Turbo Quant Memory MCP Server

by Lexus2016

Overview Schema Source Related Servers Discussions Admin

semantic_search

Retrieve relevant project memories through hybrid vector and BM25 search, then filter by memory tier or source type to surface decisions, notes, or indexed docs.

Instructions

Compact memory retrieval (dense vector + BM25, fused via RRF).

By default only the durable and reference tiers are searched, so session handoff notes (which live in the episodic tier) are NOT returned. To recover handoffs / session summaries pass tier_filter=["episodic"] (or list every tier to opt everything in). For a query-free "where did I leave off" bootstrap at session start, prefer the recent_context tool instead.

source_filter narrows results by source type: "notes" returns only memory notes (decisions/lessons/patterns/handoffs), "markdown" only indexed doc blocks. In doc-heavy projects the reference blocks often crowd notes out of the top ranks on question-shaped queries — when you are asking "what did we decide/learn about X", pass source_filter="notes".

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": {
      "query": "<query>"
    },
    "name": "semantic_search"
  }
}

Input Schema

Name	Required	Default
`limit`	No
`query`	Yes
`scope`	No	project
`tier_filter`	No
`source_filter`	No

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.36.1Nov 10, 2026

TDQS

A4.1/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does disclose a non-obvious default: only `durable` and `reference` tiers are searched, so episodic handoff notes are silently excluded unless opted in. It also explains the ranking-crowding behavior where reference doc blocks outrank notes on question-shaped queries. It omits any mention of result volume, scoring transparency, or mutation/permission concerns (though retrieval is inherently read-only).

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?

Front-loads the mechanism, then addresses the default tier exclusion (the most likely failure mode), then filter guidance — a sensible priority order. Slightly verbose with doubled-backtick RST markup and some repetition of the tier opt-in idea, but no sentence 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 needn't be explained, and the description covers the two highest-risk behavioral facts (hidden episodic exclusion, source crowding) plus their remedies. The remaining gap is `scope` defaulting to 'project' and `limit` defaulting to 5, which an agent cannot learn from the schema and which materially change results.

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 0%, so the description must compensate; it does so thoroughly for `tier_filter` and `source_filter`, including the allowed values `notes` vs `markdown`. However `query`, `limit`, and `scope` receive no explanation at all, leaving three of five parameters undocumented anywhere.

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?

Opens with a concrete verb+resource: 'Compact memory retrieval' hybridized as dense vector + BM25 with RRF fusion, which tells an agent exactly what kind of tool this is. It differentiates from `recent_context` by name, but does not distinguish itself from other retrieval-adjacent siblings such as `get_related_entities` or `hydrate`, so it stops short of a 5.

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?

Gives explicit when-to-use routing: pass `tier_filter=["episodic"]` to recover handoffs, use `recent_context` instead for a query-free session bootstrap, and pass `source_filter="notes"` when asking 'what did we decide/learn about X'. The alternatives and the conditions selecting them are stated directly.

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