Obscura Plugin
FreeNot checkedMCP server for Obscura headless browser — CLI wrapper for AI agent integration with web scraping, JavaScript rendering, and browser automation
About
MCP server for Obscura headless browser — CLI wrapper for AI agent integration with web scraping, JavaScript rendering, and browser automation
README
Skill-driven plugin for Obscura headless browser — gives AI coding agents direct access to web scraping and browser automation via slash commands.
Two approaches in Obscura:
obscura-plugin(this plugin) — skill-driven with read-only commands (obscura_fetch,obscura_scrape, etc.), designed for autonomous agent pipelines
Install
Grok Build (xAI)
grok plugin marketplace add epicsagas/obscura-plugin
grok plugin install obscura@obscura-plugin --trust
Direct install without registering a marketplace is also supported: grok plugin install epicsagas/obscura-plugin --trust. Grok reads skills from skills/ and agents from agents/ at the plugin root.
Claude Code (zero-touch)
obscura-plugin ships a .claude-plugin/ manifest. Register the standalone marketplace once, then install:
claude plugin marketplace add epicsagas/obscura-plugin
claude plugin install obscura-plugin@obscura-plugin
The SessionStart hook downloads obscura and obscura-worker automatically on first load. No manual steps needed.
Codex CLI
codex plugin marketplace add epicsagas/obscura-plugin
codex plugin add obscura-plugin@obscura-plugin
Skills and agents are available immediately — no further steps needed.
Antigravity
agy plugin install https://github.com/epicsagas/obscura-plugin
obscura-plugin installautomatically downloads theobscuraandobscura-workerbinaries from Obscura releases. Linux requires glibc 2.35+ (Ubuntu 22.04+).
macOS / Linux
# pre-built binary, no Rust required
curl --proto '=https' --tlsv1.2 -LsSf \
https://github.com/epicsagas/obscura-plugin/releases/latest/download/obscura-plugin-installer.sh | sh
Windows
# pre-built binary, no Rust required
irm https://github.com/epicsagas/obscura-plugin/releases/latest/download/obscura-plugin-installer.ps1 | iex
Homebrew (macOS / Linux)
brew install epicsagas/tap/obscura-plugin
Via Rust toolchain
# pre-built binary via Rust toolchain (fast)
cargo binstall obscura-plugin
# build from source (requires Rust toolchain)
cargo install obscura-plugin
obscura-plugin --versionto verify. Update withbrew upgrade obscura-pluginor re-run the installer script.
Register with your AI tools
After installing the binary, run obscura-plugin install to connect it to your tools:
obscura-plugin install # interactive — pick which tools
obscura-plugin install cursor # Cursor
obscura-plugin install opencode # OpenCode
obscura-plugin install cline # Cline
obscura-plugin install all # all at once
obscura-plugin uninstall cursor # remove from a specific tool
obscura-plugin list # show supported tools and status
What gets installed
| Tool | Skills | Method |
|---|---|---|
| Claude Code | plugin auto-discovers | .claude-plugin/ manifest |
| Codex CLI | plugin auto-discovers | .codex-plugin/ manifest |
| Antigravity | plugin auto-discovers | root plugin.json |
| Cursor | ~/.cursor/rules/ |
obscura-plugin install |
| OpenCode | ~/.opencode/skills/ |
obscura-plugin install |
| Cline | ~/.cline/skills/ |
obscura-plugin install |
Skills
Registered skills are available as slash commands inside your agent:
/obscura-fetch <url> [--dump html|text|links|markdown] [--eval <js>] [--selector <css>] [--stealth]
/obscura-scrape <url1> <url2> ... [--eval <js>] [--concurrency <N>] [--format json|text]
/obscura-pipeline <index-url> # discover links → scrape in one pipeline
/obscura-crawl <seed-url> # recursive crawl with depth control, pagination, sitemap discovery
Skill parameters
obscura-fetch
| Parameter | Type | Description |
|---|---|---|
url |
string | URL to fetch (required) |
dump |
string | html · text · links · markdown (default: html) |
eval |
string | JavaScript expression to evaluate |
wait_until |
string | load · domcontentloaded · networkidle0 (default: load) |
selector |
string | CSS selector to wait for before returning |
stealth |
boolean | Enable anti-detection + tracker blocking¹ |
user_agent |
string | Custom User-Agent string |
quiet |
boolean | Suppress banner (default: true) |
obscura-scrape
| Parameter | Type | Description |
|---|---|---|
urls |
string[] | URLs to scrape (required) |
eval |
string | JavaScript expression applied to each page |
concurrency |
number | Parallel workers (default: 10) |
format |
string | json · text (default: json) |
proxy |
string | HTTP/SOCKS5 proxy URL for all workers |
obscura-pipeline
| Parameter | Type | Description |
|---|---|---|
url |
string | Index page URL (required) |
selector |
string | CSS selector for link extraction |
concurrency |
number | Parallel workers for scraping |
stealth |
boolean | Anti-detection mode¹ |
¹ Stealth mode requires Obscura built with
--features stealth. The default release binary includes stealth.
obscura-crawl
| Parameter | Type | Description |
|---|---|---|
url |
string | Seed URL to start crawling from (required) |
max_depth |
number | Maximum crawl depth (default: 3) |
same_domain |
boolean | Only follow links on the same domain (default: true) |
url_filter |
string | Regex/glob pattern to filter URLs by path |
The obscura-browser agent
A self-directed web data collection specialist. Invoke it for tasks like:
"Collect all product titles and prices from these 30 URLs" "Fetch the docs at example.com/api and summarize the endpoints" "Scrape the HN front page and return structured JSON" "Crawl example.com/blog up to depth 2 and extract all post titles"
The agent knows Obscura's limits — it stops and escalates to Playwright when login or interaction is required. Supports agentic crawling with depth control, pagination detection, sitemap discovery, and adaptive extraction.
Project structure
obscura-plugin/
skills/ # shared skills
obscura-fetch/SKILL.md
obscura-scrape/SKILL.md
obscura-pipeline/SKILL.md
obscura-crawl/SKILL.md
agents/ # shared agent (markdown)
obscura-browser.md
scripts/
install.js # binary bootstrap (SessionStart hook)
.claude-plugin/ # Claude Code plugin
plugin.json, hooks.json, marketplace.json
.codex-plugin/ # Codex CLI plugin
plugin.json, hooks.json
agents/obscura-browser.toml # Codex-specific TOML agent
plugin.json # Antigravity (agy) plugin marker
hooks.json # Antigravity hooks
src/ # Rust installer (cursor, opencode, cline)
tests/
Cargo.toml
Build from source
cargo build --release
./target/release/obscura-plugin --help
License
Apache 2.0
Installing Obscura Plugin
This server has no published package — it is built from source. Open the repository and follow its README.
▸ github.com/epicsagas/obscura-pluginFAQ
Is Obscura Plugin MCP free?
Yes, Obscura Plugin MCP is free — one-click install via Unyly at no cost.
Does Obscura Plugin need an API key?
No, Obscura Plugin runs without API keys or environment variables.
Is Obscura Plugin hosted or self-hosted?
Self-hosted: the server runs locally on your machine via the install command above.
How do I install Obscura Plugin in Claude Desktop, Claude Code or Cursor?
Open Obscura Plugin on unyly.org, pick your client tab (Claude Desktop, Claude Code, Cursor) and press Install — the config is generated automatically, no JSON editing.
Related MCPs
Playwright
Browser automation, scraping, screenshots
by MicrosoftPuppeteer
Browser automation and web scraping.
by modelcontextprotocolGarmin Connect
An MCP server for Garmin Connect that provides access to fitness activities, health statistics, and sleep data by routing requests through a headless browser to
by etweisbergHiggsfield Unlimited
MCP server for Higgsfield AI that enables unlimited-mode image, video, audio generation, uploads, and job management via multiple parallel accounts, using brows
by nukIeeropentabs-dev/opentabs
Plugin-based server and Chrome extension that gives AI agents access to web apps through your authenticated browser session, with a plugin SDK.
by opentabs-devhlydecker/ucsc-genome-mcp
Interact with the UCSC Genome Browser API to find genomes, chromosomes and more.
by hlydecker34892002/bilibili-mcp-js
Search Bilibili content, with LangChain integration examples.
by 34892002achiya-automation/safari-mcp
Native Safari browser automation without a Chrome dependency.
by achiya-automationagent-infra/mcp-server-browser
Browser automation using Puppeteer, supporting local and remote browser connections.
by bytedanceaparajithn/agent-scraper-mcp
Web scraping: clean content extraction, CSS-selector scraping, Playwright screenshots, link and metadata extraction, and Google search.
by aparajithnCompare Obscura Plugin with
Not sure what to pick?
Find your stack in 60 seconds
Author?
Embed badge for your README
Browse similar
All browse MCPs
