Skip to main content
Glama
infino-ai

Infino MCP server

Official
by infino-ai

Semantic (vector) search

infino_semantic_search
Read-onlyIdempotent

Search by meaning to retrieve paraphrases and synonyms, ranked by vector similarity; optionally pre-filter rows by a keyword condition first.

Instructions

Use when searching for a concept by meaning and the exact wording is unknown — this retrieves paraphrases and synonyms, not just literal matches. Embeds the query with a local model (no API key) and ranks a table's embedding column by vector similarity. Each hit carries a score that is a DISTANCE (lower is closer) plus the columns you project ('columns'; the full text column by default). Optional 'filter' restricts the ranking to rows whose keyword column matches a predicate first (a pushdown pre-filter, e.g. semantic search only within rows tagged 'billing'). For exact terms use infino_keyword_search; when the query has both literal terms and an intent use infino_hybrid_search.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kNoMaximum results.
queryYesQuery text; embedded and matched by vector similarity.
tableYesTable to search.
columnNoText column to return with each hit; inferred if omitted.
filterNoPre-filter: rank the kNN only among rows whose FTS 'column' matches 'query' (a pushdown pre-filter, not a post-filter on the results).
columnsNoWhich of the table's columns each hit returns, with full values (a projection passed straight to the engine). Defaults to the text column; '_id' and 'score' are always included. Any column works: ['id'] for compact hits at a large k, ['id', 'text'] to get the full text alongside an id to cite, ['title', 'created_at'] for metadata. Nothing is truncated; read fewer columns or a smaller k to keep results small.
vectorColumnNoVector column to search; inferred if omitted.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changedv0.14.0
    • changedInput schema / properties / columns / description
      Previous value: -"Columns to return with each hit (e.g. an id, path, or line range to cite). Defaults to the text column; '_id' and 'score' are always included."New value: +"Which of the table's columns each hit returns, with full values (a projection passed straight to the engine). Defaults to the text column; '_id' and 'score' are always included. Any column works: ['id'] for compact hits at a large k, ['id', 'text'] to get the full text alongside an id to cite, ['title', 'created_at'] for metadata. Nothing is truncated; read fewer columns or a smaller k to keep results small."
  2. Changed2 schema fields changedv0.10.0
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedInput schema / properties / filter / additionalProperties
      Removed value: -false
  3. First observedv0.7.0

TDQS

A5/5.0
Behavior5/5

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

Even though annotations already mark this as read-only, idempotent, and non-destructive, the description adds valuable behavioral details: it uses a local model with no API key, returns a distance score where lower is closer, and applies filters as a pushdown pre-filter rather than a post-filter. These details materially affect how an agent interprets results.

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

Conciseness5/5

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

The description is dense but every sentence earns its place. It front-loads the primary use case, then covers score semantics, filters, projections, and alternatives without repetition or filler. The structure is logical and scannable.

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

Completeness5/5

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

Despite having no output schema, the description explains what each hit contains, how scores behave, what defaults are used, and how nested filters work. The required parameters and common optional parameters are all contextualized. An agent has enough information to call this tool correctly and interpret its results.

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

Parameters5/5

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

The schema has 100% description coverage, but the description goes further by explaining practical parameter behavior: how 'columns' can be used for compact vs. full projection, that '_id' and 'score' are always included, that 'filter' is a pushdown pre-filter, and that the default text column is used. This is exactly the kind of parameter guidance that helps an agent invoke the tool correctly.

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 states a specific use case ('searching for a concept by meaning'), identifies the resource ('a table's embedding column'), and immediately contrasts itself with sibling tools. The distinction from exact-match and hybrid search is explicit, so an agent can select it without ambiguity.

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

Usage Guidelines5/5

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

The description opens with 'Use when...' and later names the two relevant alternatives with their conditions: 'For exact terms use infino_keyword_search; when the query has both literal terms and an intent use infino_hybrid_search.' This explicitly tells an agent when to choose this tool and when to choose a sibling.

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/infino-ai/infino-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server