
],
"properties": {
"id": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The unique identifier of the documentation entry."
},
"url": {
"type": [
"string",
"null"
],
"description": "Link to the section on the docs site."
},
"score": {
"type": "number",
"description": "The score indicating the relevance of the entry to the keywords. Higher values indicate higher relevance."
},
"content": {
"type": "string",
"description": "The content of the documentation entry."
},
"page_id": {
"type": "string",
"description": "Id of the page this chunk is on (get_context: the page and its outline)."
},
"chunk_id": {
"type": "string",
"description": "Id of this chunk. Pass it to get_context to read the whole section the chunk is in."
},
"headings": {
"type": "array",
"items": {
"type": "string"
},
"description": "Heading path of the section, page title first."
},
"metadata": {
"type": "string",
"description": "Additional metadata about the documentation entry, as a JSON encoded string."
},
"section_id": {
"type": "string",
"description": "Id of the section this chunk is part of (get_context)."
}
},
"additionalProperties": false
},
{
"type": "object",
"required": [
"id",
"content",
"metadata",
"chunk_id",
"section_id",
"page_id",
"headings",
"url",
"rrf_score"
],
"properties": {
"id": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "The unique identifier of the documentation entry."
},
"url": {
"type": [
"string",
"null"
],
"description": "Link to the section on the docs site."
},
"content": {
"type": "string",
"description": "The content of the documentation entry."
},
"page_id": {
"type": "string",
"description": "Id of the page this chunk is on (get_context: the page and its outline)."
},
"chunk_id": {
"type": "string",
"description": "Id of this chunk. Pass it to get_context to read the whole section the chunk is in."
},
"headings": {
"type": "array",
"items": {
"type": "string"
},
"description": "Heading path of the section, page title first."
},
"metadata": {
"type": "string",
"description": "Additional metadata about the documentation entry, as a JSON encoded string."
},
"rrf_score": {
"type": "number",
"description": "Hybrid search: fused RRF score from combining semantic and keyword result rankings."
},
"section_id": {
"type": "string",
"description": "Id of the section this chunk is part of (get_context)."
}
},
"additionalProperties": false
}
]
}
}
},
"additionalProperties": false
},
"annotations": {
"title": "Search Documentation",
"readOnlyHint": true,
"idempotentHint": true
}
}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,
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.
| Parameter | Type | Description |
|---|---|---|
| id * | ["string","null"] | Any docs id: a chunk_id or section_id from search_docs, a page_id, or a parent_id / children id from an earlier get_context. A chunk_id returns the section the chunk is in. Give this or url. |
| url * | ["string","null"] | A docs URL (tigerdata.com/docs, postgresql.org/docs, postgis.net/docs), e.g. a link found in docs text. With a #fragment it returns that section, otherwise the page. Give this or id. |
| part * | any | Which part of the text to return when part_count > 1. Defaults to the part holding the chunk you passed, else part 1. |
{
"name": "get_context",
"title": "Read docs around a search hit",
"description": "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.\n\nEvery 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.",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"id",
"url",
"part"
],
"properties": {
"id": {
"type": [
"string",
"null"
],
"description": "Any docs id: a chunk_id or section_id from search_docs, a page_id, or a parent_id / children id from an earlier get_context. A chunk_id returns the section the chunk is in. Give this or url."
},
"url": {
"type": [
"string",
"null"
],
"description": "A docs URL (tigerdata.com/docs, postgresql.org/docs, postgis.net/docs), e.g. a link found in docs text. With a #fragment it returns that section, otherwise the page. Give this or id."
},
"part": {
"anyOf": [
{
"type": "integer",
"maximum": 9007199254740991,
"minimum": 1
},
{
"type": "null"
}
],
"description": "Which part of the text to return when part_count > 1. Defaults to the part holding the chunk you passed, else part 1."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"id",
"kind",
"title",
"page_id",
"page_url",
"version",
"headings",
"url",
"text",
"part",
"part_count",
"parent_id",
"children",
"previous_id",
"next_id"
],
"properties": {
"id": {
"type": "string",
"description": "This node: a section_id, or the page_id."
},
"url": {
"type": [
"string",
"null"
],
"description": "Link to this node on the docs site."
},
"kind": {
"enum": [
"page",
"section"
],
"type": "string"
},
"part": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Which part `text` is, from 1."
},
"text": {
"type": "string",
"description": "The node as markdown with everything nested under it, led by its parent headings. When part_count > 1 this is one part."
},
"title": {
"type": "string",
"description": "Page title."
},
"next_id": {
"type": [
"string",
"null"
],
"description": "The next section at the same level, under the same parent."
},
"page_id": {
"type": "string"
},
"version": {
"type": [
"string",
"null"
],
"description": "Docs version, for versioned sources (Postgres, PostGIS)."
},
"children": {
"type": "array",
"items": {
"type": "object",
"required": [
"id",
"heading",
"characters"
],
"properties": {
"id": {
"type": "string"
},
"heading": {
"type": "string",
"description": "Its heading path below this node, e.g. \"4.1. Spatial Data Model > 4.1.1. OGC Geometry\" when the level between has no text of its own."
},
"characters": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Length of its text, including its own children."
}
},
"additionalProperties": false
},
"description": "The sections one level down, in order. Their text is already in `text`; open one by id to read just that part."
},
"headings": {
"type": "array",
"items": {
"type": "string"
},
"description": "Heading path of this node, outermost first. Empty for a page."
},
"page_url": {
"type": "string"
},
"parent_id": {
"type": [
"string",
"null"
],
"description": "The node one level up (the enclosing section, or the page). Null for a page."
},
"part_count": {
"type": "integer",
"maximum": 9007199254740991,
"minimum": -9007199254740991,
"description": "Above 1, call again with `part` for the rest."
},
"previous_id": {
"type": [
"string",
"null"
],
"description": "The previous section at the same level, under the same parent."
}
},
"additionalProperties": false
},
"annotations": {
"title": "Read docs around a search hit",
"readOnlyHint": true,
"idempotentHint": true
}
}Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.
| Parameter | Type | Description |
|---|---|---|
| path * | string | A relative path to a file or directory within the skill to view. If empty, will view the `SKILL.md` file by default. Use `.` to list the root directory of the skill. |
| skill_name * | string | The name of the skill to browse, or `.` to list all available skills. |
{
"name": "view_skill",
"title": "View Skill",
"description": "Retrieve detailed skills for TimescaleDB operations and best practices.\n\n## Available Skills\n\n<available_skills>\n[11\t]{name\tdescription}:\n design-postgis-tables\tComprehensive PostGIS spatial table design reference covering geometry types, coordinate systems, spatial indexing, and performance patterns for location-based applications\n design-postgres-tables\t\"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\"\n find-hypertable-candidates\t\"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\"\n migrate-postgres-tables-to-hypertables\t\"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\"\n pgvector-semantic-search\t\"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\"\n postgres\t\"Use this skill for any PostgreSQL database work — table design, indexing,",
"inputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"skill_name",
"path"
],
"properties": {
"path": {
"type": "string",
"description": "A relative path to a file or directory within the skill to view.\nIf empty, will view the `SKILL.md` file by default.\nUse `.` to list the root directory of the skill."
},
"skill_name": {
"type": "string",
"description": "The name of the skill to browse, or `.` to list all available skills."
}
}
},
"outputSchema": {
"type": "object",
"$schema": "https://json-schema.org/draft/2020-12/schema",
"required": [
"content"
],
"properties": {
"content": {
"type": "string",
"description": "The content of the file or directory listing."
}
},
"additionalProperties": false
},
"annotations": {
"title": "View Skill",
"readOnlyHint": true,
"idempotentHint": true
}
}