Context7 MCP for AI. Never hallucinate an API signature again.

Q: Can my agent find the latest documentation for a specific Tailwind CSS version?

Yes. First, use the 'resolvelibrary' tool with 'tailwindcss'. It will return the deterministic ID and version (e.g., 'tailwindcss/3.4.1'). Then, use 'querydocs' to pull the exact Markdown blocks for your specific topic.

Q: Does Context7 provide code examples for the libraries I search for?

Absolutely. When you query documentation via the 'querydocs' tool, the agent retrieves not only textual descriptions but also version-specific code examples found in the original library documentation to ensure implementation accuracy.

Q: What is the required two-step process when I need documentation for a new library?

First, use resolvelibrary to get the precise ID and version of your target framework. Then, feed that deterministic path into querydocs. This ensures your agent gets context tied directly to the exact API version you need.

Claude

ChatGPT

Cursor

Gemini

Windsurf

VS Code

JetBrains

Vercel

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

Connect to your AI in seconds.

Context7 pulls up-to-date, version-specific documentation and code examples for any library or framework directly into your agent's conversation flow. It stops AI agents from hallucinating outdated API calls by grounding them in current technical truths.

This MCP finds the exact paths you need before pulling deep docs.

What your AI can do

Resolve library

It finds the correct, deep identifiers and the latest stable version number matching any framework or library search query.

Query docs

This tool fetches specific technical documentation and ready-to-use code examples for a defined library topic.

Resolve Library Paths

It takes a common framework name (like 'react') and finds the precise, technical path and version number needed for deep documentation retrieval.

Query Documentation

You ask about a specific feature or API call, and it pulls back raw, up-to-date documentation chunks and code examples related to that topic.

Ground Agent Context

It prevents your AI client from hallucinating outdated syntax by feeding it real, verified technical truths before generating a response.

Extract Code Examples

The system pulls ready-to-use code snippets for components or functions directly into the conversation flow.

Ask an AI about this

Included with Plan

Waiting for input…

AI Agent

Context7: 2 Tools

These two tools allow you to find the precise identifiers for any library and then retrieve its most current technical documentation and working code snippets.

Make your AI actually useful.

Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.

Start using Context7 on Vinkius

Resolve Library

It finds the correct, deep identifiers and the latest stable version number matching any framework or library search query.

Query Docs

This tool fetches specific technical documentation and ready-to-use code examples...

Security and governance baked right in.

Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.

Claude AI

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

Start a conversation

Open a new chat. The Context7 integration is available immediately — no restart needed.

Antigravity

Configure Agent Environment

Open your Antigravity agent's workspace configuration or mcp-servers.json file.

Bind the Endpoint

Add the Vinkius endpoint URL to your agent's MCP connections list:

"mcp_servers": {
  "context7": {
    "serverUrl": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
  }
}

Provide your secure token in place of [YOUR_TOKEN_HERE] to ensure your agent requests are authenticated.

Execute

Start your Antigravity session. The agent will autonomously discover and utilize the Context7 tools with full Vinkius guardrails applied.

VS Code Copilot

⚡

One-Click Install (Recommended)

In your Vinkius Dashboard, simply click the Add to VS Code button for this server. We'll automatically configure your local workspace.

Or configure manually

Open MCP Settings

Open VS Code, press Ctrl/Cmd + Shift + P, and search for GitHub Copilot: MCP Servers.

Add Server Config

Add the Vinkius endpoint configuration to your mcp-servers.json file:

"context7": {
  "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
}

Ensure you replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.

LangChain

Install Dependencies

Install the LangChain MCP adapters for your environment:

pip install langchain-mcp-adapters

Connect the Server

Use the SSEClient in LangChain to connect to the Vinkius managed endpoint:

from langchain_mcp_adapters.client import SSEClient

# Connect to Vinkius
client = SSEClient(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
tools = client.get_tools()

CrewAI

Define the Tool

Load the Vinkius MCP tools into your CrewAI agents:

from crewai import Agent
from mcp_crewai import MCPTool

# Connect securely to Vinkius
vinkius_tools = MCPTool(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

# Assign to Agent
researcher = Agent(
    role='Data Researcher',
    tools=vinkius_tools.get_all()
)

Execute Task

Run your CrewAI process. The agent will autonomously route tasks to the Vinkius managed server.

Choose How to Get Started

Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.

Build Your Own

Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.

Import from OpenAPI, Swagger, or YAML specs
Create Agent Skills with progressive disclosure
Deploy to edge with MCPFusion framework
Built in DLP, auth, and compliance on every call
Real time usage dashboard and cost metering
Publish to catalog or keep private

Start building

Make Your AI Do More

Start with Context7, then connect any of our 5,100+ other servers whenever your AI needs more. One click, no limits.

Use this MCP plus 5,100+ others, all in one place
Add new capabilities to your AI anytime you want
Every connection is secured and compliant automatically
Track usage and costs across all your servers
Works with Claude, ChatGPT, Cursor, and more
New servers added to the catalog every week

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Context7. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

VINKIUS INFRASTRUCTURE

Cloud Hosted

Managed infra

V8 Isolated

Sandboxed per request

Zero-Trust Proxy

No stored credentials

DLP Enforced

Policy on every call

GDPR Compliant

EU data residency

Token Compression

~60% cost reduction

Your data is protected. See how we built it.

Works with Claude, ChatGPT, Cursor, and more

The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.

This connection provides 2 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.

The Pain of Documentation Drift

Right now, figuring out the right way to use an API is a chore. You start by googling, then you click through three different vendor sites, and eventually, you find a tutorial—but that tutorial uses syntax from two years ago. Then you copy-paste it into your IDE, only for the compiler to throw an error because the dependency version changed last week.

With this MCP, that cycle ends. You tell your agent what you need, and it handles all the messy context switching behind the scenes. It doesn't just *tell* you; it pulls validated code examples and raw documentation chunks for the exact library version you're working on.

Context7: Reliable API Context

You no longer have to manually resolve vague framework names. The `resolve_library` tool handles that messy work, turning a search query like 'react' into deterministic paths like `/facebook/react/18.2.0`. Then, the system uses `query_docs` to pull the precise technical details for those specific path and version numbers.

What’s different now is trust. You get code that works because it’s anchored directly to the source of truth—the live documentation—and you don't have to spend time verifying if any snippet is even current.

Support 24/7 support@vinkius.com ↗

Security Vinkius Trust Center ↗

SLA Service Level Agreement ↗

Report Listing Send Report ↗

What your AI can actually do with this

You know how often an LLM spits out a piece of code using an old API signature? Or gives documentation for React v17 when your project is on v18? It's a massive time sink.

Context7 fixes that. You connect it to your agent and give it access to live, version-specific knowledge bases. Instead of relying on generalized training data—which gets stale fast—your agent queries the actual documentation for whatever library or framework you're dealing with. This isn't just another search layer; it's a developer-focused RAG engine that resolves fuzzy names into precise paths first, and then pulls raw Markdown chunks and working code examples right where your agent needs them.

It means when your AI client asks how to implement something, you get accurate snippets for the exact version of the library you need. You can connect this specialized context layer through Vinkius, giving your entire development team access to a reliable source of truth without leaving your IDE or slowing down your workflow.

Built · Hosted · Managed by Vinkius Context7 MCP - Docs and Code Examples

Server ID 019d757b-5f19-7054-8c59-dd260d3c4d66

Vinkius Inspector

Compliance Grade A+

Score 100/100

Report View Report ↗

Here's how it actually works

The bottom line is, your agent always knows the specific library version it's talking about before answering anything.

You subscribe to this MCP and enter your Context7 API Key in Vinkius.

Your AI client sends a request, asking for documentation on a specific framework or library.

The agent first uses resolve_library to find the exact ID and version (e.g., 'vercel/next.js/14.1.0'), then passes that result to query_docs to fetch the required technical data.

What Changes When You Connect

Stops outdated code generation. By using the resolve_library tool first, your agent pins down the exact library version needed before it looks up docs, guaranteeing accuracy.

Eliminates manual searching for boilerplate. The MCP pulls valid, ready-to-use code examples and full API documentation straight into the chat, saving you copy-pasting time.

Deep context retrieval. It goes beyond surface-level answers by retrieving raw Markdown chunks from official sources, giving your agent verifiable technical depth.

Handles ambiguity instantly. If a developer mentions 'react' but needs v18, resolve_library handles the fuzzy matching and gives you deterministic paths needed for deep fetching.

Works with any client. Whether it’s Cursor or VS Code Copilot, connecting this MCP via Vinkius makes high-fidelity documentation accessible across all your developer tools.

See it in action

01 01

Troubleshooting an API call

A dev hits a wall on a specific data fetching method. They ask their agent, and the agent first runs resolve_library to confirm the framework's version number. Then it uses query_docs to pull up the official documentation segment detailing that exact method, letting them see the correct syntax instantly.

02 02

Starting a new component

A rapid imprototyper needs a boilerplate for a complex UI element in Tailwind CSS. Instead of searching docs manually, they ask their agent to pull examples. The system uses Context7's tools to extract valid code components directly into the workspace.

03 03

Comparing framework versions

A senior dev needs to know how a utility function changed between Next.js 13 and 14. They prompt the agent, which uses resolve_library repeatedly to fetch documentation for two different versions, allowing them to compare API changes side-by-side.

04 04

Building an internal tool

An AI engineer is writing a Python script that interacts with external APIs. By integrating this MCP, their agent can confirm the latest required library signatures and pull verified code snippets for type safety before committing the build.

The honest tradeoffs

Asking vague questions

Anti-pattern

Just asking the agent: 'How do I use Next.js?' This gives a generic answer and might be outdated.

The Fix

First, run resolve_library to get the current version ID for Next.js, then feed that exact result into query_docs along with your specific question.

Ignoring dependencies

Anti-pattern

Assuming the agent knows which library version you're running based only on the project name.

The Fix

Always let the MCP handle context. Use both resolve_library and query_docs. This ensures every piece of code is tied to a specific, verified version.

Searching general web results

Anti-pattern

Copying documentation snippets from Stack Overflow or generic tutorials that might be old.

The Fix

Rely only on this MCP. It pulls context directly from the authoritative source: the live, official technical documentation.

When It Fits, When It Doesn't

Use this if your job requires high fidelity to specific versions and APIs. If you're building complex systems or working with rapidly evolving frameworks (like React or Next.js), this MCP is non-negotiable. It solves the 'context staleness' problem by forcing the agent to prove its knowledge against current, official docs using query_docs after first confirming the correct version via resolve_library. Don't use it if you just need general conceptual guidance or simple facts that don't involve code or library structure. For those basic needs, a standard search tool works fine.

Questions you might have

Can my agent find the latest documentation for a specific Tailwind CSS version? +

Yes. First, use the 'resolve_library' tool with 'tailwindcss'. It will return the deterministic ID and version (e.g., 'tailwindcss/3.4.1'). Then, use 'query_docs' to pull the exact Markdown blocks for your specific topic.

Does Context7 provide code examples for the libraries I search for? +

Absolutely. When you query documentation via the 'query_docs' tool, the agent retrieves not only textual descriptions but also version-specific code examples found in the original library documentation to ensure implementation accuracy.

How does this help prevent AI hallucinations in coding tasks? +

Standard LLMs have a training data cutoff. Context7 pulls live, version-specific documentation chunks that act as ground-truth context. By grounding your agent in this real-time data, it avoids hallucinating outdated or non-existent API methods.

What authentication details are required when connecting via Context7? +

You need your unique Context7 API Key. This key grants your agent access to the documentation corpus, so always store it securely in your client's settings following standard credential handling practices.

If I run the `resolve_library` tool, how does it handle unknown or misspelled framework names? +

The tool will return an explicit error message indicating that no matching library ID was found. This prevents your agent from wasting time on queries for non-existent or incorrect package paths.

When using the `query_docs` tool, are there limits on the amount of documentation I can retrieve in one query? +

The depth depends entirely on the specific topic you ask about. For extremely large sections of technical docs, it's best practice to break your request into smaller, focused queries for optimal context transfer.

Does this MCP only work for JavaScript frameworks like React and Next.js? +

No. Context7 supports documentation retrieval across a wide range of libraries and frameworks in various domains, provided the technical information is structured and accessible online.

What is the required two-step process when I need documentation for a new library? +

First, use resolve_library to get the precise ID and version of your target framework. Then, feed that deterministic path into query_docs. This ensures your agent gets context tied directly to the exact API version you need.

Connect to your AI in seconds.

Resolve library

Query docs

Context7: 2 Tools

Make your AI actually useful.

Resolve Library

Query Docs

Security and governance baked right in.

Claude AI

Open Claude Settings

Add Custom Connector

Start a conversation

Claude Code

Open your terminal

Add the MCP Server

Start coding

Cursor

One-Click Install (Recommended)

Open Cursor Settings

Add New Server

Use in Composer

Antigravity

Configure Agent Environment

Bind the Endpoint

Execute

VS Code Copilot

One-Click Install (Recommended)

Open MCP Settings

Add Server Config

Windsurf

One-Click Install (Recommended)

Open Windsurf Settings

Add Server Endpoint

LangChain

Install Dependencies

Connect the Server

CrewAI

Define the Tool

Execute Task

Choose How to Get Started

Build Your Own

Make Your AI Do More

Works with Claude, ChatGPT, Cursor, and more

The Pain of Documentation Drift

Context7: Reliable API Context

What your AI can actually do with this

Here's how it actually works

Who is this actually for?

What Changes When You Connect

See it in action

Troubleshooting an API call

Starting a new component

Comparing framework versions

Building an internal tool

The honest tradeoffs

Asking vague questions

Ignoring dependencies

Searching general web results

When It Fits, When It Doesn't

Questions you might have