Context7 MCP connector
The Context7 connector brings current documentation for software libraries into Claude, ChatGPT, Cursor and the Elaichi Agent, so anyone can ask how a library works and get an answer drawn from its latest docs, with every lookup logged.
-
How it connects. Connects over OAuth. The credential goes into a vault nobody reads back.
-
One address. https://api.elaichi.ai/mcp, the same for every user.
-
Their own access. An agent never gets more than the person it acts for.
2 tools
How to connect
How to connect Context7 to Claude, ChatGPT or Cursor
Two steps, about a minute.
In Elaichi
Connect Context7 once
-
Open Connections, choose Add connection, and pick Context7.
-
Optionally set Share with to give a team access, then press Connect.
-
Approve it in Context7. Context7's own window opens. Whoever approves it decides what this connection can reach.
The credential is vaulted. Nobody reads it back, not even the AI.
Add connection
Choose a connector.
In your AI client
Point it at one endpoint
Everyone in the organization uses the same address, and each person only ever reaches what their own account allows.
Context7 MCP connector for Claude
-
1
Open Customize, then Connectors.
-
2
Press Add.
-
3
Name it, paste the MCP server URL, then Continue.
https://api.elaichi.ai/mcp -
4
Sign in and approve.
On Team and Enterprise, an Owner adds it once. Everyone else turns it on for themselves.
Context7 MCP connector for ChatGPT
-
1
Open Plugins, then press the + button.
-
2
Name it and paste the endpoint into Server URL.
https://api.elaichi.ai/mcp -
3
Leave Authentication on OAuth, then tick the risk acknowledgement.
-
4
Press Create, then sign in and approve.
Works on the web today. The plugin directory lives at chatgpt.com/plugins.
Context7 MCP connector for Cursor
-
1
Open
~/.cursor/mcp.json. -
2
Add the endpoint under
mcpServers.https://api.elaichi.ai/mcp -
3
Reload Cursor, then sign in and approve.
~/.cursor/mcp.json
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
Set up per machine, so repeat it on each computer you work from.
Connect Context7 to any MCP client
-
1
Add the endpoint as a remote MCP server.
https://api.elaichi.ai/mcp -
2
Sign in and approve.
{
"mcpServers": {
"elaichi": {
"url": "https://api.elaichi.ai/mcp"
}
}
}
The Elaichi Agent already has these tools, with nothing to set up.
Use cases
What teams do with Context7 through Elaichi
Every one of these runs inside the access the person already has, and lands in the same audit log.
-
Engineering
Check the current way to call a library
Ask how a library handles something today and get an answer from its latest docs instead of a model's memory of an older version. Paste the answer straight into the pull request.
-
Developer Relations
Write a tutorial against the real docs
Pull the current docs for a library before drafting a guide or sample, so the steps match what the library actually does right now.
-
Support
Answer a customer question about a library
When a ticket asks why a library behaves a certain way, look up the relevant docs and reply with the current guidance rather than guessing.
-
Product
Confirm what a library can do before committing
Before promising a feature that depends on a third party library, check its docs to see whether the capability exists and how it is meant to be used.
-
QA
Read the docs behind a failing test
When a test breaks after a library upgrade, look up what changed in that library's docs and point the fix at the right place.
-
Solutions Engineering
Prepare a proof of concept with fewer surprises
Resolve the exact library a prospect uses and read its docs ahead of a demo, so the setup works the first time in front of them.
Try asking
- “Find the current docs for React Router loaders and show an example.”
- “How do I set up authentication in Next.js 15?”
- “Look up the Stripe Node library and explain webhook signing.”
Compare
Elaichi vs Zapier MCP vs Composio for Context7
All three can connect Context7 to an AI assistant, and all three have admin controls. They differ in where access lives and how you pay.
| What to check | Elaichi | Zapier MCP | Composio |
|---|---|---|---|
| Where the AI connects |
One address for the whole organization.
https://api.elaichi.ai/mcp
|
A server per member, created at sign-in. | An MCP endpoint per team, or an SDK. |
| Control over Context7 tools | Allow or restrict single Context7 tools, per role or user. | App and action restrictions on the account. | Role permissions, down to the action. |
| Record of calls | One audit entry per Context7 call. | A History tab of tool calls. | A log of every tool call. |
| Single sign-on | SAML or OIDC, plus SCIM, on Gold. | SAML on Enterprise. | SAML and OIDC on Enterprise. |
| Price | $15 per user per month. | 2 tasks per successful call. | Billed per tool call. |
Sources: Zapier MCP docs, security, usage; Composio docs, gateway, enterprise, pricing. Checked September 2026.
Longer take: Zapier MCP alternative and when you don't need an MCP gateway.
AI tools
Context7 tools for your AI agents
2 tools are ready to call through Elaichi's MCP endpoint the moment you connect Context7, governed by the same roles, restrictions, and audit log as everything else in Elaichi. Context7 builds and runs these tools.
No tools match your search.
See it in Elaichi
What connecting Context7 gets you
6 screens from the product, each doing one job for your Context7 account.
The agent
Ask about any library, get current docs back.
Type a question in plain language and read answers drawn from up-to-date Context7 documentation.
- libraries
- docs
- snippets
- versions
Ask Elaichi to work across your apps.
Find the current docs for React Router loaders and show an example.
How do I set up authentication in Next.js 15?
Look up the Stripe Node library and explain webhook signing.
Also runs in Claude, ChatGPT or Cursor
MCP clients
One endpoint brings Context7 to every client.
Claude, ChatGPT and Cursor read Context7 docs through one governed endpoint, no SDK or shared key.
ElaichiMCP clientsClaude
ChatGPT
Cursor
Copy the endpoint
Tool catalog
2 tools cover Context7 with no code.
Resolve any library and query its docs, with nothing to build or maintain.
- Resolve library ID
- Query docs
ElaichiToolsToolboxes
Every team gets its own Context7 toolbox.
Scope a toolbox to Engineering, Support or Developer Relations and hand each team what it needs.
- Engineering
- Developer Relations
- Support
- Product
ElaichiToolboxesShared connections
Share one Context7 connection, keep the credential private.
One person connects, teams and members work through it, and nobody else sees a secret.
- Platform
- Frontend
- Mobile
- Developer Relations
ElaichiConnectionsAudit log
Every Context7 lookup is on the record.
See who searched which library, when, and what came back, in an append-only log.
- When
- Who
- What happened
- Type
ElaichiAudit logLaunching soon
From answering questions to doing the work
A person no longer has to ask. A trigger starts the work, inside the same permissions and the same audit log as everything else. Automations and live dashboards are launching soon, on the Black plan.
Automations
A schedule starts the work, a person approves.
Fetch Context7 docs for your libraries, group changes, draft a digest, approve, post it back.
Context7 digest
Run 418 · started 2 minutes ago · on behalf of Emily Carter
-
✓
Schedule
Every weekday at 8:00 AM
0.2s -
✓
Fetch libraries
Context7
1.4s -
✓
Group by owner
Transform
0.1s -
✓
Draft the digest
Agent step
Ran with 4 tools, returned a structured summary
6.2s -
Approve the digest
Needs approval
Assigned to Michael Brennan
Approve Deny -
Post the digest
Context7
Queued
Collections and dashboards
Context7 usage numbers arrive without anyone asking.
Four metrics, a 14 day chart, a team breakdown, computed on a schedule with no model.
Context7 health
Refreshed 4 minutes ago · every 15 minutes · from the libraries collection
Libraries
1,284 ↓ 12%
Docs
96 ↓ 8%
Needs attention
3 ↑ 2
Updated this week
412 ↑ 9%
Libraries created
Last 14 days
By team
Share of activity
Platform 34%
Frontend 27%
Mobile 21%
Developer Relations 18%
FAQ
Frequently asked questions
How do I connect Context7 to Claude?
Connect Context7 inside Elaichi first, which takes an OAuth sign-in and nothing else, with no OAuth application to register and no client ID or secret to generate. Then open Claude, go to Customize, then Connectors, then Add, and paste https://api.elaichi.ai/mcp. Claude can then read current library docs from Context7 on your behalf.
Does Context7 work with ChatGPT and Cursor as well as Claude?
Yes. Once Context7 is connected in Elaichi, the same endpoint, https://api.elaichi.ai/mcp, works in Claude, ChatGPT, Cursor, any other MCP client and the Elaichi Agent. You connect Context7 once and every client picks it up.
What can an AI agent actually do with my Context7 data?
With Context7 connected, an agent can find the right library when you name it and read its current documentation to answer your question, whether that is how to set up authentication in a framework or what a method expects. Short, specific asks such as naming the library and the feature work better than long paragraphs. The connector reads docs; it does not change anything in Context7.
Does connecting Context7 give the AI everything?
No. An agent working through Context7 only has the access of the person who signed in, and Elaichi can narrow that access further with roles and restrictions. Elaichi never widens what a person could already do in Context7.
Can I stop an agent from deleting or changing things in Context7?
The Context7 connector only reads library docs, so there is nothing for an agent to delete or change. Even so, Elaichi applies restrictions per action, and a restricted action is never shown to the AI client at all, so no prompt can reach it.
What happens to a Context7 connection when someone leaves?
Offboarding a person in Elaichi ends their access to Context7 through every client at once. A Context7 connection they shared keeps working for everyone else on the team. Disconnecting Context7 once in Elaichi removes it from Claude, ChatGPT, Cursor and every other client together.
Does the Context7 MCP connector work with Gemini, Codex, Claude Code or other MCP clients?
Yes. Context7 is reached over the same MCP endpoint every client uses, so anything that speaks MCP can call it — Gemini, Codex, Claude Code, Windsurf, Cline, Zed and OpenCode among them — alongside Claude, ChatGPT, Cursor, and the Elaichi Agent. The tools on offer and the access behind them are identical whichever client asks. Only the setup screen differs.
Is Elaichi an alternative to Zapier MCP for Context7?
Yes. Both let Claude, ChatGPT or Cursor use Context7. Zapier MCP fits a team that already automates in Zapier, since each person signs in and acts as themselves in that account. Elaichi fits when IT wants one address for the whole company, per-tool rules by role, and a record of every Context7 call.
How is Elaichi different from Composio for Context7?
Composio gives AI agents tools and sign-in handling across 1,000+ apps, for developers building agents or people using an assistant, billed per tool call. Elaichi gives a company's own people governed access to Context7: one address, restrictions per role or user, and $15 per user per month. Both have role permissions and a log of every call.
Put Context7 in front of your team
14 days on Gold, no credit card. Connect it once and pick what each team can call.
- Works with
-
and any other MCP client, or the Elaichi Agent.
- When the trial ends
- Nothing is deleted. Connections, roles and the audit log stay where they are, so subscribing picks up exactly where you left off.