# Anthropic (/docs/providers/anthropic)

The Anthropic Provider transforms Composio tools into a format compatible with the [Claude Messages API](https://docs.anthropic.com/en/api/messages).

> Looking for the Claude Agent SDK? See the [Claude Agent SDK](/docs/providers/claude-agent-sdk) provider page.

**Install**

**Python:**

```bash
pip install composio composio_anthropic anthropic
```

**TypeScript:**

```bash
npm install @composio/core @composio/anthropic @anthropic-ai/sdk
```

**Configure API Keys**

> Set `COMPOSIO_API_KEY` with your API key from [Settings](https://platform.composio.dev/?next_page=/settings) and `ANTHROPIC_API_KEY` with your [Anthropic API key](https://console.anthropic.com/settings/keys).

```txt title=".env"
COMPOSIO_API_KEY=xxxxxxxxx
ANTHROPIC_API_KEY=xxxxxxxxx
```
**Create session and run**

**Python:**

```python
import json
import anthropic
from composio import Composio
from composio_anthropic import AnthropicProvider

composio = Composio(provider=AnthropicProvider())
client = anthropic.Anthropic()

# Create a session for your user
session = composio.create(user_id="user_123")
tools = session.tools()

messages = [
    {"role": "user", "content": "Send an email to john@example.com with the subject 'Hello' and body 'Hello from Composio!'"}
]

response = client.messages.create(
    model="claude-opus-4-6",
    max_tokens=4096,
    tools=tools,
    messages=messages,
)

# Agentic loop — keep executing tool calls until the model responds with text
while response.stop_reason == "tool_use":
    tool_use_blocks = [block for block in response.content if block.type == "tool_use"]
    results = composio.provider.handle_tool_calls(user_id="user_123", response=response)
    messages.append({"role": "assistant", "content": response.content})
    messages.append({
        "role": "user",
        "content": [
            {"type": "tool_result", "tool_use_id": tool_use_blocks[i].id, "content": json.dumps(result)}
            for i, result in enumerate(results)
        ]
    })
    response = client.messages.create(
        model="claude-opus-4-6",
        max_tokens=4096,
        tools=tools,
        messages=messages,
    )

# Print final response
for block in response.content:
    if block.type == "text":
        print(block.text)
```
**TypeScript:**

```typescript
import Anthropic from '@anthropic-ai/sdk';
import { Composio } from '@composio/core';
import { AnthropicProvider } from '@composio/anthropic';

const composio = new Composio({
    provider: new AnthropicProvider(),
});
const client = new Anthropic();

// Create a session for your user
const session = await composio.create("user_123");
const tools = await session.tools();

const messages: Anthropic.MessageParam[] = [
    {
        role: "user",
        content: "Send an email to john@example.com with the subject 'Hello' and body 'Hello from Composio!'"
    },
];

let response = await client.messages.create({
    model: "claude-opus-4-6",
    max_tokens: 4096,
    tools: tools,
    messages: messages,
});

// Agentic loop — keep executing tool calls until the model responds with text
while (response.stop_reason === "tool_use") {
    const toolResults = await composio.provider.handleToolCalls("user_123", response);
    messages.push({ role: "assistant", content: response.content });
    messages.push(...toolResults);
    response = await client.messages.create({
        model: "claude-opus-4-6",
        max_tokens: 4096,
        tools: tools,
        messages: messages,
    });
}

// Print final response
for (const block of response.content) {
    if (block.type === "text") {
        console.log(block.text);
    }
}
```

---

📚 **More documentation:** [View all docs](https://docs.composio.dev/llms.txt) | [Glossary](https://docs.composio.dev/llms.mdx/docs/glossary) | [Cookbooks](https://docs.composio.dev/llms.mdx/cookbooks) | [API Reference](https://docs.composio.dev/llms.mdx/reference)

---

# Composio SDK — Instructions for AI Code Generators

**Purpose:** Enforce only the **current** and **correct** patterns for integrating [Composio](https://composio.dev/) tools into AI agents.
**Scope:** All AI-generated code using Composio must follow these guardrails.

---

## 1. Correct Composio Integration

Composio supports two integration modes: **Native Tools** (with a provider package) and **MCP** (no provider package needed).

### Native Tools

```python
# ✅ CORRECT — Python (defaults to OpenAI)
from composio import Composio

composio = Composio()
session = composio.create(user_id="user_123")
tools = session.tools()
# Pass tools to your agent/LLM framework
```

```typescript
// ✅ CORRECT — TypeScript (defaults to OpenAI)
import { Composio } from "@composio/core";

const composio = new Composio();
const session = await composio.create("user_123");
const tools = await session.tools();
// Pass tools to your agent/LLM framework
```

For other providers, pass the provider explicitly. Provider packages follow the naming convention: `composio_<provider>` for Python, `@composio/<provider>` for TypeScript.

### MCP

Use `session.mcp.url` and `session.mcp.headers` with any MCP-compatible client (Claude Desktop, Cursor, OpenAI Agents, etc.). No provider package needed.

---

## 2. CRITICAL INSTRUCTIONS FOR AI MODELS

### 2.1 — ALWAYS DO THE FOLLOWING

1. **Use `composio.create(user_id)`** to create a session — this is the entry point for all Composio integrations.
2. **Use `session.tools()`** for native tool integration or **`session.mcp.url`** for MCP integration.
3. **Import** from the correct provider package (`composio_<provider>` for Python, `@composio/<provider>` for TypeScript).
4. **Pass `user_id` to `composio.create()`**, not to individual tool calls.

### 2.2 — NEVER DO THE FOLLOWING

1. **Do not** instruct users to manually create auth configs or connected accounts before running.
2. **Do not** import from `composio_openai` / `@composio/openai` when using OpenAI Agents SDK — use `composio_openai_agents` / `@composio/openai-agents` instead.

### 2.3 — DISCOURAGED (do not use unless user explicitly asks)

Do **not** generate `composio.tools.get()`, `composio.tools.execute()`, or `composio.provider.handle_tool_calls()` unless the user explicitly requests direct tool execution. These are a supported but **not recommended** low-level interface.


---

## Terminology Migration (old → current)

If you encounter these terms in error messages, old documentation, or user prompts, translate them to the current equivalents. **Do not use the old terms in generated code or explanations.**

| Old term (v1/v2) | Current term (v3) | In code |
|---|---|---|
| entity ID | user ID | `user_id` parameter |
| actions | tools | e.g., `GITHUB_CREATE_ISSUE` is a *tool* |
| apps / appType | toolkits | e.g., `github` is a *toolkit* |
| integration / integration ID | auth config / auth config ID | `auth_config_id` parameter |
| connection | connected account | `connected_accounts` namespace |
| ComposioToolSet / OpenAIToolSet | `Composio` class with a provider | `Composio(provider=...)` |
| toolset | provider | e.g., `OpenAIProvider` |

If a user says "entity ID", they mean `user_id`. If they say "integration", they mean "auth config". Always respond using the current terminology.