Our grade: 4 checks
Based on public data, not a full audit. See how we grade. Something changed? Request a re-grade.
Community rating
- 5 6
- 4 4
- 3 3
- 2 0
- 1 0
Trust in production
- Trust it - 77%
- With caveats - 23%
- Wouldn't - 0%
85% would recommend this server
How reviewers scored it
- Setup & docs 4.2
- Auth experience 3.6
- Reliability 4.2
- Maintainer responsiveness 4.2
Why it got an A
Read-only documentation retrieval with a low blast radius, very active and hosted over HTTPS. Its one real flaw, prompt injection through user-submitted library instructions (CVE-2026-75130, "ContextCrush"), was fixed 5 days after it was reported. Biggest deduction: it works with no key by default, and that flaw showed that the docs it returns can carry instructions into your agent.
How to connect
// ~/.cursor/mcp.json (or .cursor/mcp.json in a project)
{
"mcpServers": {
"context7": {
"command": "npx",
"args": ["-y", "@upstash/context7-mcp", "--api-key", "YOUR_API_KEY"]
}
}
}claude mcp add --scope user --header "Authorization: Bearer YOUR_API_KEY" --transport http context7 https://mcp.context7.com/mcpIs Context7 MCP safe?
Is Context7 MCP safe to use?
Context7 MCP grades A (strong public trust signals). Login is optional, so check that it is turned on in your setup.
Does Context7 MCP have known vulnerabilities?
Not in our current data: it has no open CVEs or advisories. We re-check as new ones are published.
Does Context7 MCP support authentication?
Optionally. It can run with a login, but it does not require one, so turn it on.
Alternatives in Docs & Knowledge
- B Stack Overflow MCP ServerOfficial hosted Stack Overflow server (beta) to search questions and answers.
- B Zotero MCP (zotero-mcp-server)A community MCP server for your Zotero library, run locally from PyPI, to search, read and annotate papers, add items by DOI or BibTeX, and manage collections and tags.
- C AIOS Public Discovery MCP ServerHosted server that checks the status, recent changes and source evidence of five monitored GOV.UK employment guidance topics, including minimum wage and statutory sick pay.
- C AWS Knowledge MCP ServerAWS's hosted read-only server for AWS docs, API references, regional availability and agent skills.
- C Connect Pro for Obsidian (Smart Plugins)Paid Smart Plugins add-on that serves your open Obsidian vault to ChatGPT (Remote MCP) or to desktop AI apps on the same computer (Local MCP), to read notes, run semantic lookups and propose edits you approve in an Inbox.
Embed this badge
[](https://trustedmcp.io/servers/context7-mcp)<a href="https://trustedmcp.io/servers/context7-mcp"><img src="https://trustedmcp.io/badge/context7-mcp.svg" alt="TrustedMCP grade A" height="80"></a>Community reviews
Worth the five minutes to set up
Clear tool names, sensible outputs, very few surprises. You can tell it is actively maintained, the rough edges keep getting fixed. Good choice if you need Context7 in your agent.
Used for Pulling up-to-date library docs into prompts
- Setup & docs 4/5
- Auth experience 4/5
- Reliability 5/5
- Maintainer responsiveness 5/5
Solid and well behaved
Replaced a homegrown script with Context7 MCP and have not looked back. Out of the box it runs without sign-in, so remember to enable auth before exposing it anywhere. Filed an issue and got a reply within two days. Would recommend without hesitation.
Used for Keeping a team knowledge base tidy
- Setup & docs 4/5
- Auth experience 4/5
- Reliability 3/5
- Maintainer responsiveness 4/5
Low blast radius, high value
Read-only doc retrieval — about as safe as an MCP server gets. Treat what it returns as untrusted input like any web content and there is very little to worry about. Uses it every day.
Used for Pulling version-accurate library docs into a coding agent
- Setup & docs 5/5
- Auth experience 4/5
- Reliability 5/5
- Maintainer responsiveness 4/5
Mixed feelings after two weeks
Useful tool, though I would not hand it to a junior unsupervised. Turned on read-only mode on day one, highly recommend doing the same. Out of the box it runs without sign-in, so remember to enable auth before exposing it anywhere.
Used for Finding the right runbook during incidents
- Setup & docs 3/5
- Auth experience 3/5
- Reliability 3/5
- Maintainer responsiveness 3/5
Recommended it to two teams already
Of the Context7 integrations I tried, this one is the most predictable. I run it with auth enabled. Without it I would not let it near anything shared. Easy recommendation.
Used for Drafting docs from existing pages
- Setup & docs 5/5
- Auth experience 4/5
- Reliability 5/5
- Maintainer responsiveness 5/5
Does one thing, does it safely
No credentials needed for the stdio mode, hosted option if you want rate limits lifted. Nothing about it keeps me up at night.
Used for Docs lookup in a shared team agent
- Setup & docs 4/5
- Auth experience 4/5
- Reliability 4/5
- Maintainer responsiveness 4/5
Clean integration, sensible permissions
Hooked Context7 MCP into Claude Code and it worked on the first try. I run it with auth enabled. Without it I would not let it near anything shared. Good choice if you need Context7 in your agent.
Used for Answering questions from our internal wiki
- Setup & docs 5/5
- Auth experience 4/5
- Reliability 5/5
- Maintainer responsiveness 5/5
Good defaults, good docs
I use this almost daily. Turned on read-only mode on day one, highly recommend doing the same. Auth is optional, which is convenient locally. I turned it on before sharing it with the team. Releases come often and the changelog is clear. Happy to run it in production.
Used for Summarising meeting notes
- Setup & docs 5/5
- Auth experience 4/5
- Reliability 5/5
- Maintainer responsiveness 4/5
No complaints after a month
Tried it on a side project first, then rolled it out at work. Anything it pulls in I treat as untrusted, prompt injection through content is a real risk here. Updates land regularly, and nothing broke when I upgraded. Out of the box it runs without sign-in, so remember to enable auth before exposing it anywhere.
Used for Onboarding Q&A for new hires
- Setup & docs 5/5
- Auth experience 3/5
- Reliability 4/5
- Maintainer responsiveness 5/5
Useful, with a few rough edges
It does the job, but it took some tweaking. Watch out for instructions hidden in the data it reads. I review actions before approving them. Auth is optional, which is convenient locally. I turned it on before sharing it with the team.
Used for Finding the right runbook during incidents
- Setup & docs 4/5
- Auth experience 2/5
- Reliability 4/5
- Maintainer responsiveness 3/5
Does the job, docs could be better
I like it, with reservations. Auth is optional, which is convenient locally. I turned it on before sharing it with the team. Read-only mode is the first thing I enable, and it covers most of what I need. Keep permissions tight and it is a good tool.
Used for Answering questions from our internal wiki
- Setup & docs 3/5
- Auth experience 4/5
- Reliability 3/5
- Maintainer responsiveness 3/5
Saves me a context switch every hour
Started with it as an experiment, now it is a fixture. Nice that it supports both stdio and HTTP, I use stdio locally and HTTP for the shared agent. It is in our production agent and I sleep fine.
Used for Onboarding Q&A for new hires
- Setup & docs 4/5
- Auth experience 3/5
- Reliability 4/5
- Maintainer responsiveness 5/5
Our team uses it every day
Installed it on a Friday, it was part of my workflow by Monday. Read-only mode is the first thing I enable, and it covers most of what I need. Out of the box it runs without sign-in, so remember to enable auth before exposing it anywhere. It is in our production agent and I sleep fine.
Used for Keeping a team knowledge base tidy
- Setup & docs 4/5
- Auth experience 4/5
- Reliability 5/5
- Maintainer responsiveness 4/5
Write a review
Ran this server? Tell other teams how it went. You get one review per server. We email you a link to confirm it, then an editor checks it before it goes up. We never show your email.