An add-on that fetches current documentation and code examples for software libraries and frameworks when the agent needs them.

Use it when asking about how to use a library or framework, especially when you need current API details or example code.

It reduces the chance of answers relying on outdated information from the model’s training data.

context7 — MCP server by shanraisshan

Install

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.

agentmods

npx agentmods add mcp/shanraisshan/claude-code-best-practice/context7

Clone the repo

git clone --depth 1 https://github.com/shanraisshan/claude-code-best-practice

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

context7 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 2d 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.

Origin

Copies of this mod

8 near-identical copies found in the catalogue:

context7 — 100% identical, 2 lines differ
context7 — 100% identical, 2 lines differ
context7 — 100% identical, 2 lines differ
Context7 — 100% identical, 4 lines differ
context7 — 100% identical, 2 lines differ
context7 — 100% identical, 2 lines differ
context7 — 100% identical, 2 lines differ
context7 — 100% identical, 2 lines differ

.mcp.json · 9 lines

What it actually says

{
  "context7": {
    "command": "npx",
    "args": [
      "-y",
      "@upstash/[email protected]"
    ]
  }
}

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.

2d ago First seen · 9 lines scan A e35e4e0cc0e7

Subscribe to this mod's changes

context7 is an MCP server published in the GitHub repository shanraisshan/claude-code-best-practice (65,460 stars, last pushed today), 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. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Data and AI Writing and docs agentic-ai agentic-coding agentic-engineering agentic-workflow ai ai-agents

elicit

Elicitation MCP server. Runs locally from the @blizzy/mcp-elicit npm package.

shanraisshan/claude-code-hooks · not measured

figma-desktop

A Model Context Protocol Server that runs as stdio, wrapping a Streamable HTTP server, so any MCP-supporting client can use Streamable HTTP MCP Servers. Runs locally from the @pyroprompts/mcp-stdio-to-streamable-http-adapter npm package. Needs 1 environment variable to run.

L-X-T/ng-agentic · not measured

context7

Getting it into your agent

Grade A, and why

Nothing flagged

Copies of this mod

What it actually says

What this file has done since we first saw it

Other mcp servers, from other repositories

elicit

figma-desktop

chrome-devtools

patch-file-mcp

docs-langchain

reference-langchain