Skip to main content
Glama
Second Read

Second Read

Second Read

Second Read reviews a draft the way a careful editor would, and shows its sources. You give it an article, a blog post or a design doc. It returns one report:

  • Facts checked against the web. Each claim is looked up, and every "this is wrong" comes with the page that says so.

  • The strongest counter-case. A devil's advocate builds the best argument against your piece from sources it retrieves.

  • Copy edits. Grammar and clarity fixes that keep your voice.

  • Originality notes. Sentences that closely match text found online.

It runs as an MCP server with one tool, review_document, so you can ask for a review from Claude Code or Claude Desktop. It also has a command-line tool. It runs on your machine with your own API keys; nothing is sent to the author of this project.

A finding looks like this:

Factual error — "Mjällby clinched the title on 20 October 2025 by winning 2-0 at IFK Göteborg, with two games to spare"

The date, the 2-0 score and the opponent are confirmed. ESPN and Flashscore both say three rounds were left (27 of 30 played), so "two games to spare" is wrong.

What you need

  • uv (it installs Python 3.12 for you).

  • An Anthropic API key: ANTHROPIC_API_KEY.

  • A Tavily search key: TAVILY_API_KEY.

Getting your keys

You need two keys. Each takes a couple of minutes: sign up, create a key, copy it.

Key

Where to get it

ANTHROPIC_API_KEY

Sign in at https://platform.claude.com, add credit under Billing, then create a key under API keys (https://platform.claude.com/settings/keys)

TAVILY_API_KEY

Sign up at https://app.tavily.com; the key is shown on the dashboard

The Anthropic key is pay-as-you-go: reviews fail with a clear message if the account has no credit. Keep keys out of chats and out of version control; put them in the MCP client's env block or in a .env file as shown below.

A review of a 700-word article takes about two minutes and uses roughly 150,000–180,000 tokens on your model key (about $0.60–$1.20 at Anthropic's list prices in October 2026) plus about 30 searches.

Related MCP server: footnote

Install: Claude Code

claude mcp add second-read \
  -e ANTHROPIC_API_KEY=your-key \
  -e TAVILY_API_KEY=your-key \
  -- uvx second-read

Start Claude Code with a longer tool timeout, because a review takes minutes:

MCP_TOOL_TIMEOUT=600000 claude

Then ask: "Use second-read to review this draft", and paste the text or give a public URL.

Install: Claude Desktop

Add this to claude_desktop_config.json (on macOS: ~/Library/Application Support/Claude/claude_desktop_config.json), then restart the app. If Claude Desktop cannot find uvx, use its full path (which uvx).

{
  "mcpServers": {
    "second-read": {
      "command": "uvx",
      "args": ["second-read"],
      "env": {
        "ANTHROPIC_API_KEY": "your-key",
        "TAVILY_API_KEY": "your-key"
      }
    }
  }
}

To try it without keys, replace the env block with {"SECONDREAD_FAKE": "1"}. Demo mode returns placeholder findings and makes no model calls.

Install: other MCP clients

Any client that runs local (stdio) MCP servers can use the same command. For Cursor, VS Code and similar, add a server named second-read that runs uvx second-read with ANTHROPIC_API_KEY and TAVILY_API_KEY in its environment, as in the Claude Desktop example above.

Second Read is listed in the official MCP Registry as io.github.sbanthia92/second-read, so clients and directories that read the registry can find it.

ChatGPT and claude.ai on the web connect only to remote (hosted) MCP servers, so they cannot run Second Read yet. A hosted version is on the roadmap.

Command line

export ANTHROPIC_API_KEY=your-key TAVILY_API_KEY=your-key
uvx --from second-read secondread review path/to/draft.md --profile opinion > report.md

Or keep the keys in a .env file and pass it with --env-file path/to/.env.

Progress prints to the terminal; the report goes to report.md. Use --profile design_doc for technical design docs, or leave the profile out to let the tool decide. A URL works in place of a file path.

The tool

review_document takes:

Argument

Required

Notes

content

one of content / url

The draft as text or markdown (up to 20,000 words)

url

one of content / url

A public web page to fetch and review

profile

no

auto (default), opinion or design_doc

focus

no

A steer, e.g. "check the financial figures"

It returns the report as markdown and sends progress updates while it works.

The report has these sections: a verdict line; Must fix (factual errors and claims the sources do not back); Could not verify (claims it found no adequate source for, which is not the same as wrong); Strongest counter-case; Should fix (structure); Polish (copy edits); Originality notes; and an appendix listing every claim with its verdict and sources.

Settings

Set these in the MCP client's env block, in the environment, or in a .env file (the server reads .env from its working directory, or the file named by SECONDREAD_ENV_FILE).

Variable

Purpose

ANTHROPIC_API_KEY

Anthropic model key

TAVILY_API_KEY

Web search key

SECONDREAD_MODEL_CHEAP, _MID, _STRONG

Override the model used for each tier

SECONDREAD_MAX_WORDS

Document size cap (default 20000)

SECONDREAD_FAKE=1

Demo mode: no keys, no model calls

Privacy

Second Read runs on your machine. The project's author runs no server and receives no data.

  • What it collects. Nothing is collected by the project. To do a review the tool handles the document you give it and the web pages it retrieves.

  • What leaves your machine, and where.

    • Your document goes to Anthropic, under your key and their terms.

    • Search queries built from your document's claims, and up to eight sentences quoted exactly for the originality check, go to Tavily, under your key and their terms.

    • Web pages named in search results are fetched directly from your machine. The fetcher refuses private and local network addresses.

  • Storage and retention. Nothing is stored after the review finishes. The report is returned to your client and is not kept by Second Read. Logs go to your terminal and never contain keys or document text.

  • Sharing. Nothing is shared with anyone else. The only third parties are the model and search providers above, which you choose by supplying their keys.

  • Keys. Read from your environment or a .env file you control, and never logged.

  • Contact. Questions or concerns: open an issue at https://github.com/sbanthia92/second-read/issues. For security problems see SECURITY.md.

How well it works

What was tested. Four articles written for the test, each with errors planted in it that cannot be settled from memory (recent results, exact figures): 19 planted wrong facts in all. Every planted error has an answer key recording the exact sentence and the true value. Each article was reviewed once by two setups:

  • Single prompt: one request to the model Second Read uses for its strongest tier, "review this and argue the other side". No web search, so it cannot look anything up or cite a page.

  • Second Read: the full review described below, with web search.

What "caught" means. The report has a factual-error finding on the sentence that holds the planted error. A "could not verify" note does not count, so a careful miss scores as a miss. "Rebutted" means a counter-argument was written against a deliberately weak argument; "caught" for borrowed sentences means an originality note on the copied sentence.

Single prompt

Second Read

Planted wrong facts caught (of 19)

7

13

...of those, with a cited source

0

13

Weak arguments rebutted (of 4)

2

4

Borrowed sentences caught (of 3)

3

1

Tokens per article

about 5,000

about 136,000

Reading the result. Second Read earns its cost on claims that need looking up: recent events, exact figures, and details a model cannot know from memory. The gain appears to come mainly from searching and reading sources, though this test did not separate that from the other design choices. Every finding names its source so you can check it in one click. It is slower, uses about 27 times the tokens, and did worse on borrowed sentences.

Limits of this test. It is small: 19 errors, one run each, so each error is worth about five points and the exact percentages are rough. It does not measure false alarms (true facts wrongly called wrong) for either setup. It does not say which of the six misses were careful "could not verify" results and which were missed outright. A larger run (all 40 documents, three runs each) is on the roadmap.

Getting the most from it:

  • Open the cited source before acting on a "factual error". The report links the page and quotes the passage it relied on.

  • Search results change, so two runs on the same draft can differ slightly.

  • The originality check is a heuristic: it flags close matches found online.

  • Sources are web pages; PDFs are not read.

How it works

An orchestrator runs specialist agents and settles their disagreements:

  1. A claim extractor splits the document into its thesis, supporting claims and checkable facts.

  2. In parallel: a fact-checker researches each fact in a bounded loop (search, fetch, read, assess; at most three rounds per claim); a devil's advocate gathers counter-evidence; a copy editor; for articles, an originality checker; and, for design docs, a structure reviewer.

  3. A reaction round: a verified fact the devil's advocate disputes is re-checked, and the two argue once over the most important disagreements.

  4. Fixed rules settle what is left (for example, a grammar fix on a sentence flagged as wrong is dropped), findings are ranked, and the report is written.

ARCHITECTURE.md describes how the system is built, the decisions behind it and their trade-offs, the planned hosted service, and the shared types.

Development

uv sync
uv run ruff check . && uv run ruff format --check . && uv run mypy && uv run pytest

Tests run offline with fakes. Tests that call real providers are marked live and skipped by default (uv run pytest -m live). The evaluation harness and its 40 seeded documents are in eval/ (see eval/README.md); running it against real providers spends money on your keys.

Status

The local MCP server and command-line tool work. A hosted version (sign in, add a key once, get the report by email) is designed in ARCHITECTURE.md but not built. ROADMAP.md lists what comes next.

License

MIT. See LICENSE.

Available Tools

1 tool
review_documentReview a documentA
Read-only

Review a document draft with a desk of specialist agents: a fact-checker that cites sources, a devil's advocate that builds the strongest counter-case, a structure reviewer, a copy editor and an originality check. Returns a markdown report (must fix, counter-case, should fix, polish, originality notes, claim ledger). Pass exactly one of content (the text or markdown) or url (a public page). Reviews take a few minutes.

Inputs: url, focus, content, profile.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.4/5.0

    Scored across 1 tool

    Disambiguation5/5

    With a single tool there is no possibility of misselection; the tool's purpose (multi-perspective document review) is stated explicitly and unambiguously. The input contract (exactly one of `content` or `url`) and the report shape are spelled out, leaving no room for a competing interpretation.

    Naming Consistency5/5

    `review_document` follows a clean verb_noun snake_case pattern that describes exactly what it does. There are no other names to clash with or deviate from.

    Tool Count3/5

    A one-tool server is inherently thin against the 3-15 sweet spot, even though the single tool internally bundles several specialist reviewers. It works as a focused capability, but there is no granularity — you cannot invoke just the fact-checker or just the copy editor.

    Completeness4/5

    The tool covers the core end-to-end review workflow (fact-check, counter-case, structure, copy edit, originality) and returns a structured markdown report, so the primary job is done. Minor gaps exist: no way to re-run a targeted subset of reviewers, iterate on a revised draft, compare versions, or retrieve a past report.

    Maintenance

    ActivityMaintained
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      Provides Claude Code with local-first multimodal semantic search across documents, code, images, and video, plus multi-engine web research with active counter-evidence hunting and source-verified, extract-only briefings.
      4
      AGPL 3.0
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables agents to verify their own output mid-task by checking every claim against provided sources, returning supported, partial, unsupported, or contradicted verdicts with exact citations.
      MIT
    • A
      license
      A
      quality
      C
      maintenance
      Enables pre-submission review of ML papers inside Claude Code or Claude Desktop by checking format and anonymization risks, resolving every reference, finding prior work for each claim, verifying quotes against the PDF, and running methodology and writing checks. It reports findings only, never scores, ratings, or accept/reject verdicts, and never rewrites the author's text.
      7
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables agents to verify manuscript references against public scholarly records, checking that cited works exist, match their citations, and have not been retracted or flagged. It also lets an agent gather the best source passages for each citing sentence and record its own claim-support verdicts back into the report.
      4
      MIT