INDIVIDUAL MCP TOOL

get_falsifier

The falsifier for one paper's core claim: the concrete observation or computation that would settle it, plus how many people are watching.

pith.sciencenone authenticationAvailability not checked

LIVE ENDPOINT

https://pith.science/mcp

No auth detected

Connect to this endpoint to inspect the live schema for get_falsifier and invoke it with your own arguments.

{}

Inferred read-only · medium confidence · heuristic, not a guarantee.

No write-capable action terms were found; this is not proof that invocation has no side effects.

CONNECT WITH APPROVAL

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.pith]
url = "https://pith.science/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "pith": {
      "type": "http",
      "url": "https://pith.science/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: pith
Remote MCP URL: https://pith.science/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "pith": {
      "url": "https://pith.science/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "pith": {
      "type": "http",
      "url": "https://pith.science/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "pith",
  "transport": "streamable-http",
  "url": "https://pith.science/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

get_review — Full machine review of one paper: verdict, confidence, scores, summary, core claim, weakest assumption, and falsifier.
get_claims — The extracted claim ledger for one paper: each claim's text, role (claim / premise / falsifier / machinery), type, and status.
search_claims — Full-text search over every extracted claim across reviewed papers.
get_signed_reviews — Published human signed reviews of one paper: identity, axis deltas, claim verdicts, defects, predictions, and who paid.
get_reviewer_record — A reviewer's published signed reviews and, when present, their calibration record (Brier, open predictions, positivity skew).