Agent skills & MCP Context7
Is Context7 safe?
Short answer: Caution. StackGrade's weekly scan of upstash/context7 gives it a Caution label for 2 critical-severity known vulnerabilities in runtime dependencies (OSV). It does list 35 high-severity advisories in runtime dependencies, which don't change the label. Critical advisories are counted once per package; a known issue in a locked package version does not prove Context7 is exploitable in your setup. Automated scan of commit 7836c58 on 2 Nov 2026, not a manual audit.
Updated : the last week its score, rank or safety result changed.
Serves up-to-date library documentation to LLMs and AI code editors via MCP.
- 64,060 stars
- pushed 1 Nov
- MIT
- TypeScript
#19of 52 overall#2in Agent skills & MCP▲ 5 vs Week 44
- Maintenance 30%67
- Adoption 30%39
- Docs 20%69
- Community 20%–
Score over the last 4 weeks: 58, 52, 52, 57.
2 critical-severity known vulnerabilities in runtime dependencies (OSV).
How this score works
Each part is a percentile among all 52 tracked tools, so 50 is average for this list. Community is not measured yet; the score uses the other 80%.
- Maintenance: Last push 1 Nov 2026. Last 10 GitHub releases within 8 days (about 35 per 30 days), latest release 23 Oct 2026. Median 13.3 h to close an issue (19 closed issues).
- Adoption: 64,060 stars (70%), 3,198 forks (30%).
- Docs: README 12,843 characters, 17 headings, 7 code blocks, install section: yes.
#2 of 9 in Agent skills & MCP
Ranked by score. The yellow row is this tool.
- 1Superpowers#13 overall62No dependencies scanned
- 2Context7#19 overall57Caution
- 3Agent Skills#25 overall53No issues found
- 4MCP reference servers#29 overall48No issues found
- 5awesome-mcp-servers#30 overall47No dependencies scanned
- 6Playwright MCP#32 overall45No issues found
Show the other 3
- 7wshobson/agents#38 overall42No issues found
- 8GitHub MCP Server#40 overall41No issues found
- 9skill-recorder#52 overall22No issues found
Safety scan, 2 Nov 2026
Automated scan of commit 7836c58, 308 files. Not a manual audit.
Caution
- 2Critical dependency advisories35 high, 53 medium, 8 low. OSV, runtime dependencies only.
- 0Install hooksNo npm install scripts found.
- 0Remote-code patternsFor example eval(fetch(…)).
- 34Agent files checked0 phrases flagged for review.
- 0curl | sh installersIn docs or program code. Information only.
Why this label?
Why this label:
- 2 critical-severity known vulnerabilities in runtime dependencies (OSV)
Known vulnerabilities in runtime dependencies (OSV): 2 critical, 35 high, 53 medium, 8 low
proxy-addr@2.0.7 (GHSA-jqcg-44mw-7w3h) in pnpm-lock.yamlshell-quote@1.10.0 (GHSA-pqg4-j6r4-53mv) in pnpm-lock.yaml
Also found (informational, does not change the label):
- 35 high-severity known vulnerabilities in runtime dependencies (OSV)
Notes:
- Telemetry/analytics references in code: telemetry
Automated scan of commit 7836c58 on 2 Nov 2026, not a manual audit. 308 files checked. What we check
Repo activity
From the GitHub API, fetched 2 Nov 2026.
- 10+Releases, 90 daysLatest @upstash/context7-sdk@0…, 23 Oct
- 13hMedian issue closeOver 19 closed issues
- 64.1kStars+370 since 26 Oct
- 3.2kForks50 open issues
- 2025Repo created26 Mar 2025
10 releases in the last 30 days (GitHub releases feed, last 10 entries):
Questions about Context7
Answers use this week's StackGrade data.
Is Context7 safe to use?
Caution. StackGrade's weekly scan of upstash/context7 gives it a Caution label for 2 critical-severity known vulnerabilities in runtime dependencies (OSV). It does list 35 high-severity advisories in runtime dependencies, which don't change the label. Critical advisories are counted once per package; a known issue in a locked package version does not prove Context7 is exploitable in your setup. Automated scan of commit 7836c58 on 2 Nov 2026, not a manual audit.
How does StackGrade score Context7?
Context7 scores 57 out of 100 in Week 45: #19 of 52 tracked tools overall and #2 in Agent skills & MCP. The score combines maintenance (67), adoption (39) and docs (69) as percentiles among all 52 tracked tools; community (20% weight) is not measured yet, so the score uses the other 80%. It is not a hands-on test and it is separate from the safety label.
What are the alternatives to Context7?
The highest-scored other tools in Agent skills & MCP this week: Superpowers (62, No dependencies scanned), Agent Skills (53, No issues found), MCP reference servers (48, No issues found), awesome-mcp-servers (47, No dependencies scanned). StackGrade has not tested them hands-on.
What licence does Context7 use?
The licence listed for upstash/context7 is MIT. Read the licence text before commercial use.
Compare and use it
Side by side
Used in 1 AI use case
All facts and sources
- Type
- MCP server
- License
- MIT
- Language
- TypeScript
- Created
- 26 Mar 2025
- Owner
- upstash (Organization)
- Forks
- 3,198
- Homepage
- context7.com
GitHub description: “Context7 Platform -- Up-to-date docs for AI agents”
Sources: github.com/upstash/context7, api.github.com/repos/upstash/context7, raw.githubusercontent.com/upstash/context7/master/README.md. Fetched 2 Nov 2026.
Know when Context7 changes label
One email a week: the new top 10, the biggest score changes and every safety label that changed.
Free. Double opt-in: you confirm by email first, unsubscribe in one click.