X (Twitter)LinkedInGitHubDiscordYouTube

How to integrate Mathpix MCP with Hermes

Connect Hermes to Mathpix MCP. Extract latex from equation image, parse photographed table into csv, and more using natural language, with authentication handled for you.

Get started for freeGet a demo
Mathpix logoMathpix
Api Key

Mathpix extracts text, mathematics, tables, and other structured content from images and documents. Converts visual content into editable formats for publishing, computation, and archival.

28 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 Mathpix 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 Mathpix with

ChatGPT WorkClaude Cowork

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 Mathpix 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 Mathpix

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

4. Done. You're all set with a new Mathpix 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 Mathpix or request any Mathpix-related task. It will prompt you to authenticate and authorize access.

5. Done!

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

The Mathpix MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Mathpix account. It provides structured and secure access so your agent can perform Mathpix operations on your behalf.

Way Forward

With Mathpix 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 Mathpix action and event your agent gets out of the box.

Convert Mathpix Markdown

Submit Mathpix Markdown, wait for one requested format to finish, then return the conversion ID and downloadable output file.

Create App Token

Mint a short-lived client OCR credential, optionally with a live ink strokes session.

Delete Conversion

Permanently delete one Mathpix Markdown conversion's hosted output data after explicit confirmation.

Delete Document

Permanently delete one Mathpix document source and its hosted outputs after explicit confirmation.

Delete File

Permanently delete one terminal Files API file and its Mathpix-hosted results.

Finalize File Job

Permanently close one Files API job to new file additions and arm its completion webhook.

Get App Token

Get expiry and ownership metadata for a specific short-lived Mathpix app token.

Get Conversion Result

Wait for an existing Mathpix Markdown conversion and requested format to finish, then return its status and downloadable output file without creating a conversion.

Get Document Result

Wait for an existing Mathpix document job and requested format to finish, then return its status and downloadable output file without creating a new job.

Get File Job

Get aggregate status, file and page counters, and timestamps for one Files API job.

Get File Result

Wait for an existing Files API file and selected format to finish, then return its status and downloadable output without creating a file.

Get Job File by Custom ID

Get the complete Files API processing status for one job member using the exact caller-defined custom ID assigned at submission.

Get OCR Usage

Return one page of aggregated Mathpix OCR usage for a date range, optionally grouped by usage type, request configuration, or application.

Get Storage Onboarding Identities

Get the Mathpix AWS, Azure, and GCP identities needed to grant cloud-storage access.

List Conversions

List one page of retained Mathpix Markdown conversion records, optionally filtered by date, and return IDs usable by conversion result or deletion tools.

List Data Sources

List cloud-storage data sources registered with Mathpix, returning only allowlisted non-secret metadata.

List Documents

List retained document OCR jobs for the connected account, optionally filtered by date or document ID, and return one page.

List File Job Files

List one cursor-paginated page of files in a Mathpix Files API job, optionally filtered by terminal status.

List File Jobs

List one cursor-paginated page of Files API jobs newest first, optionally bounded by inclusive UTC dates.

OCR Document

Submit a PDF, office document, or ebook URL, wait for OCR and the requested conversion to finish, then return its Mathpix job ID and downloadable output file.

OCR Image

Extract text, math, tables, diagrams, or chemistry from one image URL or base64 data URI and return the requested OCR representations.

Process File URI

Submit one public or registered-cloud document URI to the paid Files API, wait for OCR and one requested output, and return the retained file ID and downloadable result.

Process Image Batch

Submit a paid asynchronous batch of 1-100 named public image URLs, wait until every key has a semantically successful OCR result, and return the retained batch ID and results.

Recognize Strokes

Recognize handwritten math or text from aligned x/y digital-ink stroke arrays and return OCR representations.

Revoke App Token

Irreversibly revoke one short-lived app token immediately.

Search OCR Results

Search retained image and stroke OCR history by date, identifiers, content, tags, or detected content and return one page of results.

Submit File Job

Submit 1 to 200,000 remote documents as one paid asynchronous Mathpix Files job.

Upload and Process File

Upload one local document to the paid Mathpix Files API, wait until OCR and one requested output are ready, then return the retained Mathpix file ID and a downloadable result.

FRAMEWORKS

How to build Mathpix MCP Agent with another framework

ChatGPT Work logo

ChatGPT Work

Use Mathpix MCP with ChatGPT Work

Claude Cowork logo

Claude Cowork

Use Mathpix MCP with Claude Cowork

FAQ

Frequently asked questions

With a standalone Mathpix MCP server, the agents and LLMs can only access a fixed set of Mathpix tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Mathpix 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 Mathpix tools.

Yes, absolutely. You can configure which Mathpix 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 Mathpix data and credentials are handled as safely as possible.

Start with Mathpix.It takes 30 seconds.

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

Start building