How to integrate CapSolver MCP with Hermes

Connect Hermes to CapSolver MCP. Create and poll a captcha solving task, check your capsolver account balance, and more using natural language, with authentication handled for you.

CapSolver logoCapSolver
Api Key

CapSolver is a CAPTCHA-solving service with APIs for recognition and token workflows. It helps developers automate CAPTCHA challenges with fast, programmable task handling.

16 Tools

Introduction

Hermes is a 24/7 autonomous agent that lives on your computer or server — it remembers what it learns and evolves as your usage grows.

This guide explains the easiest and most robust way to connect your CapSolver account to Hermes. You can do this through either Composio Connect CLI or Composio Connect MCP. For personal use we recommend the CLI, but you won't go wrong with MCP either.

Also integrate CapSolver with

What is Composio Connect?

Composio Connect is a consumer offering that lets anyone plug 1,500+ applications directly into their agent harness — including Hermes. It can:

  • Search and load tools from relevant toolkits on-demand, reducing context usage.
  • Chain multiple tools to accomplish complex workflows via a remote workbench, without excessive back-and-forth with the LLM.
  • Manage app authentication end-to-end with zero manual overhead.

Integrating CapSolver with Hermes

Using Composio Connect CLI

1. Install the Composio CLI

Run the install script directly, or paste https://composio.dev/hermes into your Hermes chat box to have it installed for you.

bash
curl -fsSL https://composio.dev/install | bash
Hermes authenticating with Composio

2. Authenticate

Once the CLI is installed, ask Hermes to authenticate with Composio.

3. Connect to CapSolver

Ask your agent to connect to CapSolver, or simply request any CapSolver-related task. Hermes will prompt you to authenticate and authorize access.

4. Done. You're all set with a new CapSolver connection.


Using Composio Connect MCP

1. Get your MCP URL and API Key

Go to dashboard.composio.dev and copy your Connect MCP URL and API key.

Copy MCP URL and API key from Composio dashboard

2. Open the Hermes config file

bash
nano ~/.hermes/config.yaml

3. Add the Composio Connect MCP server

bash
mcp_servers:
  composio:
    url: "https://connect.composio.dev/mcp"
    headers:
      x-consumer-api-key: "YOUR_COMPOSIO_API_KEY"
    connect_timeout: 60
    timeout: 180

Save with Ctrl + O, Enter, then exit with Ctrl + X.

4. Restart your Hermes agent

Once restarted, ask your agent to connect to CapSolver or request any CapSolver-related task. It will prompt you to authenticate and authorize access.

5. Done!

What is the CapSolver MCP server, and what's possible with it?

The CapSolver MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your CapSolver account. It provides structured and secure access to CAPTCHA recognition and token-solving workflows, so your agent can solve supported CAPTCHA challenges, recognize text from images, check task results and balances, and submit solution feedback on your behalf.

  • Solve supported CAPTCHA challenges: Have your agent solve reCAPTCHA, Cloudflare Turnstile, Cloudflare Challenge, AWS WAF, GeeTest, MTCaptcha, DataDome, and BotDeflector challenges.
  • Track asynchronous solutions: Let the agent wait for and retrieve CAPTCHA task results, with bounded polling for supported workflows.
  • Recognize CAPTCHA images: Direct your agent to classify AWS WAF or reCAPTCHA v2 images, recognize image text, or run supported vision modules for points, distances, angles, rectangles, and text.
  • Monitor usage and report outcomes: Instruct your agent to check the CapSolver balance and submit feedback when a previously returned solution token worked or failed.

Way Forward

With CapSolver connected, Hermes can now act on your behalf whenever it detects a relevant task or you ask it to.

From here, you can extend Hermes further:

  • Connect more apps: Calendar, Slack, Notion, Linear, and hundreds of others are available through the same Composio Connect setup. Each new integration compounds what Hermes can do for you.
  • Build workflows across tools: Once multiple apps are connected, Hermes can chain actions together — turn an email into a calendar invite, a Slack message into a Linear ticket, or a meeting note into a follow-up draft.
  • Let it learn your patterns: The more you use Hermes, the better it gets at anticipating how you'd handle recurring tasks. Give it feedback on drafts and decisions, and it will adapt.

If you run into trouble or want to share what you've built, join the community or check out the Docs for deeper configuration options.

TOOLS

Supported Tools

Every CapSolver action and event your agent gets out of the box.

Classify AWS WAF Image

Classify one AWS WAF challenge image or a nine-image grid and return the immediate geometric or object result.

Classify reCAPTCHA V2 Image

Classify a reCAPTCHA v2 challenge image for a documented object category and return the immediate selection result.

Get Balance

Return the connected CapSolver account balance and non-secret package metadata.

Get Task Result

Get one asynchronous CapSolver task result, or optionally poll it every three seconds for a bounded time.

Run Vision Engine

Run one documented CapSolver vision module and return its immediate points, distance, angle, rectangles, or text result.

Solve AWS WAF

Create one AWS WAF token task with or without a caller-supplied proxy and optionally poll every three seconds for a bounded time.

Solve BotDeflector

Create exactly one proxyless BotDeflector task from a target flow token and optionally poll every three seconds for a bounded time.

Solve Cloudflare Challenge

Create one Cloudflare challenge task through a sticky caller-supplied proxy and optionally poll every three seconds for bounded clearance output.

Solve Cloudflare Turnstile

Create one proxyless Cloudflare Turnstile task and optionally poll every three seconds for a bounded time.

Solve DataDome

Create exactly one DataDome slider task with a caller-supplied proxy and optionally wait a bounded time for its solution cookie.

Solve GeeTest

Create one GeeTest v3 or v4 token task and optionally poll every three seconds for a bounded time.

Solve Image To Text

Recognize text or number answers from base64-encoded images and return the immediate recognition result.

Solve MTCaptcha

Create one proxyless or caller-proxied MTCaptcha token task and optionally poll every three seconds for a bounded time.

Solve reCAPTCHA V2

Solve one standard or enterprise reCAPTCHA v2 challenge in task or synchronous mode.

Solve reCAPTCHA V3

Solve a standard, enterprise, or M1 reCAPTCHA v3 challenge in task or synchronous mode.

Submit Task Feedback

Report whether a previously returned CapSolver token worked, using only the documented minimal task and result fields.

FAQ

Frequently asked questions

With a standalone CapSolver MCP server, the agents and LLMs can only access a fixed set of CapSolver tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from CapSolver and many other apps based on the task at hand, all through a single MCP endpoint.

Yes, you can. Hermes fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right CapSolver tools.

Yes, absolutely. You can configure which CapSolver scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your CapSolver data and credentials are handled as safely as possible.

Start with CapSolver.It takes 30 seconds.

Managed auth, hosted MCP servers, and every CapSolver tool your agent needs.Free to start.

Start building