Skip to main content
skill CX Codex

redis-docs-mcp — Claude Code skill: features and installation

redis-docs-mcp is a Claude Code skill for interpreting Redis documentation results from MCP tools. It applies before a docs lookup or when search, fetch, or ask returns something confusing.

MIT 101 installs ★ 178 updated 2026-09-08

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add redis/agent-skills --skill redis-docs-mcp -a claude-code
Open on GitHub

What redis-docs-mcp does

The skill explains how the Redis documentation index is organized and how to work with results from search, fetch, and ask. Multiple hits can point to different sections on one page, while a short snippet may be only part of a section; the skill shows how result IDs guide a follow-up fetch.

It also clarifies the meaning of metadata.version and the index’s coverage, including client guides and Redis Cloud material. GitHub issues, package registry pages, and third-party posts fall outside the index. The Redis Docs MCP server’s tools must be available for the skill to work.

What it helps with

  • find the right Redis documentation section from search results
  • tell separate sections apart when they share a URL
  • retrieve more than a truncated search snippet
  • interpret metadata.version without treating it as the current release
  • identify which Redis materials the index covers

Example prompts for the agent

  • Find when the HEXPIRE command was introduced in the Redis docs.
  • Several search results have the same URL. Explain how to choose the right section.
  • fetch returned a short excerpt. Retrieve the full relevant section.

How to install redis-docs-mcp

1Skills CLI (Vercel)

npx skills add redis/agent-skills --skill redis-docs-mcp -a claude-code

2Manually: put the files in place

~/.claude/skills/redis-docs-mcp/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/redis-docs-mcp/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about redis-docs-mcp

How do I install redis-docs-mcp in Claude Code?

Run npx skills add redis/agent-skills --skill redis-docs-mcp -a claude-code. The skill file is at ~/.claude/skills/redis-docs-mcp/SKILL.md.

What does redis-docs-mcp do?

It explains the Redis Docs index and helps interpret search, fetch, and ask results, including section IDs and the metadata.version field.

What does redis-docs-mcp need to work?

The Redis Docs MCP server tools must be available: search, fetch, and ask.

Source text

SKILL.md · MIT
---
name: redis-docs-mcp
description: >-
  Working with the redis-docs MCP server (search / fetch / ask at redis.io/mcp) — how its index is
  shaped and how to read what it returns. Use when those tools are available and you are about to
  look something up in the Redis documentation, or when a result is confusing — fetch returned one
  short section instead of a page, several hits share one url, ids look like #sec:w1,
  metadata.version reads 1.0.0, a search came back empty, or ask was rate-limited or said the docs
  do not cover it. Also covers what redis.io does and does not index.
license: MIT
metadata:
  author: Redis, Inc.
  version: "0.1.0"
---

# Redis Docs MCP

The `redis-docs` server exposes the redis.io documentation over MCP as `search`, `fetch`, and `ask`. Those tools carry their own descriptions, and on *when* to call each one they are accurate — start with `search`, `fetch` what you need, keep `ask` for questions that span several areas. This skill covers what they get wrong or leave out.

## When to apply

- You are about to look something up through these tools.
- A result did not look like what the tool description promised.
- A `search` came back empty, or `ask` was rate-limited or declined to answer.

Reach for the sibling Redis skills first where they cover the topic — they carry curated guidance that raw docs pages do not. Use these tools to verify specifics and fill gaps.

## 1. Ids address sections, not pages

The tool descriptions say `search` returns "pages" and `fetch` returns "one Redis documentation page". The index is per **section**, and ids come in four shapes:

| Shape | Example | What `fetch` returns |
|---|---|---|
| Bare page | `commands/expire` | The whole page — ~8.5 KB for EXPIRE, examples and appendices included |
| Named anchor | `develop/using-commands/keyspace#sec:key-expiration` | That section |
| Ordinal window | `develop/ai/search-and-query/advanced-concepts/expiration#sec:w0` | That window, ~1–2 KB |
| Anchor + window | `develop/clients/jedis/connect#sec:configure-a-connection-pool-w0` | That window of that section |

What follows from this:

- **Repeated urls in one result set are not duplicates.** Several hits often share a page url while carrying distinct ids — they are different sections of the same page. Tell them apart by their snippets, not their urls.
- **`#sec:wN` ordinals are index windows.** They come back in relevance order, not `w0, w1, w2`. Don't try to reassemble a page out of snippets; `fetch` the section you actually need.
- **Never construct an id.** Valid ids come from a `search` result or an `ask` result's `sources[].id`. Guessing happens to work for `commands/<name>` and fails on everything with sections.
- **Snippets are truncated prefixes of the body, not summaries.** When one cuts off mid-word right at the interesting part, `fetch` on that id is guaranteed to contain the continuation — no need to re-search with different words.
- **Cite the page `url` and name the section in prose.** `#sec:w1` is an index address, not a web anchor. Ids with a named anchor (`#sec:<name>`, or `#sec:<name>-wN`) return a url with a usable fragment; bare `#sec:wN` ids don't.

Links in returned text point at source files — `` [`DEL`](/content/commands/del.md) `` — which are neither web URLs nor `fetch` ids. Don't cite them or turn them into ids; `search` for the term instead.

## 2. `metadata.version` means "added in", not "current as of"

`fetch` returns `metadata` with `topic`, `version`, and `section`. On a `commands/*` page that `version` is the release the command was **introduced** in — `commands/setex` reports `2.0.0`, `commands/hexpire` reports `7.4.0`. Useful for "when did this land", and nothing more: `commands/expire` reports `1.0.0` while its own body documents a behavior change in 2.1.3 and a Redis 8 interaction with Redis Search. Outside `commands/*` the field is often not a release at all — a Redis Search page reports `stack`, a product channel.

So never answer "did this change in Redis N?" from `metadata.version`. Read it from the body text, which states it explicitly ("Before Redis 8…", "since Redis 7.4"), and cite that.

## 3. What the corpus covers

The index is redis.io only — but that is broader than it sounds. Per-language client **usage guides** are indexed and returned (`develop/clients/redis-py/connect#sec:…`, `develop/clients/jedis/connect#sec:…`), along with the `integrate/…` pages, the Redis Software and Redis Cloud operational docs under `operate/…`, and the Kubernetes operator's generated CRD reference. So search first, including for client-library and Enterprise questions.

Details often sit past the snippet. A search for redis-py's `max_connections` returns `develop/clients/redis-py/async#sec:connection-pools` with a snippet that never mentions it, yet the fetched section documents it. For a library's complete signatures, its own API reference or source is the authority.

Genuinely outside the index: GitHub issues and discussions, package-manager pages (PyPI, npm, Maven), and third-party posts.

So `fetch` the relevant hits before concluding anything is missing, and even then report it as "not found in the results I retrieved" — never as "not on redis.io" or "does not exist".

## 4. `ask` costs more than it looks

- **Rate-limited per IP at a low per-minute budget**, shared by everyone behind the same NAT, so an office or a CI runner can exhaust it collectively. On a rate-limit error, back off before retrying rather than retrying straight away, and ask one narrow question at a time.
- **On a refusal, do not retry it reworded.** "The documentation does not cover this" is a grounded result, not a parsing failure. Fall back to `search` + `fetch` instead.
- **`ask` → `sources[].id` → `fetch`** when you want the primary source behind a synthesized answer.

Query text from every tool reaches Redis, and from `ask` the model provider behind the gateway too, so prefer a generic question about the Redis command or behavior over pasting in proprietary code.

© Redis, Inc. · MIT · redis/agent-skills

Similar skills

All skills for Data and databases →

From the same set16

The whole set →
iris-development iris-development — a skill for Redis Agent Memory: wire an AI agent to a persistent memory store on Redis Cloud, with session events and searchable long-term records. CX Codex +1 1,700installs add-agent-memory add-agent-memory — a skill for Claude Code and Cursor that wires Redis agent memory into existing workflows for cross-session recall. CX Codex +1 113installs add-agent-playbooks The add-agent-playbooks Claude Code skill connects Redis Iris Agent Playbooks to an existing Python agent. It runs when approved answers or repeatable procedures need to move out of prompts, documents, or a semantic cache. CX Codex +1 110installs add-redis-iris The add-redis-iris skill for Claude Code integrates Redis Iris into AI agents across various frameworks. Runs when the user requests to add agent memory, playbooks, or a context gateway. CX Codex +1 110installs add-intent-router The add-intent-router Claude Code skill replaces keyword checks or a route-only LLM call with Redis Iris Intent Router. It kicks in when an agent needs to map messages to defined intents and dispatch targets. CX Codex +1 109installs add-context-gateway The add-context-gateway Claude Code skill routes an agent’s MCP servers through one Redis Iris Context Gateway. It activates when the agent has separate server configurations or too many tool schemas in context. CX Codex +1 107installs add-lens add-lens — a skill for Claude Code and Cursor that adds Redis Iris Lens tracing to an existing AI agent. Runs when asked to add observability or per-turn traces. CX Codex +1 106installs redis-development redis-development equips Claude Code with Redis practices covering data structures, vector search, semantic caching, and query profiling. ★ 178repo stars

Project sponsors

Companies that keep this analytics open