Skip to content

AI & Memory MCP Server

Context7

Up-to-date code documentation for LLMs and AI code editors.

Scan found nothing by upstash49,251MITTypeScriptBeginnerstdio
View on GitHub Install Guide

Install

Claude Code

claude mcp add context7 -- npx -y @upstash/context7-mcp

Safety Report

100% Scan found nothing
Scanned 5 months ago
8 passed
Security
Authentication
details

Public docs API, no sensitive credentials

Pass
CORS Policy
details

stdio transport

N/A
Rate Limiting
details

Upstash API rate limits

Pass
Known CVEs
details

No public CVEs

Pass
Code Quality
Dependency Audit
details

No known vulnerabilities

Pass
Dangerous Patterns
details

No dangerous code patterns detected

Pass
License
details

MIT License

Pass
Code Source
details

Upstash (verified company)

Pass
Community
Maintenance Status
details

Active development

Pass

Learn about our security methodology →

Compatibility

Claude CodeFull support
Tested
CursorFull support
Tested
VS CodeFull support
Tested
Windsurf
Not Tested
Claude Desktop
Not Tested

Tools Provided (2)

resolve-library-id

Resolve a package name to a Context7 library ID

get-library-docs

Fetch documentation for a library

Frequently Asked Questions

What is Context7?

Up-to-date code documentation for LLMs and AI code editors.

What tools does Context7 provide?

Context7 provides 2 tools including resolve-library-id, get-library-docs. Each tool can be called by AI agents to perform specific operations.

Is Context7 safe to use?

We cannot tell you that, and nobody scanning at this scale can. What we did in March 2026 was shallow-clone Context7 and run five keyword searches over its source: auth identifiers, CORS configuration, rate-limit identifiers, the dependency manifest against a hardcoded list of 18 known-vulnerable packages, and unguarded eval/exec calls. None of them matched. A text search cannot follow a variable, judge intent, or tell you what a server does once it is running, so "nothing matched" is not "safe". What the scan does and does not cover is written out at /mcp/security.

What are alternatives to Context7?

Similar MCP servers include Cognee, Hindsight, Basic Memory. Each serves a similar purpose but may differ in features, language, and compatibility.

Similar MCP Servers

Cognee

Scan flagged something
by topoteretes

Memory manager for AI apps and Agents using various graph and vector stores and allowing ingestion from 30+ data sources

ai memory Python stdio
14.2k 11 tools
View

Hindsight

Not scanned
by vectorize-io

Hindsight: Agent Memory That Works Like Human Memory - Built for AI Agents to manage Long Term Memory

ai memory Python stdio
4.1k 3 tools
View

Basic Memory

Scan found nothing
by basicmachines-co

Local-first knowledge management with bi-directional LLM sync via Markdown files.

ai memory Python stdio
claude mcp add basic-memory -- uvx basic-memory
2.7k
View
Was this helpful?

Free AI writing tools

Check a draft for AI tells, then fix what the check finds.

Stay Updated on MCP Servers

New servers, safety alerts, and install guides — weekly.