MCPg - Production-grade PostgreSQL MCP Server

Overview Schema Source Related Servers Discussions Admin

Get TurboQuant index metadata

get_turboquant_index_metadata

Read-only

Fetch metadata for a single turboquant index by schema and index name, returning typed attributes plus the full raw payload for advisory analysis.

Instructions

Fetch the tq_index_metadata payload for a single turboquant index (schema.index). Documented fields are surfaced as typed attributes; the full upstream payload is preserved in raw_metadata so advisors can reach unanticipated fields. Raises when the extension is not installed or no turboquant index by that name exists. Returns an object with schema, index, algorithm_version, quantizer_family, residual_sketch_kind, fast_path_eligible, capability_flags, delta_state, maintenance_recommended, and raw_metadata (full upstream payload).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "schema": "<schema>",
      "index": "<index>"
    },
    "name": "get_turboquant_index_metadata"
  }
}

Input Schema

Name	Required	Description
`index`	Yes
`schema`	Yes
`database`	No	Optional: a database id from list_databases, to target a configured secondary (read-only) database; omit for the primary. Database names that are not configured ids are rejected.

Output Schema

Name	Required	Description	Default
`index`	Yes
`table`	Yes
`column`	Yes
`schema`	Yes
`opclass`	No
`input_type`	No
`operability`	Yes
`capabilities`	Yes
`raw_metadata`	Yes
`access_method`	No
`delta_enabled`	No
`heap_relation`	No
`index_options`	Yes
`delta_head_block`	No
`delta_live_count`	No
`delta_page_depth`	No
`delta_tail_block`	No
`delta_live_fraction`	No
`delta_batch_page_count`	No
`delta_merge_thresholds`	Yes
`delta_merge_recommended`	No
`heap_live_rows_estimate`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.8.4Nov 5, 2026

changedInput schema / properties / database / description

Previous value: -"Optional: target a configured secondary (read-only) database by name; omit for the primary. Call list_databases to see the configured ids."New value: +"Optional: a database id from list_databases, to target a configured secondary (read-only) database; omit for the primary. Database names that are not configured ids are rejected."

First observedv0.6.8Jul 6, 2026

TDQS

A3.7/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish readOnlyHint=true and openWorldHint=false, and the description adds genuinely new behavior: it raises when the extension is not installed or when no turboquant index by that name exists, and it discloses that typed attributes are a curated subset with the full upstream payload preserved in raw_metadata. That failure-mode and truncation disclosure is exactly the kind of context annotations cannot carry.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The critical information — what is fetched and for which index — is front-loaded, and the failure conditions follow logically. The trailing enumeration of ten return-field names is somewhat redundant given an output schema exists, but it is compact and does orient the reader.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only three-parameter lookup with an output schema, the description covers what is returned at a high level, the error cases, and the raw_metadata fallback. An output schema exists so detailed return-value documentation is not required; the only minor gap is the lack of routing guidance versus the other turboquant inspection tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33% (just the optional database parameter), so the description needs to carry weight for schema and index. It does partially: '(schema.index)' defines the pair as a qualified index identity, but gives no guidance on casing, quoting, or whether a non-turboquant index name is simply a not-found case. The database parameter is fully explained in the schema itself.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource — 'Fetch the tq_index_metadata payload for a single turboquant index' — and the parenthetical '(schema.index)' pins down the lookup key. 'Single' implicitly distinguishes it from the sibling list_turboquant_indexes, though that sibling is never named, so the contrast requires a small inference.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied rather than stated: the tool is for retrieving metadata on one known index, and the mention of advisors reaching 'unanticipated fields' via raw_metadata hints at an investigative use case. There is no explicit when-to-use/when-not guidance and no named alternative (e.g., list_turboquant_indexes for discovery).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server