# Mistral Agents API — Built-In Tools, Memory & Search

> Mistral's Agents API gives any model built-in tools (web search, code interpreter, MCP), persistent memory, and multi-agent handoff via one endpoint.

## Install

Copy the content below into your project:

## Quick Use

1. Get an API key at console.mistral.ai
2. `pip install mistralai` (or `npm install @mistralai/mistralai`)
3. Use the agents.create + conversations.create snippet below

---

## Intro

The Mistral Agents API is a single endpoint that wraps a Mistral model with built-in tools — web search, code interpreter, image generation, document library, and MCP server connectors — plus persistent conversation memory and agent handoff. Best for: production agents where you don't want to glue tools yourself. Works with: Mistral API directly, or via the official Mistral SDK in Python / JavaScript. Setup time: 5 minutes (API key + 30 lines of code).

---

### Create an agent

```python
from mistralai import Mistral

client = Mistral(api_key=os.environ["MISTRAL_API_KEY"])

agent = client.beta.agents.create(
    model="mistral-large-latest",
    name="Research Assistant",
    description="Researches topics and writes summaries",
    instructions="You are a research assistant. Use web search aggressively. Cite sources.",
    tools=[
        {"type": "web_search"},
        {"type": "code_interpreter"},
        {"type": "document_library", "library_id": "lib-xyz"},
    ],
)
```

### Run a conversation

```python
conversation = client.beta.conversations.create(
    agent_id=agent.id,
    inputs="Compare the energy density of LFP vs NMC batteries with citations.",
)

# The agent runs the web_search tool, code_interpreter, then synthesizes
print(conversation.outputs[-1].content)
print(conversation.outputs[-1].tool_calls)  # see what tools were used
```

### Multi-agent handoff

```python
researcher = client.beta.agents.create(
    name="Researcher", model="mistral-large-latest",
    tools=[{"type": "web_search"}],
)
writer = client.beta.agents.create(
    name="Writer", model="mistral-large-latest",
    instructions="Polish drafts into newsletter format.",
)

# Hand off mid-conversation
conv = client.beta.conversations.create(
    agent_id=researcher.id,
    inputs="Find 3 papers on retrieval-augmented generation from arxiv this month",
)
# Then transfer to writer
final = client.beta.conversations.append(
    conversation_id=conv.id,
    agent_id=writer.id,
    inputs="Now turn this into a 200-word LinkedIn post",
)
```

### Connect MCP servers

```python
agent = client.beta.agents.create(
    name="Coder",
    model="codestral-latest",
    tools=[
        {
            "type": "mcp",
            "server_url": "https://your-mcp-server.example.com",
        },
    ],
)
```

Any MCP server (Postgres MCP, GitHub MCP, etc) works. Agents API speaks the protocol natively.

---

### FAQ

**Q: Is the Mistral Agents API free?**
A: Pay-as-you-go via Mistral's API. Pricing varies by model (mistral-large is most expensive, mistral-small cheapest). Free tier on console.mistral.ai for prototyping. See pricing on mistral.ai/pricing.

**Q: How does this compare to OpenAI Assistants API?**
A: Similar architecture (agent + tools + memory) but Mistral adds native MCP support — connect any MCP server as a tool with one config line. OpenAI Assistants only support OpenAI-flavored function calling.

**Q: Can I use Codestral with the Agents API?**
A: Yes. Set `model='codestral-latest'` when creating the agent. Codestral is the recommended model for code-focused agents (lower latency, cheaper, better on code-specific benchmarks).

---

## Source & Thanks

> Built by [Mistral AI](https://github.com/mistralai). Commercial API.
>
> [docs.mistral.ai/agents](https://docs.mistral.ai/capabilities/agents) — Official documentation

---

<!-- ZH -->

## 快速使用

1. 到 console.mistral.ai 拿 API key
2. `pip install mistralai`（或 `npm install @mistralai/mistralai`）
3. 用下面的 agents.create + conversations.create 代码

---

## 简介

Mistral Agents API 是一个端点，把 Mistral 模型套上内置工具 —— 网页搜索、code interpreter、图像生成、文档库、MCP server 连接器 —— 加上持久会话记忆和 agent 切换。适合不想自己粘工具的生产 agent。兼容 Mistral API 直调，或官方 Mistral SDK（Python / JS）。装机时间 5 分钟（API key + 30 行代码）。

---

### 创建 agent

```python
from mistralai import Mistral

client = Mistral(api_key=os.environ["MISTRAL_API_KEY"])

agent = client.beta.agents.create(
    model="mistral-large-latest",
    name="Research Assistant",
    description="Researches topics and writes summaries",
    instructions="You are a research assistant. Use web search aggressively. Cite sources.",
    tools=[
        {"type": "web_search"},
        {"type": "code_interpreter"},
        {"type": "document_library", "library_id": "lib-xyz"},
    ],
)
```

### 跑一段对话

```python
conversation = client.beta.conversations.create(
    agent_id=agent.id,
    inputs="Compare the energy density of LFP vs NMC batteries with citations.",
)

# Agent 自己跑 web_search、code_interpreter，再综合
print(conversation.outputs[-1].content)
print(conversation.outputs[-1].tool_calls)  # 看用了哪些工具
```

### 多 agent 切换

```python
researcher = client.beta.agents.create(
    name="Researcher", model="mistral-large-latest",
    tools=[{"type": "web_search"}],
)
writer = client.beta.agents.create(
    name="Writer", model="mistral-large-latest",
    instructions="Polish drafts into newsletter format.",
)

# 对话中途切换
conv = client.beta.conversations.create(
    agent_id=researcher.id,
    inputs="Find 3 papers on retrieval-augmented generation from arxiv this month",
)
# 然后切给 writer
final = client.beta.conversations.append(
    conversation_id=conv.id,
    agent_id=writer.id,
    inputs="Now turn this into a 200-word LinkedIn post",
)
```

### 接 MCP server

```python
agent = client.beta.agents.create(
    name="Coder",
    model="codestral-latest",
    tools=[
        {
            "type": "mcp",
            "server_url": "https://your-mcp-server.example.com",
        },
    ],
)
```

任何 MCP server（Postgres MCP、GitHub MCP 等）都能接。Agents API 原生支持协议。

---

### FAQ

**Q: Mistral Agents API 免费吗？**
A: 通过 Mistral API 按量付费。价格按模型分（mistral-large 最贵、mistral-small 最便宜）。console.mistral.ai 有免费档用于原型。价格见 mistral.ai/pricing。

**Q: 跟 OpenAI Assistants API 比怎样？**
A: 架构相似（agent + 工具 + 记忆），但 Mistral 加了原生 MCP 支持 —— 一行配置接任何 MCP server 当工具。OpenAI Assistants 只支持 OpenAI 风格的 function calling。

**Q: Agents API 能用 Codestral 吗？**
A: 能。创建 agent 时设 `model='codestral-latest'`。Codestral 是代码 agent 推荐模型（延迟低、更便宜、代码 benchmark 更强）。

---

## 来源与感谢

> Built by [Mistral AI](https://github.com/mistralai). Commercial API.
>
> [docs.mistral.ai/agents](https://docs.mistral.ai/capabilities/agents) — Official documentation


---
Source: https://tokrepo.com/en/workflows/mistral-agents-api-built-in-tools-memory-search
Author: Mistral AI