What is indexed-text-matching?

A guide for finding text in MongoDB without falling back to slow scans. It explains case-insensitive matching, substring search, text indexes, wildcard fields, sorting, and counting.

Use it when adding or reviewing browse search, especially searches that ignore letter case or match part of a string.

Common regular-expression searches can read every record instead of using an index, becoming slow as the database grows.

How jtv4k/mongodb-memory-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to jtv4k/mongodb-memory-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/jtv4k/mongodb-memory-mcp/main/.claude/skills/indexed-text-matching/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/jtv4k/mongodb-memory-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/jtv4k/mongodb-memory-mcp/indexed-text-matching/github.svg)](https://agentmods.dev/skills/jtv4k/mongodb-memory-mcp/indexed-text-matching)

Your own site

<a href="https://agentmods.dev/skills/jtv4k/mongodb-memory-mcp/indexed-text-matching"><img src="https://agentmods.dev/badge/skills/jtv4k/mongodb-memory-mcp/indexed-text-matching/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/jtv4k/mongodb-memory-mcp/indexed-text-matching"><img src="https://agentmods.dev/badge/skills/jtv4k/mongodb-memory-mcp/indexed-text-matching.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,777 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00110	$0.01777
Opus 5.5	$0.00044	$0.00711
Sonnet 5.5	$0.00022	$0.00355
Haiku 4.5	$0.00011	$0.00178

Measured 2mo ago against content hash 7e696f8eb959, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

indexed-text-matching scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/indexed-text-matching/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Indexed text matching

Every text-matching decision in this repository is downstream of three facts about MongoDB indexes. Get these wrong and the query works — correctly, even — while silently scanning the collection on every call.

The three disqualifying facts

A case-insensitive $regex can never use an index. Case folding defeats b-tree bounds even when the pattern is anchored: /^abc/i scans. The index stores Abc and abc in different places, and the regex engine cannot ask for both ranges.
An unanchored $regex cannot use index bounds either, case-sensitive or not. /abc/ reads every key (a full index scan at best, a collection scan when the filtered fields are not covered).
A collation index does not rescue a regex. $regex only uses an index whose collation is simple; a strength-2 (case-insensitive) collation helps equality and range queries, never regex.

The consequence: substring or case-insensitive matching belongs to MongoDB Search, or to a value normalised at write time. There is no third road. This repository learned that concretely — browse search originally shipped as an unanchored 'i' regex over title/sourceId/uri and was a collection scan on every keystroke until it moved onto the documents text index.

Choosing the mechanism

You need	Use	Notes
Exact match, case fixed at write time	b-tree equality on a normalised value	`tags` are lowercased on ingest for exactly this reason
Exact match, arbitrary case, in $search	`equals` on a `token` field with the `lowercase` normalizer	`tokenEquals()` in `knowledge-service.ts`; also how the text-leg filters work
Prefix, case-insensitive	`wildcard` `abc*` on a keywordLowercase `string` field	no leading-wildcard cost
Substring, case-insensitive	`wildcard` `abc` on a keywordLowercase `string` field	the browse-search recipe below
Words / relevance ranking	`text` on a `lucene.standard` `string` field	the chunks text index; this is search, not matching
Sorting inside `$search`	`token` (strings), `date`, `number` mappings on every field you sort by	unmapped fields cannot be sorted; `_id` cannot serve as a tie-break

Read the full file on GitHub · 132 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 132 lines · 110 tokens per session scan A 7e696f8eb959

Subscribe to this mod's changes

indexed-text-matching is a skill published in the GitHub repository jtv4k/mongodb-memory-mcp (0 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 110 tokens to every session and 1,777 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Databases MongoDB

indexed-text-matching next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
indexed-text-matchingjtv4k/mongodb-memory-mcp	Skill	0	2mo ago	Apache-2.0	A	110	Claude Code
dbxt8y2/dbx	Skill	29k	yesterday	Apache-2.0	A	74	Claude Code, Codex
azure-mgmt-mongodbatlas-dotnetmicrosoft/skills	Skill	3.2k	yesterday	MIT	A	64	Claude Code
nosqliPurpleAILAB/Decepticon	Skill	6.5k	8d ago	Apache-2.0	A	38	Claude Code, Codex
byted-volcengine-mongodbbytedance/agentkit-samples	Skill	484	yesterday	Apache-2.0	A	82	Claude Code, Codex
commerce-app-storageadobe/skills	Skill	319	yesterday	Apache-2.0	A	78	Claude Code
mongodb-connectionfcakyon/claude-codex-settings	Skill	1.2k	yesterday	Apache-2.0	A	122	Claude Code

mongodb-memory-mcp: Skill for Claude Code