Context7 for AI agents
Context7 pulls current, version-specific documentation and code examples straight from the source, so an agent writes code against the library's real API. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Context7.
Look up a library's docs
Resolve a library's identifier and pull its current documentation before writing code against it.
Query docs for a specific version
Query documentation for a specific library version to avoid using an outdated API.
Find a code example
Query docs for a working code example instead of guessing at a function's usage.
2 Context7 actions, graded by risk.
Every Context7 action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
2Look things up. Allowed by default.
- context7.query_docsQuery-docs
- context7.resolve_library_idResolve-library-id
write
0Create and change things. Allow, or ask the user first.
- No write actions.
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Context7 in three steps.
- 01Your users connect Context7They add their Context7 api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “updates” can wait for the user to approve.
- 03Any agent can actYour agent calls Context7 through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('context7', { read: 'allow', write: 'ask', destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Context7 connects.
Users add their Context7 api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Context7 connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Context7 from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Context7 and Arc0, answered.
Can I use Context7 with Claude, ChatGPT or Cursor?
Yes. Connect Context7 to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Context7 actions you allow.
How do users connect Context7?
Users add their Context7 api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Context7 actions can my agent take?
2 in total: 2 read, 0 write and 0 destructive. Your policies decide which of them each agent may call.
Can I make my agent read-only in Context7?
Yes. Allow read actions and deny writes in the Context7 policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Context7 too?
Yes. The same Context7 connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Context7 into your agent.
Your users connect Context7 once, under your brand. Your agent gets 2 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan