Skip to main content
Glama
Sign In
MCPg - Production-grade PostgreSQL MCP Server

MCPg - Production-grade PostgreSQL MCP Server

by devopam
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Vector range search

vector_range_search
Read-only

Returns rows within a maximum distance of a query vector for de-duplication, similarity gating, or clustering pre-passes; results are distance-ordered and limit-capped.

Instructions

Return every row within max_distance of a query vector (a threshold-based query rather than top-k). Useful for de-dup, similarity gating, and clustering pre-passes. Still ordered by distance and capped at limit to avoid pulling huge result sets. Reports available=false if the pgvector extension is not installed.

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>",
      "table": "<table>",
      "column": "<column>",
      "query_vector": "<query_vector>",
      "max_distance": "<max_distance>"
    },
    "name": "vector_range_search"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNo
tableYes
columnYes
metricNol2
schemaYes
databaseNoOptional: 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.
max_distanceYes
query_vectorYes

Output Schema

NameRequiredDescriptionDefault
matchesYes
availableYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.8.4
    • 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."
  2. First observedv0.6.8

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and openWorldHint=false, so the safety profile is covered; the description adds real behavior beyond that: results are still distance-ordered, capped at limit to prevent huge result sets, and the tool reports available=false when pgvector is absent. It stops short of describing failure modes for a missing column/index or how the threshold interacts with the chosen metric.

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?

Four short sentences, front-loaded with the defining behavior (threshold vs top-k) before the use cases and the limit/ordering caveat. Slight redundancy between the limit clause and the 'huge result sets' rationale, but nothing is wasted.

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?

An output schema exists, so return-shape detail is unnecessary, and the description covers purpose, use cases, ordering/cap behavior, and the pgvector availability flag. The remaining gap is the undocumented metric parameter, which matters for interpreting max_distance across 8 parameters at 13% schema coverage.

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 description coverage is only 13%, so the description must compensate, and it does explain max_distance as a threshold and limit as a result cap with ordering. However, it never explains the metric parameter (default l2, no enum) even though the meaning of a max_distance threshold depends heavily on which distance metric is used, and schema/table/column are left to inference.

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

Purpose5/5

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

The description names a specific verb and resource (return every row within max_distance of a query vector) and immediately scopes it as a threshold-based query rather than top-k, which is exactly the axis that separates it from the sibling vector_search. An agent can tell which tool to pick without opening either schema.

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

Usage Guidelines4/5

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

It gives concrete when-to-use contexts (de-dup, similarity gating, clustering pre-passes) and implicitly contrasts with top-k retrieval. It does not explicitly name vector_search/mmr_search/hybrid_search as the alternative for top-k queries, so the routing is implied rather than stated.

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

Deploy Server

Other Tools