Maindex Expert Memory Service

This connector has been deprecated

Replaced by Maindex Expert Memory Service.

Duplicate entry

memory_search

Read-onlyIdempotent

Full-text and semantic search across memories. Multi-tier retrieval: exact match, relaxed OR fallback with synonym expansion, fuzzy trigram, and optional semantic/hybrid search. Read-only. Returns { items, total, search_mode, retrieval_sources, degraded_components }.

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": {
      "q": "<q>"
    },
    "name": "memory_search"
  }
}

Input Schema

Name	Required	Description	Default
`q`	Yes	Search query
`kind`	No	Filter by memory kind
`sort`	No	Sort field	relevance
`tags`	No	Filter by tags
`team`	No	Team slug filter. Omit for mixed personal+team results. Use "personal" for personal-only.
`limit`	No	Maximum number of results to return
`order`	No	Sort order: ascending or descending	desc
`offset`	No	Number of results to skip for pagination
`status`	No	Filter by status: active, stale, deleted
`tag_mode`	No	Tag matching mode: all (AND) or any (OR)	all
`tag_facet`	No	Filter by tag facet
`collection`	No	Filter by collection slug or ID
`session_id`	No	Filter by interaction session
`canon_status`	No	Filter by canon status
`allow_relaxed`	No	Allow AND-to-OR relaxed fallback when strict search returns nothing
`search_fields`	No	Restrict search to specific fields
`stale_penalty`	No	How much to penalize stale memories in ranking. 0 = no penalty, 1 = fully suppress. Default 0.5.
`max_confidence`	No	Maximum confidence as an integer percentage from 0 to 100
`min_confidence`	No	Minimum confidence as an integer percentage from 0 to 100
`search_strategy`	No	Search strategy: auto (best available), lexical (text only), semantic (vector only), hybrid (both with fusion)	auto
`verification_status`	No	Filter by verification status
`include_match_context`	No	Include highlighted match context snippets
`include_graph_neighbors`	No	Include graph-linked neighbor memories in results
`include_score_breakdown`	No	Include per-signal score breakdown for each result

Output Schema

Name	Required	Description
`items`	Yes	Search result items
`total`	Yes	Total matching count
`search_mode`	No	Search mode used
`suggested_tags`	No	Suggested related tags
`degraded_reason`	No	Reason for degradation
`retrieval_sources`	No	Retrieval sources used
`degraded_components`	No	Components running in degraded mode

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

B3.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the 'Read-only' sentence is largely redundant. However, the description adds genuinely new behavior: the multi-tier retrieval ladder (exact, relaxed OR with synonym expansion, fuzzy trigram, semantic/hybrid) and the presence of degraded_components in the response, which tells the agent results may be partial.

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?

Three tight sentences: purpose first, mechanism second, safety and return shape last. Nothing is wasted, though the 'Read-only' line duplicates the annotations and could be dropped in favor of sibling routing guidance.

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

Completeness3/5

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

With an output schema present, the response-shape sentence is optional rather than necessary, and full schema coverage means parameters need no elaboration. What is missing for a 24-parameter search tool in a crowded sibling set is disambiguation guidance, so the definition is adequate but not complete.

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% across 24 parameters, so the schema already carries the parameter burden and the baseline is 3. The description only adds meaning for the fallback behavior (allow_relaxed) and strategy selection implicitly, not for the many filter parameters.

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?

States a specific verb and resource ('Full-text and semantic search across memories') and names the retrieval mechanisms, so the agent knows exactly what the tool does. It does not distinguish itself from siblings such as memory_list or memory_recall, which likely overlap in the retrieval space, 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 Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance and no named alternative. With siblings like memory_recall, memory_list, and memory_get_related in the same family, the description leaves the agent to infer which retrieval tool to pick.

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

All Maindex Expert Memory Service tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?