Http Client logo

Http Client

Organization
openbotx
http-client

Make HTTP requests (GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONS) to APIs and web services. Use when the user needs to call a REST API, fetch data from an endpoint, send form data, upload files, download files, or test HTTP services.

Overview

Publisheropenbotx
Repositoryopenbotx
Skill namehttp-client
Stars
95
Forks
25
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by openbotx on GitHub. Read the source before you install it.

Installation

Install the Http Client AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/openbotx/openbotx/tree/main/openbotx/skills/http-client
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/openbotx/openbotx.git /tmp/openbotx
mkdir -p .claude/skills
cp -r /tmp/openbotx/openbotx/skills/http-client .claude/skills/http-client
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Http Client in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Http Client on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Http Client is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

HTTP Client

Use the http_client tool to make HTTP requests directly without needing curl or external binaries.

Tool: http_client

Parameters

ParameterTypeRequiredDescription
methodstringYesGET, POST, PUT, DELETE, PATCH, HEAD, or OPTIONS
urlstringYesRequest URL
headersobjectNoHTTP headers as key-value pairs
bodystringNoRequest body
content_typestringNoBody content type: json (default), form, text, or xml
authstringNoAuth profile name for authenticated requests (configured in config)
timeoutintegerNoTimeout in seconds (default: 30)
follow_redirectsbooleanNoFollow redirects (default: true)
download_pathstringNoSave response body to this file path
upload_filestringNoPath to file to upload as multipart form data
upload_fieldstringNoForm field name for uploaded file (default: file)

Basic GET

http_client(method="GET", url="https://api.example.com/users")

GET with query parameters

http_client(method="GET", url="https://api.example.com/users?page=2&limit=10")

GET with custom headers

http_client(method="GET", url="https://api.example.com/users", headers={"Accept": "application/json", "X-Custom-Header": "value"})

POST with JSON body

http_client(method="POST", url="https://api.example.com/users", body="{\"name\": \"Alice\", \"email\": \"alice@example.com\"}")

The content_type defaults to json, which sets Content-Type: application/json automatically.

POST with form-encoded body

http_client(method="POST", url="https://api.example.com/login", content_type="form", body="username=alice&password=secret")

POST with XML body

http_client(method="POST", url="https://api.example.com/soap", content_type="xml", body="<request><action>query</action></request>")

PUT (full update)

http_client(method="PUT", url="https://api.example.com/users/42", body="{\"name\": \"Alice Updated\", \"email\": \"alice@example.com\"}")

PATCH (partial update)

http_client(method="PATCH", url="https://api.example.com/users/42", body="{\"name\": \"Alice Updated\"}")

DELETE

http_client(method="DELETE", url="https://api.example.com/users/42")

HEAD (check resource existence)

http_client(method="HEAD", url="https://api.example.com/users/42")

OPTIONS (check allowed methods)

http_client(method="OPTIONS", url="https://api.example.com/users")

Authentication

Auth profiles (recommended)

Use the auth parameter with a configured profile name. Auth profiles support OAuth 1.0a, Basic, and Bearer authentication automatically:

http_client(method="POST", url="https://api.twitter.com/2/tweets", auth="twitter", body="{\"text\": \"Hello!\"}")
http_client(method="GET", url="https://api.example.com/data", auth="my_api")

Manual headers

You can also pass auth headers manually:

http_client(method="GET", url="https://api.example.com/me", headers={"Authorization": "Bearer eyJhbGciOi..."})
http_client(method="GET", url="https://api.example.com/me", headers={"Authorization": "Basic dXNlcjpwYXNz"})
http_client(method="GET", url="https://api.example.com/data", headers={"X-API-Key": "your-api-key"})

Download

Save a response directly to a file using download_path. Use the absolute paths from your system prompt:

http_client(method="GET", url="https://example.com/report.pdf", download_path="/path/to/workspace/reports/report.pdf")

Download an image to the public media directory:

http_client(method="GET", url="https://example.com/photo.jpg", download_path="/path/to/public/media/photo.jpg")

Returns: {"status": 200, "path": "/absolute/path/to/file", "size": 12345, "content_type": "application/pdf"}

Upload

Upload a file as multipart form data using upload_file:

http_client(method="POST", url="https://api.example.com/upload", upload_file="reports/data.csv")

Custom field name (default is "file"):

http_client(method="POST", url="https://api.example.com/upload", upload_file="images/logo.png", upload_field="image")

Upload with extra form fields (pass as JSON in body):

http_client(method="POST", url="https://api.example.com/upload", upload_file="doc.pdf", body="{\"description\": \"Monthly report\"}")

Upload with auth:

http_client(method="POST", url="https://api.example.com/upload", upload_file="data.csv", headers={"Authorization": "Bearer token123"})

Advanced Options

Custom timeout

http_client(method="GET", url="https://slow-api.example.com/data", timeout=120)

Disable redirect following

http_client(method="GET", url="https://example.com/redirect", follow_redirects=false)

Tips

  • The response includes status, headers, body, and truncated fields.
  • Response bodies larger than 50,000 characters are truncated.
  • For APIs that return JSON, parse the response body as needed.
  • The content_type parameter sets the Content-Type header automatically: json → application/json, form → application/x-www-form-urlencoded, text → text/plain, xml → application/xml.
  • Use GET for reads, POST for creates, PUT for full replacements, PATCH for partial updates, DELETE for removals, HEAD for existence checks, OPTIONS for CORS/capability checks.
  • Use download_path for binary files (images, PDFs, audio) — avoids encoding issues.
  • Use upload_file for multipart uploads — auto-detects MIME type from file extension.

Frequently asked questions

What does the Http Client AI skill do?

Make HTTP requests (GET, POST, PUT, PATCH, DELETE, HEAD, OPTIONS) to APIs and web services. Use when the user needs to call a REST API, fetch data from an endpoint, send form data, upload files, download files, or test HTTP services.

Why use Http Client on TypingMind?

Because you install it once and use it with any model. Http Client is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Http Client in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/openbotx/openbotx/tree/main/openbotx/skills/http-client. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Http Client?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Http Client?

As many as you like. As long as a model supports skills, you can use Http Client with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Http Client AI skill free?

Yes. It is published on GitHub by openbotx under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇