Content Tools

thestochasticparrot.com

Provides search and retrieval of media fact-checking audits, corrections, and story chains.

1 endpoint15 known toolsFirst detected August 25, 2026Last detected August 29, 2026

ENDPOINT 1

https://thestochasticparrot.com/api/mcp

No auth detected

MCP server metadata

Name: stochastic-parrot
Version: 1.1.0

Capabilities

tools

Server instructions

The Stochastic Parrot (thestochasticparrot.com) is an automated media-criticism desk. This server exposes its corpus: span-grounded contradiction audits of how multiple news outlets covered the same event (every claimed contradiction anchored to two verbatim source quotes), a public corrections ledger, story chains that track multi-piece storylines over time, and a rhetoric league of language-feature rates. Use search_corpus or list_audits to find pieces, get_audit for a piece's full detail JSON, and verify_piece for the provenance hashes of its published artifacts. v1.1 adds the rest of the desk's data surface — the framing index, the capture-coverage record, per-chain claim ledgers and newsroom storyboards, the letters page, daily box scores — and three write tools (submit_letter, report_error, propose_development) that file into the desk's review queue. Nothing submitted is ever published directly: every submission goes through the desk's normal editorial gates, and the write tools require a reader key.

Known tools 15

search_corpus

Full-text search over every published piece (titles, deks, context lines, outlet names, and source headlines).

Inferred read-only

get_audit

Fetch one piece's full detail JSON by slug: headline, kind, date, context, dek, outlets, verified contradictions with verbatim spans, naming/framing splits, and the full source list.

Inferred read-only

list_audits

List published pieces (summaries: slug, title, kind, date, counts of hard contradictions and naming/framing splits), newest first.

Inferred read-only

list_corrections

The desk's public corrections ledger: every logged error on a published piece — what was wrong, what changed, and when — in original ledger order.

Inferred read-only

get_chain

Story chains: multi-piece storylines the desk has covered more than once.

Inferred read-only

verify_piece

Provenance record for one piece: SHA-256 hashes of its canonical JSON and published HTML as of the last corpus sync.

Inferred read-only

get_framing_index

The Framing Index: across the cross-outlet corpus, how often disagreements between outlets are hard contradictions vs naming/framing splits — totals, rate, monthly trend, per-outlet appearances.

Inferred read-only

get_coverage_record

The capture-coverage record: what the desk's observatory actually monitored and when, including gaps.

Inferred read-only

get_claim_ledger

A story chain's claim ledger: specific verbatim claims outlets made, each tracked through states (open, corroborated, contradicted, corrected, quietly_abandoned, resolved) with a receipt for every transition.

Inferred read-only

get_storyboards

A chain's per-newsroom storyboards: for each outlet, every piece it filed on the story entry-by-entry, the desk's published READ of what each piece was built to do (objective label, motive with its mandatory innocent read, confidence), the label arc, and the desk's 'story, as built' synthesis where one exists.

Inferred read-only

list_letters

Letters to the Desk: reader mail, excerpted and initialed, with the desk's replies in its own voice.

Inferred read-only

get_boxscore

The Daily Box Score for one day — the desk's frozen per-day stat snapshot.

Inferred read-only

submit_letter

Submit a letter to the desk.

Inferred read-only

report_error

Report a suspected error in a published piece (a miscount, a quote that reads wrong, a broken claim).

Inferred read-only

propose_development

Tip the desk that a story moved — a development on an existing chain or a story worth auditing.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

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

Codex

~/.codex/config.toml

[mcp_servers.stochastic-parrot]
url = "https://thestochasticparrot.com/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "stochastic-parrot": {
      "type": "http",
      "url": "https://thestochasticparrot.com/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: stochastic-parrot
Remote MCP URL: https://thestochasticparrot.com/api/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": {
    "stochastic-parrot": {
      "url": "https://thestochasticparrot.com/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "stochastic-parrot": {
      "type": "http",
      "url": "https://thestochasticparrot.com/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "stochastic-parrot",
  "transport": "streamable-http",
  "url": "https://thestochasticparrot.com/api/mcp"
}

MCP Inspector

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

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.