# Valyu

```json
{
  "name": "Valyu",
  "slug": "valyu",
  "url": "https://composio.dev/toolkits/valyu",
  "markdown_url": "https://composio.dev/toolkits/valyu.md",
  "logo_url": "https://logos.composio.dev/api/valyu",
  "categories": [
    "ai & machine learning"
  ],
  "is_composio_managed": false,
  "updated_at": "2026-11-18T05:46:00.070Z"
}
```

![Valyu logo](https://logos.composio.dev/api/valyu)

## Description

Securely connect your AI agents and chatbots (Claude, ChatGPT, Cursor, etc) with Valyu MCP or direct API to search specialist sources, run multi-step research, gather citations, and structure findings through natural language.

## Summary

Valyu is a research API for searching specialist, proprietary, and web sources.
It returns multi-step research with cited, structured outputs.

## Categories

- ai & machine learning

## Toolkit Details

- Tools: 32

## Images

- Logo: https://logos.composio.dev/api/valyu

## Authentication

- **Api Key**
  - Type: `api_key`
  - Description: Api Key authentication for Valyu.
  - Setup:
    - Configure Api Key credentials for Valyu.
    - Use the credentials when creating an auth config in Composio.

## Suggested Prompts

- Compare recent battery recycling methods with citations
- Research clinical trial results from specialist sources
- Find cited market data for renewable energy

## Supported Tools

| Tool slug | Name | Description |
|---|---|---|
| `VALYU_ADD_DEEP_RESEARCH_BATCH_TASKS` | Add DeepResearch Batch Tasks | Add 1-100 paid research tasks to an open or processing DeepResearch batch. Each task costs the batch mode's base price: at least 25 credits per task (fast), or 100 standard, 500 heavy, and 2,500 max, before add-ons. Valyu reserves the full set's mode prices in one all-or-nothing step; a 402 adds no tasks, and a 503 means billing could not be checked and nothing was added. |
| `VALYU_ANSWER` | Answer | Generate a cited answer from live search and return the complete answer, sources, warnings, token usage, and authoritative billed cost. |
| `VALYU_CANCEL_DEEP_RESEARCH_BATCH` | Cancel DeepResearch Batch | WARNING: irreversibly cancel all queued and running tasks in an open or processing DeepResearch batch. Completed tasks are not undone. Cancelling running tasks can incur their full mode price; queued-task cancellation is free. |
| `VALYU_CANCEL_DEEP_RESEARCH_TASK` | Cancel DeepResearch Task | WARNING: irreversibly cancel a DeepResearch task in queued, running, awaiting_input, or paused status. Cancelling a running or awaiting_input task charges its full mode price; cancelling a queued or paused task is free. |
| `VALYU_CREATE_DEEP_RESEARCH_BATCH` | Create DeepResearch Batch | Create an empty DeepResearch batch with shared mode, output, search, webhook, and metadata configuration. WARNING: Valyu provides no batch-delete endpoint, so even an empty batch persists. Adding tasks later incurs the selected DeepResearch mode cost for each task. |
| `VALYU_CREATE_DEEP_RESEARCH_TASK` | Create DeepResearch Task | Start a paid asynchronous DeepResearch task. Choose exactly one side: freeform mode, supplying query (preferred) or the deprecated input field; or workflow mode, supplying workflow_id and the required workflow_params. Do not mix freeform and workflow fields. When share_with is provided, share_notify defaults to true and sends notification email to those recipients; set it false to create sharing access without emailing them. Base prices before tool add-ons are 8 credits (instant), 25 (fast), 100 (standard), 500 (heavy), and 2,500 (max). Creation holds the mode price; insufficient balance returns 402 without creating a task. |
| `VALYU_CREATE_WORKFLOW` | Create Workflow | Create a private organization workflow and its first immutable version. Use a new slug for each attempt. If Valyu returns 5xx, this action performs one lookup by slug because the workflow may have persisted; it never retries or deletes automatically. |
| `VALYU_DELETE_DEEP_RESEARCH_TASK` | Delete DeepResearch Task | Permanently delete a completed, failed, or cancelled DeepResearch task and all associated outputs, sources, PDFs, and images. Running or queued tasks must be cancelled first. |
| `VALYU_DELETE_WORKFLOW` | Delete Workflow | Soft-delete an organization-owned workflow. Valyu-curated workflows cannot be deleted. |
| `VALYU_EXTRACT_CONTENTS` | Extract Contents | Extract content from up to 10 URLs synchronously or queue up to 50 URLs asynchronously. Returns every per-URL success, failure, or not-found outcome and the authoritative charge; async responses return a job_id for Get Contents Job. |
| `VALYU_GET_CONTENTS_JOB` | Get Contents Job | Get an asynchronous content extraction job's status, per-URL results, failures, and final charge. HTTP 200 and top-level success=true only mean the status request succeeded; inspect status and each result to determine extraction success. |
| `VALYU_GET_DEEP_RESEARCH_BATCH_STATUS` | Get DeepResearch Batch Status | Get a DeepResearch batch's lifecycle status, task counts, shared configuration, timestamps, and aggregate cost. |
| `VALYU_GET_DEEP_RESEARCH_SHARING` | Get DeepResearch Sharing | List the people and company domains a DeepResearch report is shared with, including its share link, public setting, notification timestamps, and view timestamps. Sharing with named recipients is separate from public access, and only the API key that created the task can read it. |
| `VALYU_GET_DEEP_RESEARCH_STATUS` | Get DeepResearch Status | Get a DeepResearch task's status, progress, checkpoint, report, sources, generated files, warnings, and cost. |
| `VALYU_GET_WORKFLOW` | Get Workflow | Get a workflow's current version, including its template, tools, output formats, deliverables, and variables. Use Get Workflow Version to read a specific historical version. |
| `VALYU_GET_WORKFLOW_VERSION` | Get Workflow Version | Get a workflow resolved at one specific immutable version, including its template, tools, output formats, deliverables, and variables. |
| `VALYU_LIST_DATASOURCE_CATEGORIES` | List Datasource Categories | List current datasource category IDs, names, descriptions, and dataset counts. |
| `VALYU_LIST_DATASOURCES` | List Datasources | List searchable datasources and their IDs, capabilities, pricing, plan requirements, schemas, and example queries, optionally by category. |
| `VALYU_LIST_DEEP_RESEARCH_BATCHES` | List DeepResearch Batches | List DeepResearch batches with lifecycle status, task counts, and aggregate cost. |
| `VALYU_LIST_DEEP_RESEARCH_BATCH_TASKS` | List DeepResearch Batch Tasks | Return one cursor-controlled page of a DeepResearch batch's tasks, optionally filtered by status and expanded with outputs, sources, files, errors, and costs. |
| `VALYU_LIST_DEEP_RESEARCH_TASKS` | List DeepResearch Tasks | List up to 100 DeepResearch task summaries for the connected API key. |
| `VALYU_LIST_WORKFLOWS` | List Workflows | List visible curated and organization workflows with discovery metadata and optional current-version expansion. Returns at most the requested 1-100 rows; a returned next_cursor is informational because the API accepts no continuation input. |
| `VALYU_LIST_WORKFLOW_VERSIONS` | List Workflow Versions | List a workflow's immutable version history newest first, including current-version and changelog metadata. |
| `VALYU_PREVIEW_WORKFLOW` | Preview Workflow | Resolve workflow variables and return the exact DeepResearch configuration and estimated credits without launching or charging for a research task. |
| `VALYU_PUBLISH_WORKFLOW_VERSION` | Publish Workflow Version | Publish a new immutable version of an organization-owned workflow. Supply the complete prompt, strategy, and report format, not a partial patch, plus a non-empty changelog describing what changed. Optionally make the published version current. Published versions cannot be edited in place. |
| `VALYU_RESPOND_TO_DEEP_RESEARCH_CHECKPOINT` | Respond to DeepResearch Checkpoint | Answer an active planning, plan-review, source-review, or outline-review checkpoint so a DeepResearch task in awaiting_input or paused state can continue. Resuming a paused task requires enough balance and can continue paid execution that incurs the task's mode price and add-on charges. |
| `VALYU_SEARCH` | Search | Search web, news, academic, financial, and specialist sources, returning ranked content, source coverage, warnings, and the amount charged. |
| `VALYU_SEARCH_DATASOURCES` | Search Datasources | Find datasources accessible to the connected key from a natural-language need, returning ranked datasource IDs and full metadata. |
| `VALYU_SET_DEEP_RESEARCH_PUBLIC_ACCESS` | Set DeepResearch Public Access | Make a DeepResearch task public or private. Public results are accessible without authentication, so review sensitive content before enabling access. |
| `VALYU_UPDATE_DEEP_RESEARCH_SHARING` | Update DeepResearch Sharing | Atomically add or remove people and company domains that can open a private DeepResearch report. The report remains private and sharing does not change its public setting. Omitted notify defaults to true and emails every individual in add; set notify=false to avoid notification emails. Domains are never emailed. A report can be shared with at most 100 people and domains, and only the API key that created the task can change sharing. |
| `VALYU_UPDATE_DEEP_RESEARCH_TASK` | Update DeepResearch Task | Add a follow-up instruction to a running DeepResearch task before its writing phase begins. |
| `VALYU_UPDATE_WORKFLOW` | Update Workflow | Update metadata on an organization-owned workflow. Provide at least one of title, subtitle, description, vertical, tags, or icon. Use Publish Workflow Version to publish an immutable version. Valyu-curated workflows are read-only. |

## Supported Triggers

None listed.

## Installation and MCP Setup

### Path 1: SDK Installation

#### Path 1, Step 1: Install Composio

Install the Composio SDK, the OpenAI provider, and the OpenAI SDK
```python
pip install composio composio_openai openai
```

```typescript
npm install @composio/core @composio/openai openai
```

#### Path 1, Step 2: Create a Composio session

Initialize Composio with the OpenAI Responses provider and create a session scoped to Valyu
```python
import json
from openai import OpenAI
from composio import Composio
from composio_openai import OpenAIResponsesProvider

composio = Composio(provider=OpenAIResponsesProvider())
client = OpenAI()

session = composio.create(user_id="your-user-id", toolkits=["valyu"])
tools = session.tools()
```

```typescript
import OpenAI from "openai";
import { Composio } from "@composio/core";
import { OpenAIResponsesProvider } from "@composio/openai";

const composio = new Composio({ provider: new OpenAIResponsesProvider() });
const client = new OpenAI();

const session = await composio.create("your-user-id", { toolkits: ["valyu"] });
const tools = await session.tools();
```

#### Path 1, Step 3: Run Valyu tools with your agent

Send a request, execute the Valyu tool calls through the session, and print the final answer
```python
response = client.responses.create(
    model="gpt-5.6-sol",
    tools=tools,
    input=[{"role": "user", "content": "Research the latest battery recycling methods using specialist and web sources, and return a cited comparison."}],
)

while True:
    tool_calls = [o for o in response.output if o.type == "function_call"]
    if not tool_calls:
        break
    results = composio.provider.handle_tool_calls(response=response, session=session)
    response = client.responses.create(
        model="gpt-5.6-sol",
        tools=tools,
        previous_response_id=response.id,
        input=[
            {"type": "function_call_output", "call_id": call.call_id, "output": json.dumps(results[i])}
            for i, call in enumerate(tool_calls)
        ],
    )

print(response.output_text)
```

```typescript
let response = await client.responses.create({
  model: "gpt-5.6-sol",
  tools,
  input: [{ role: "user", content: "Research the latest battery recycling methods using specialist and web sources, and return a cited comparison." }],
});

while (response.output.some((o) => o.type === "function_call")) {
  const outputs = await composio.provider.handleToolCalls(session, response.output);
  response = await client.responses.create({
    model: "gpt-5.6-sol",
    tools,
    previous_response_id: response.id,
    input: outputs,
  });
}

console.log(response.output_text);
```

### Path 2: MCP Server Setup

#### Path 2, Step 1: Install Composio

Install the Composio SDK and your agent framework
```python
pip install composio claude-agent-sdk
```

```typescript
npm install @composio/core ai @ai-sdk/mcp @ai-sdk/openai
```

#### Path 2, Step 2: Create a session with MCP enabled

Create a session scoped to Valyu and read its MCP URL and headers
```python
from composio import Composio

composio = Composio()
session = composio.create(user_id="your-user-id", toolkits=["valyu"], mcp=True)
```

```typescript
import { Composio } from "@composio/core";

const composio = new Composio();
const { mcp } = await composio.create("your-user-id", {
  toolkits: ["valyu"],
  mcp: true,
});
```

#### Path 2, Step 3: Connect your agent to the MCP server

Pass the session's MCP URL and headers to your agent and run a Valyu request
```python
import asyncio
from claude_agent_sdk import ClaudeSDKClient, ClaudeAgentOptions, AssistantMessage, TextBlock

options = ClaudeAgentOptions(
    mcp_servers={
        "composio": {
            "type": "http",
            "url": session.mcp.url,
            "headers": session.mcp.headers,
        }
    },
    system_prompt="You are a helpful assistant with access to Valyu tools.",
    tools=[],
    allowed_tools=["mcp__composio__*"],
)

async def main():
    async with ClaudeSDKClient(options=options) as client:
        await client.query("Research the latest battery recycling methods using specialist and web sources, and return a cited comparison.")
        async for message in client.receive_response():
            if isinstance(message, AssistantMessage):
                for block in message.content:
                    if isinstance(block, TextBlock):
                        print(block.text)

asyncio.run(main())
```

```typescript
import { createMCPClient } from "@ai-sdk/mcp";
import { openai } from "@ai-sdk/openai";
import { generateText, stepCountIs } from "ai";

const client = await createMCPClient({
  transport: { type: "http", url: mcp.url, headers: mcp.headers },
});

const { text } = await generateText({
  model: openai("gpt-5.6-sol"),
  tools: await client.tools(),
  prompt: "Research the latest battery recycling methods using specialist and web sources, and return a cited comparison.",
  stopWhen: stepCountIs(10),
});

console.log(text);
await client.close();
```

## Why Use Composio?

### 1. AI Native Valyu Integration

- Supports both Valyu MCP and direct API based integrations
- Structured, LLM-friendly schemas for reliable research tool execution
- Search specialist, proprietary, and web sources from one agent workflow

### 2. Secure API Key Auth

- Connect Valyu with your own API key through Composio
- Central place to store, scope, and revoke Valyu access
- Per user and per environment credentials instead of hard-coded keys

### 3. Agent Optimized Design

- Tools are tuned using real error and success rates to improve research reliability over time
- Structured outputs help agents preserve citations and present clear findings
- Comprehensive execution logs show what ran, when, and on whose behalf

### 4. Enterprise Grade Security

- Fine-grained RBAC so you control which agents and users can access Valyu
- Scoped, least privilege access to Valyu research capabilities
- Full audit trail of agent actions to support review and compliance

## Use Valyu with any AI Agent Framework

Choose a framework you want to connect Valyu with:

- [ChatGPT](https://composio.dev/toolkits/valyu/framework/chatgpt)
- [Claude Cowork](https://composio.dev/toolkits/valyu/framework/claude-cowork)
- [Hermes](https://composio.dev/toolkits/valyu/framework/hermes-agent)
- [Atomic Agent](https://composio.dev/toolkits/valyu/framework/atomic-agent)

## Related Toolkits

- [Composio](https://composio.dev/toolkits/composio) - Composio is an integration platform that connects AI agents with hundreds of business tools. It streamlines authentication and lets you trigger actions across services—no custom code needed.
- [Composio search](https://composio.dev/toolkits/composio_search) - Composio search is a unified web search toolkit spanning travel, e-commerce, news, financial markets, images, and more. It lets you and your apps tap into up-to-date web data from a single, easy-to-integrate service.
- [Perplexityai](https://composio.dev/toolkits/perplexityai) - Perplexityai delivers natural, conversational AI models for generating human-like text. Instantly get context-aware, high-quality responses for chat, search, or complex workflows.
- [Browser tool](https://composio.dev/toolkits/browser_tool) - Browser tool is a virtual browser integration that lets AI agents interact with the web programmatically. It enables automated browsing, scraping, and action-taking from any AI workflow.
- [Ai ml api](https://composio.dev/toolkits/ai_ml_api) - Ai ml api is a suite of AI/ML models for natural language and image tasks. It provides fast, scalable access to advanced AI capabilities for your apps and workflows.
- [Aivoov](https://composio.dev/toolkits/aivoov) - Aivoov is an AI-powered text-to-speech platform offering 1,000+ voices in over 150 languages. Instantly turn written content into natural, human-like audio for any application.
- [All images ai](https://composio.dev/toolkits/all_images_ai) - All-Images.ai is an AI-powered image generation and management platform. It helps you create, search, and organize images effortlessly with advanced AI capabilities.
- [AllModels](https://composio.dev/toolkits/allmodels) - AllModels is a unified API for text-to-speech, speech-to-text, realtime voice, and voice cloning across AI providers. It gives developers one consistent way to build and manage voice features.
- [AltTextLab](https://composio.dev/toolkits/alt_text_lab) - AltTextLab is an AI service that generates accessible, SEO-aware alt text for images. It helps teams make image content easier to understand, index, and publish.
- [Anthropic administrator](https://composio.dev/toolkits/anthropic_administrator) - Anthropic administrator is an API for managing Anthropic organizational resources like members, workspaces, and API keys. It helps you automate admin tasks and streamline resource management across your Anthropic organization.
- [Api labz](https://composio.dev/toolkits/api_labz) - Api labz is a platform offering a suite of AI-driven APIs and workflow tools. It helps developers automate tasks and build smarter, more efficient applications.
- [Apiframe](https://composio.dev/toolkits/apiframe) - Apiframe is an API platform for generating and managing AI images, videos, music, uploads, assets, jobs, and custom LoRAs. It gives developers one clean API for creative AI workflows without juggling multiple model providers.
- [Apipie ai](https://composio.dev/toolkits/apipie_ai) - Apipie ai is an AI model aggregator offering a single API for accessing top AI models from multiple providers. It helps developers build cost-efficient, latency-optimized AI solutions without juggling multiple integrations.
- [Arize AX](https://composio.dev/toolkits/arize_ax) - Arize AX is an AI engineering platform for tracing, evaluating, and improving AI applications. Use it to debug LLM behavior, compare experiments, and improve production AI quality.
- [Artificial Analysis](https://composio.dev/toolkits/artificial_analysis) - Artificial Analysis is an independent benchmarking platform for AI models and API providers. Use it to compare model intelligence, coding, math, pricing, latency, throughput, and arena rankings.
- [AssemblyAI](https://composio.dev/toolkits/assemblyai) - AssemblyAI is a speech-to-text and audio intelligence API for uploaded or hosted media. Use it to turn audio and video into accurate transcripts, summaries, and insights.
- [Astica ai](https://composio.dev/toolkits/astica_ai) - Astica ai provides APIs for computer vision, NLP, and voice synthesis. Integrate advanced AI features into your app with a single API key.
- [Avoma](https://composio.dev/toolkits/avoma) - Avoma is an AI meeting assistant for recording, transcribing, analyzing, and managing meetings, calls, notes, scorecards, and conversation intelligence. It helps teams turn conversations into searchable notes, follow-ups, coaching insights, and revenue intelligence.
- [Bigml](https://composio.dev/toolkits/bigml) - BigML is a machine learning platform that lets you build, train, and deploy predictive models from your data. Its intuitive interface and robust API make machine learning accessible and efficient.
- [Black Forest Labs](https://composio.dev/toolkits/bfl) - Black Forest Labs provides hosted FLUX models for generating and editing images and videos. It offers fast, flexible media creation with asynchronous processing and fine-tuning support.

## Frequently Asked Questions

### Do I need my own developer credentials to use Valyu with Composio?

Yes, Valyu requires you to configure your own API key credentials. Once set up, Composio handles secure credential storage and API request handling for you.

### Can I use multiple toolkits together?

Yes! Composio's Tool Router enables agents to use multiple toolkits. [Learn more](https://docs.composio.dev/tool-router/overview).

### Is Composio secure?

Composio is SOC 2 and ISO 27001 compliant with all data encrypted in transit and at rest. [Learn more](https://trust.composio.dev).

### What if the API changes?

Composio maintains and updates all toolkit integrations automatically, so your agents always work with the latest API versions.

---
[See all toolkits](https://composio.dev/toolkits) · [Composio docs](https://docs.composio.dev/llms.txt)
