# Porticol with Claude Code

> Connect Claude Code to Porticol's MCP server, so it can search, read, send and run your API collections.

Canonical: https://porticol.app/integrations/claude-code

Claude Code starts `porticol-cli mcp` as a local server and calls it like any other tool. Each call reads the workspace on your computer; your collections stay in Porticol.

## Install the app and the command line

```
curl -fsSL https://porticol.app/install.sh | sh
```

On Windows, run `irm https://porticol.app/install.ps1 | iex` in PowerShell. Open Porticol once and sign in.

## Add the server

```
claude mcp add porticol -- porticol-cli mcp
```

Add `--write` to let the agent create or change requests: `claude mcp add porticol -- porticol-cli mcp --write`.

## What it can do

- Search collections, requests and history for a query.
- Read a collection with its requests and examples, or one request of it.
- List the environments, or read one by id.
- Send a request and return what came back.
- Run a collection and wait for the finished run.
- Read recent sends and their results.
- Preview an OpenAPI document as a collection, without importing it.
- Create or change requests only when the server starts with --write.
- Secret values stay in Porticol: every result is masked, and a protected environment waits for a person in the app.

## Try it

Ask it to search your workspace for checkout, send the request that fails, and say why the response is a 401.

## Questions

**Does Claude Code need my API secrets?**

No. Porticol resolves a secret inside the app when it sends the request, and masks it in every tool result. A protected environment refuses an agent's send until a person allows it.

**Can Claude Code change my collections?**

Only when the server starts with --write. Without it the two write tools are refused.

## Try it on your own APIs

Free for one seat, on macOS, Windows and Linux.