Agents Index

Pith

OnlineOfficial

Reviews of arXiv papers for AI agents: verdicts, claims, flaws, compiled records, citation graphs.

Visit publisherConnectJSON

What it can do: 24 tools

  • get_review read-onlyPith's review of one specific paper, in one call: the verdict, confidence, novelty and correctness scores, one-line summary, weakest assumption, and the paper's argument as short labeled statements (premise,
  • search_papers read-onlySearch Pith-reviewed papers by title and abstract. Call this when the user names a research topic, phenomenon, method, or paper title without an identifier, or asks whether Pith has reviewed anything on a subject
  • latest_reviews read-onlyThe papers Pith reviewed most recently, newest first. Call this when the user asks what is new, notable, or recently reviewed in a field or overall. days caps how far back to look (max 90).
  • analyze_paper_claims read-onlyThe structured argument of one specific paper: what it actually asserts, the premises it assumes, the machinery connecting those premises to the claim, and the falsifier, as short labeled statements in argume
  • get_claims read-onlyAlias of analyze_paper_claims: the same ledger of what the paper asserts, its premises, machinery, and falsifier, in argument order.
  • search_claims read-onlyFull-text search over every scientific claim Pith has extracted, across all reviewed papers. Call this when the user asks who claims something, whether a claim appears in the recent literature, or what eviden
  • get_paper_falsifier read-onlyThe falsifier for one specific paper's core claim: the concrete observation, experiment, or computation that would settle or disprove it, plus how many people are watching for that result. Use this when the u
  • get_falsifier read-onlyAlias of get_paper_falsifier: the same falsifier and watcher count.
  • get_signed_reviews read-onlyPublished human signed reviews of one paper: reviewer identity, axis deltas against the machine review, claim verdicts, defects, predictions, and who paid. Call this when the user asks what human experts said abo
  • get_reviewer_record read-onlyA reviewer's published signed reviews and, when present, their calibration record (Brier score, open predictions, positivity skew). Call this when the user asks about a named Pith reviewer or how trustworthy
  • get_record read-onlyThe compiled record of one paper: the authors' own sentences, arranged with typed labels. It carries the main claim in the authors' words, each abstract sentence's role, results with the qualifications the author
  • resolve_paper read-onlyTurn a pasted arXiv id, arXiv URL, DOI, or Pith Number into the arXiv id the other tools key on. ``resolved`` is false when the input did not become an arXiv id.
  • paper_packet read-onlyOne paper's compiled record, small enough to hold beside others: the main claim and contribution in the authors' words, each abstract sentence with its role and probability, paper-level labels, and, for full-
  • citation_neighbors read-onlyOne hop from a paper: every reference entry with its resolved work identity, the papers that cite it, and, where a record exists, the citing sentences with their labeled intent. An edge means the paper names
  • paper_bridge read-onlyWhether either paper cites the other, the resolved works both cite (on or off arXiv), and the papers that cite both.
  • paper_connections read-onlyWhat other arXiv papers do with this paper, and what it does with the arXiv papers it cites: builds on, uses the method or tool, uses the data, compares with, cites as support or background, or contests. Each gro
  • check_claim read-onlyWhich arXiv papers support a scientific statement, which contradict it, and which study it without deciding, each with the paper's own main claim quoted and the classifier's probability. Call this before assertin
  • verify_citation read-onlyWhether the cited paper's own sentences support what a sentence attributes to it: supports, partly supports (a condition is missing), contradicts, or not addressed, with the single best sentence from the pape
  • find_passages read-onlyAuthor sentences the classifier labeled with one role, across every stored record, each with its probability and paper. Abstract-tier records cover limitation, result and main_claim; full-text records add con
  • record_coverage read-onlySources read and levels run for one paper's record, or the number of stored records by tier. Call before treating an empty result as a finding: an empty list means nothing in the examined scope matched.
  • my_citations read-onlyFor the papers claimed on the account behind your key: how many papers cite each, whether they cite it as support, extension or disagreement, and the citing sentence quoted. Call when the user asks who is bui
  • my_reviews read-onlyPith's machine review verdict and the count of published signed human reviews for each paper claimed on the account behind your key. Needs a personal key.
  • check_my_draft read-onlyResolve each reference in a draft, flag retracted works, and for arXiv papers show how later papers cite them: as support, and whether any contest them, with the contesting sentence quoted. Call before a subm
  • ask_field read-onlyRead the papers closest to a question and return, for each, whether its own abstract sentences answer yes, no or not addressed, with the deciding sentence quoted. Call when a user asks whether something holds acr

Connect it

Claude Code
claude mcp add --transport http pith https://pith.science/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://pith.science/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "pith": {
      "url": "https://pith.science/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "pith": {
      "type": "http",
      "url": "https://pith.science/mcp"
    }
  }
}

Questions

What does Pith do?

Reviews of arXiv papers for AI agents: verdicts, claims, flaws, compiled records, citation graphs. It exposes 24 tools to AI assistants.

What tools does Pith provide?

24 tools, including get_review, search_papers, latest_reviews, analyze_paper_claims, get_claims, search_claims, get_paper_falsifier, get_falsifier, get_signed_reviews, get_reviewer_record, get_record, resolve_paper….

How do I connect Pith to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://pith.science/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does Pith require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is Pith online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes Pith?

pith.science. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Research & Knowledge