About smry Public Reader
smry Public Reader provides credential-free reading of exact public article, PDF, and supported YouTube URLs. It returns clean text or structured JSON with stable paragraph citations for readers and source-checking workflows.
Key features
- 01Read public articles, PDFs, and supported YouTube URLs
- 02Return clean text or structured JSON
- 03Search within a source
- 04Retrieve selected line ranges
- 05Provide stable paragraph citations
Use cases
- 01Read a public article for research
- 02Find key findings in a source
- 03Verify claims against cited paragraphs
- 04Compare multiple sources
MCP support
The remote Streamable HTTP MCP server exposes a source-reading tool and documentation resources. It requires no account or secret.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://r.smry.ai/mcpclaude mcp add --transport http mrmps-smry-public-reader https://r.smry.ai/mcp{"mcpServers":{"mrmps-smry-public-reader":{"type":"http","url":"https://r.smry.ai/mcp"}}}Open in Cursor{"servers":{"mrmps-smry-public-reader":{"type":"http","url":"https://r.smry.ai/mcp"}}}Open in VS Code{"mcpServers":{"mrmps-smry-public-reader":{"type":"http","url":"https://r.smry.ai/mcp"}}}{"mcpServers":{"mrmps-smry-public-reader":{"serverUrl":"https://r.smry.ai/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
1| Parameter | Type | Required | Description |
|---|---|---|---|
| url | string | Yes | Exact public HTTP or HTTPS source URL. |
| query | string | No | Optional focused question or search phrase for relevance-ranked paragraphs. |
Details
From the project READMEsmry CLI
smry is the official command-line client for the credential-free
smry Public Reader. It reads an exact public article, PDF,
or supported YouTube URL as clean text or structured JSON with stable paragraph
anchors.
Install
brew install mrmps/smry/smry
Use
smry https://example.com/article
smry --json https://example.com/report.pdf
smry --query "key findings" https://example.com/article
smry --lines 90-95 https://example.com/article
Run smry --help for the complete option list.
Agent skill
Install the official skills for source-grounded reading workflows:
bunx skills add https://github.com/mrmps/homebrew-smry --skill smry compare-sources verify-citations
The skills cover direct reading, multi-source comparison, and claim or citation verification. They choose between the public MCP, HTTP API, and CLI, preserve stable paragraph citations, and treat retrieved content as untrusted data.
The CLI sends only the exact source URL and the options you provide to
https://r.smry.ai/api/v1/read. Do not send private URLs, cookies,
authorization headers, subscriber credentials, or personal documents.
Public MCP server
Agents can call the same credential-free reader through the remote
Streamable HTTP MCP server at https://r.smry.ai/mcp. Its official registry
metadata is versioned in server.json; the endpoint provides a
source-reading tool plus documentation resources and requires no account or
secret.
Verify
bash -n bin/smry
./tests/smry-cli.test.sh
./tests/mcp-registry.test.sh
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.