Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/viknesh20-20/claude-code-tool-kitWrote 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.
[](https://agentmods.dev/mcp/viknesh20-20/claude-code-tool-kit/redis)<a href="https://agentmods.dev/mcp/viknesh20-20/claude-code-tool-kit/redis"><img src="https://agentmods.dev/badge/mcp/viknesh20-20/claude-code-tool-kit/redis/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.
<a href="https://agentmods.dev/mcp/viknesh20-20/claude-code-tool-kit/redis"><img src="https://agentmods.dev/badge/mcp/viknesh20-20/claude-code-tool-kit/redis.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
redis 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 1mo 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.
This is a copy
100% identical to redis — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
{
"redis": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-redis"
],
"env": {
"REDIS_URL": "${REDIS_URL}"
}
}
}What else .mcp.json configures
This page is one entry in a file that holds 45. Installing the file brings all of them; each is measured and scanned on its own page.
- MCP server aws A not measured
- MCP server brave-search A not measured
- MCP server browserbase A not measured
- MCP server chroma A not measured
- MCP server claude-context A not measured
- MCP server cloudflare A not measured
- MCP server context7 A not measured
- MCP server datadog A not measured
- MCP server e2b A not measured
- MCP server elevenlabs A not measured
- MCP server exa A not measured
- MCP server fetch A not measured
- MCP server figma A not measured
- MCP server filesystem A not measured
- MCP server firecrawl A not measured
- MCP server github A not measured
- MCP server gitlab A not measured
- MCP server grafana A not measured
- MCP server huggingface A not measured
- MCP server kubernetes A not measured
- MCP server linear A not measured
- MCP server magic A not measured
- MCP server memory A not measured
- MCP server mongodb A not measured
- MCP server netlify A not measured
- MCP server notion A not measured
- MCP server perplexity A not measured
- MCP server playwright A not measured
- MCP server postgres A not measured
- MCP server puppeteer A not measured
- MCP server qdrant A not measured
- MCP server replicate A not measured
- MCP server sentry A not measured
- MCP server sequential-thinking A not measured
- MCP server serena A not measured
- MCP server slack A not measured
- MCP server snyk A not measured
- MCP server sonarqube A not measured
- MCP server sqlite A not measured
- MCP server stripe A not measured
- MCP server supabase A not measured
- MCP server tavily A not measured
- MCP server twilio A not measured
- MCP server vercel A not measured
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.
- 1mo ago First seen · 12 lines scan A 956098b3a919
redis is an MCP server published in the GitHub repository viknesh20-20/claude-code-tool-kit (7 stars, last pushed 5mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. It is 100% identical to redis, differing in 0 lines, and is treated as a copy.
Other mcp servers, from other repositories
acmi-mcp
Persistent agent memory via ACMI — Profile/Signals/Timeline. 16 tools on Upstash Redis. Runs locally from the @madezmedia/acmi-mcp npm package. Needs 2 environment variables to run.
redis-mcp
Redis MCP server providing tools and resources for interacting with Redis databases through the Model Context Protocol. Runs locally from the redis-mcp npm package.
unstorage-mcp
Key-Value storage MCP server based on unstorage. Runs locally from the @slow-groovin/unstorage-mcp npm package.
mcp-memory-redis
MCP server "mcp-memory-redis" as configured in BakeMark/mcp-memory-redis. Runs locally from the mcp-memory-redis npm package.
mcp-server-redis
MCP Redis server with data operations, permission control and operation logs. Runs locally from the @liangshanli/mcp-server-redis npm package.
mcp-server-motherduck
A MCP server for MotherDuck and local DuckDB. Runs locally from the mcp-server-motherduck Python package.