
AgentReader
io.github.jedidiahcox-bitPublished by GitHub account jedidiahcox-bitv0.2.0Updated Oct 16, 2026
Any URL to clean markdown/JSON; PDF, XLSX, CSV, DOCX to text and tables. Free tier for agents.
The publisher's own server: AgentReader
Overview
Clearcrawl MCP turns public URLs and documents (PDF, XLSX, CSV, DOCX) into clean markdown, JSON or tables for an AI assistant.
- What you can do
- Fetch and extract a public URL as clean markdown or structured JSON with title, author, date, text, links and tables, with ads, menus and footers stripped.
- Convert PDF, XLSX/XLS, CSV and DOCX files, given by URL or local path, into per-page text, sheet rows and records, or markdown tables.
- When to use it
- Useful when an assistant needs readable text or tables from web pages or office documents without writing its own scraping and parsing code, especially for one-off research or document extraction within the free daily allowance.
- Requirements
- Remote streamable HTTP endpoint, no install needed; a local stdio mode via npx is also described. No signup for the free tier of 100 calls per day. Paid credits need an API key sent as an Authorization Bearer header (or the CLEARCRAWL_API_KEY variable in local mode), bought through a Stripe checkout. Public http(s) URLs only, 15 MB max.
Installation
In SourceWeft
- Open AgentReader in the dashboard and add it to a workspace.
- Enable the server for the chats that should use its tools.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Use with an agent
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.jedidiahcox-bit%2Fagentreader/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Other MCP clients
Add this to your client's mcpServers config.
{
"mcpServers": {
"agentreader": {
"type": "http",
"url": "https://agentreader.onrender.com/mcp"
}
}
}README
Clearcrawl MCP
An MCP server for Clearcrawl, a pay-per-call API built for AI agents:
read_url: turns any public URL into clean markdown or structured JSON (title, author, date, text, links, tables). Ads, menus and footers are stripped. PDF URLs are converted automatically.convert_file: turns a PDF, XLSX/XLS/CSV or DOCX (by URL or local path) into text and tables (per-page text, sheet rows and records, markdown tables).
Free tier: 100 calls a day with no signup. Paid: 1 credit = $0.001; read_url costs 2 credits and convert_file costs 3 per page. Credit packs start at $5 for 5,000 credits.
Option 1: remote (no install)
Streamable HTTP endpoint: https://agentreader.onrender.com/clearcrawl/mcp
Claude Code: claude mcp add --transport http clearcrawl https://agentreader.onrender.com/clearcrawl/mcp
For paid credits, add the header Authorization: Bearer <your key>.
Option 2: local stdio
The local mode can also convert files from your disk (convert_file with path).
Getting an API key
POST https://agentreader.onrender.com/v1/credits/checkout {"pack":"ar_pack_5"} returns a Stripe Checkout URL. Once you pay, the success page shows your key. Full docs: https://agentreader.onrender.com/llms.txt
Notes
- Clearcrawl runs on a free host, so the first call after it has been idle can take about a minute.
- Limits: public http(s) URLs only, 15 MB max, no JavaScript rendering or OCR yet.
MIT licensed (this client). The Clearcrawl API itself is a hosted service.
More from our studio: VibePicks · LinkPreflight
Pairs well with LinkPreflight, our sister brand: preflight a URL with LinkPreflight, then extract it with Clearcrawl.
Source: README.md at commit ec3db43
Tools
0Version history
1- v0.2.0LatestOct 16, 2026
Score
50% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
- Reached in the last 30 daysRequired25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
- Auth declaredRequired10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
- Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
- DescriptionRequired15 pts
- Logo10 pts
- Documentation15 pts
- License10 pts
Other Agentreader integrations
AgentReader
xyz.agentreaderOfficial publisher
AgentReader is a remote MCP server that reads web pages and PDFs and returns clean Markdown or JSON, plus web search, using prepaid credits.

Axiom Works AgentReader
Published by GitHub account grokbot1233
Pay-per-call x402 API server for web reading, company due diligence, official registries, and EVM on-chain lookups, billed in USDC on Base.

Agentreader Mcp
Published by GitHub account ajanani1
Local MCP server giving an assistant 13 pay-per-call web tools — page reading, PDF text, feeds, screenshots, extraction and sanctions screening — paid in USDC.