Skip to main content
Glama
jagoff

MEMO MCP Server

by jagoff

memo_search

Read-onlyIdempotent

Search durable memories by keyword, semantic, or hybrid mode. Retrieve ranked hits with dates, tags, and excerpts for informed decisions.

Instructions

Search durable memories by text, vector similarity, or hybrid mode.

Read-only. Returns raw ranked hits — source records with ids, dates, tags, and excerpts. Use memo_context instead for a budgeted prompt-ready pack, memo_search_trace for scoring diagnostics, and memo_rerank to reorder hits you already have.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fileNoKeep only hits whose capture-stamped files_read/files_modified arrays contain this path fragment (case-insensitive substring). Date filters and explain are not applied in file mode.
modeNoRetrieval mode: 'hybrid' (RRF fusion of vector + BM25, default), 'vec' (semantic only), 'bm25' (keyword FTS5), 'exact' (strict-AND keyword with tag/title boost), or 'fuzzy' (typo-tolerant keyword). Unrecognized values behave as 'hybrid'.hybrid
typeNoRestrict retrieval to one memory type (e.g. 'decision', 'fact'); None searches every type.
whenNoNatural-language date phrase (EN/ES: 'yesterday', 'last week', 'hace 3 dias', ...) parsed into date_from/date_to when neither is set; unrecognized phrases apply no date filter.
limitNoMaximum hits to return (clamped to 1-500).
queryYesSearch text; empty or whitespace-only returns no hits.
sourceNoCalling layer for consult attribution (e.g. 'claude-code', 'codex'); empty falls back to client info.
date_toNoInclusive ISO date/datetime upper bound; a bare date covers that whole day. Ignored when 'file' is set.
explainNoWhen true, add per-hit 'explain' fields and a 'trace' key showing pipeline scoring. Not available with 'file' (explain stays empty).
date_fromNoInclusive ISO date/datetime lower bound (e.g. '2026-07-01'); ignored when 'file' is set.
body_charsNoCharacter cap per hit body; longer bodies are truncated with body_truncated=true. Negative disables truncation.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior4/5

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

Annotations already mark the tool as read-only and idempotent. The description adds value by confirming 'Read-only' and describing the return format ('raw ranked hits — source records with ids, dates, tags, and excerpts'). No contradiction with annotations.

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?

Two sentences plus a list of alternatives. Every sentence is substantive and earns its place. The core purpose is front-loaded, and the alternatives are clearly enumerated. No wasted words.

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?

Given the tool's complexity (11 parameters, no enums, has output schema), the description is fully adequate. It covers purpose, read-only nature, return type, and provides clear links to siblings. The output schema handles return value details, so the description doesn't need to.

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 100%, so the description carries minimal parameter burden. It does not repeat or augment schema details, which is appropriate. Baseline score of 3 is correct.

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 opens with a specific verb-resource pair ('Search durable memories') and immediately distinguishes the tool from siblings by naming three alternative tools (memo_context, memo_search_trace, memo_rerank). This meets the highest standard.

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 explicitly states when to use this tool ('for raw ranked hits') and directs the agent to three alternatives for different use cases (prompt-ready pack, diagnostics, reordering). This is exemplary guidance.

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

Install Server

Other Tools

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/jagoff/memo'

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