Compare · Documentation
Context7 vs Docfork MCP Server
Context7 exposes 2 tools and adds about 1,188 tokens to every model turn. Docfork exposes 2 tools and adds about 333. Context7 costs 3.6× as much context. Measured by connecting to each server and counting its tool list, not from the README.
| Context tax | ~1,188 tok/turn | ~333 tok/turn(leaner) |
|---|---|---|
| Tools | 2 | 2 |
| Cost per 1,000 turns (Claude Sonnet 5.5, uncached) | $2.38 | $0.67 |
| Security score | 100/100 | 85/100 |
| Cold start | — | 389 ms |
| Runs | Local or hosted | Local or hosted |
| Needs keys | CONTEXT7_API_KEY | None declared |
| Freshness | Active | Abandoned |
| GitHub stars | 63k | 484 |
| License | MIT | MIT |
| Official MCP registry | Yes | Yes |
Install in Claude Code
Context7
claude mcp add context7 -e CONTEXT7_API_KEY='<context7-api-key>' -- npx -y @upstash/context7-mcp
Tools
By name, from each server's live tool list. The same name can still behave differently.
Only in Context7 · 2
- resolve-library-id
- query-docs
In both · 0
- none
Only in Docfork · 2
- docfork_search_docs
- docfork_read_url
Questions
- Which uses fewer tokens, Context7 or Docfork?
- Docfork: its tool definitions take about 333 tokens per turn against 1,188 for Context7 (3.6× more). Tool definitions are resent on every model turn.
- Do Context7 and Docfork have the same tools?
- No tool names overlap: Context7 has 2 tools and Docfork has 2.
- Are Context7 and Docfork hosted or local?
- Context7: local or hosted. Docfork: local or hosted.
Token counts use the o200k tokenizer on each server's tool definitions as an agent receives them; clients that load tools lazily pay less. Prices are Claude Sonnet 5.5 input at $2/MTok. Want to check one yourself? Run npx mcpskillhub test <package> — how it works.