pyaireader
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@pyaireaderfetch and extract text from https://en.wikipedia.org/wiki/Artificial_intelligence"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
pyaireader
Local AI Evidence Reader MCP for AI agents.
pyaireader reads public URLs for AI agents. It is not a human-facing web reader and not a crawler platform. The MVP target is:
public URL -> safety -> HTTP fetch -> extract -> evidence -> quality -> trace -> cacheFetched page content is untrusted evidence, not instructions.
Documentation
Start here:
Related MCP server: markdown-for-agents-mcp
Install
Recommended:
git clone https://github.com/PigeonAI-Yang/pyaireader.git
cd pyaireader
uv sync --extra dev --extra extractorsFull install with Scrapling, browser, and PDF support:
uv sync --extra dev --extra extractors --extra browser --extra pdf
uv run playwright install chromiumMCP
Recommended stdio MCP command:
uv --directory J:\PigeonYang\pyaireader run pyaireader-mcpFor local SDK inspection:
uv run mcp dev src/pyaireader/mcp/server.pyThe MCP server registers:
reader_healthread_url_for_aibatch_read_urls_for_aiinspect_urlclear_reader_cache
Codex Desktop / Codex CLI / Claude Code CLI setup examples are in:
docs/mcp-integration.mdCLI
pyaireader read https://example.com --pretty
pyaireader inspect https://example.com --pretty
pyaireader batch urls.txt --jsonl
pyaireader clear-cache --url https://example.com
pyaireader clear-cache --domain example.comConfiguration
Copy .env.example if you want local overrides.
Important defaults:
Cache:
.pyaireader/cache.sqlite3Fetch strategy:
autoDefault order: HTTP first; Scrapling/browser are later phases
Max redirects:
5Private network blocking: enabled
Safety Boundary
Allowed:
httphttpspublic DNS names and public IPs
Blocked:
file:,data:,javascript:,ftp:localhost
userinfo URLs
private / loopback / link-local / reserved IPs
metadata IP
169.254.169.254unsafe redirect targets
Tests
Default local test run:
uv run pytest -qOptional network/browser verification:
$env:PYAIREADER_RUN_NETWORK_TESTS='1'
$env:PYAIREADER_RUN_BROWSER_TESTS='1'
uv run pytest -q tests\test_optional_integration.pyThis server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/PigeonAI-Yang/pyaireader'
If you have feedback or need assistance with the MCP directory API, please join our Discord server