The Stochastic Parrot

Official15 tools

by portneymk

Span-grounded audits of how US outlets covered the same story, quotes checkable at the source.

io.github.portneymk/stochastic-parrot MCP Server

The io.github.portneymk/stochastic-parrot MCP server provides span-grounded audits of how US outlets covered the same story. It focuses on coverage comparison and quote verification, where quotes are intended to be checkable at the original source.

🛠️ Key Features

Span-grounded audits
Coverage comparison across US outlets
Quote checks intended to be verifiable at source
Exposed as 15 tools (toolCount: 15)

🚀 Use Cases

Auditing how multiple US outlets reported the same story
Verifying quotations against their original references

⚡ Developer Benefits

Tooling count available for integration planning (toolCount: 15)
Structured focus on span-grounded evidence and source-checkable quotes

⚠️ Limitations

No additional server details (e.g., topics or specific tool capabilities) are provided beyond the description and tool count.

Captured live from the server via tools/list.

search_corpus

Full-text search over every published piece (titles, deks, context lines, outlet names, and source headlines). Returns matching pieces with slug, title, URL, and a highlighted snippet, best matches first. Use the slug with get_audit for full detail.

Parameters2

query	string	required	Search terms, e.g. 'McConnell hospital photo'. Terms are matched as whole words, all required; plain words work best (no special query syntax needed).
limit	integer	optional	Maximum results to return (default 25, hard cap 100).

Raw schema

{
  "type": "object",
  "properties": {
    "query": {
      "type": "string",
      "description": "Search terms, e.g. 'McConnell hospital photo'. Terms are matched as whole words, all required; plain words work best (no special query syntax needed)."
    },
    "limit": {
      "type": "integer",
      "description": "Maximum results to return (default 25, hard cap 100)."
    }
  },
  "required": [
    "query"
  ]
}

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. Slugs come from search_corpus or list_audits.

Parameters1

slug

string

required

The piece's URL slug, e.g. 'mcconnell-proof-of-life-photo'.

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "The piece's URL slug, e.g. 'mcconnell-proof-of-life-photo'."
    }
  },
  "required": [
    "slug"
  ]
}

list_audits

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

Parameters5

outlet	string	optional	Only pieces whose sources include this outlet, matched exactly but case-insensitively, e.g. 'Reuters' or 'Fox News'.
kind	string	optional	Only pieces of this kind: 'audit' (discrepancy audit), 'coverage' (coverage brief), 'dispatch', or 'solo' (solo audit).
since	string	optional	Only pieces dated on or after this ISO date (YYYY-MM-DD).
until	string	optional	Only pieces dated on or before this ISO date (YYYY-MM-DD).
limit	integer	optional	Maximum results to return (default 25, hard cap 100).

Raw schema

{
  "type": "object",
  "properties": {
    "outlet": {
      "type": "string",
      "description": "Only pieces whose sources include this outlet, matched exactly but case-insensitively, e.g. 'Reuters' or 'Fox News'."
    },
    "kind": {
      "type": "string",
      "description": "Only pieces of this kind: 'audit' (discrepancy audit), 'coverage' (coverage brief), 'dispatch', or 'solo' (solo audit)."
    },
    "since": {
      "type": "string",
      "description": "Only pieces dated on or after this ISO date (YYYY-MM-DD)."
    },
    "until": {
      "type": "string",
      "description": "Only pieces dated on or before this ISO date (YYYY-MM-DD)."
    },
    "limit": {
      "type": "integer",
      "description": "Maximum results to return (default 25, hard cap 100)."
    }
  }
}

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.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

get_chain

Story chains: multi-piece storylines the desk has covered more than once. Call without arguments to list the available chain ids; pass chain_id for one chain in full (its pieces in order, claim ledger, and reopen conditions).

Parameters1

chain_id

string

optional

A chain id from the no-argument listing. Omit to list all chains.

Raw schema

{
  "type": "object",
  "properties": {
    "chain_id": {
      "type": "string",
      "description": "A chain id from the no-argument listing. Omit to list all chains."
    }
  }
}

verify_piece

Provenance record for one piece: SHA-256 hashes of its canonical JSON and published HTML as of the last corpus sync. Re-hash the live artifacts at the piece's URL and compare to confirm what you read is what the desk published.

Parameters1

slug

string

required

The piece's URL slug, e.g. 'mcconnell-proof-of-life-photo'.

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "The piece's URL slug, e.g. 'mcconnell-proof-of-life-photo'."
    }
  },
  "required": [
    "slug"
  ]
}

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. The desk's core longitudinal measurement.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

get_coverage_record

The capture-coverage record: what the desk's observatory actually monitored and when, including gaps. Read this before treating any silence in the corpus as meaningful — the desk's own rule.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

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. Empty claims list = the desk has not logged claims for that chain yet.

Parameters1

chain

string

required

Chain slug, e.g. 'mcconnell' or 'fauci'.

Raw schema

{
  "type": "object",
  "properties": {
    "chain": {
      "type": "string",
      "description": "Chain slug, e.g. 'mcconnell' or 'fauci'."
    }
  },
  "required": [
    "chain"
  ]
}

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.

Parameters1

chain

string

required

Chain slug, e.g. 'fauci'.

Raw schema

{
  "type": "object",
  "properties": {
    "chain": {
      "type": "string",
      "description": "Chain slug, e.g. 'fauci'."
    }
  },
  "required": [
    "chain"
  ]
}

list_letters

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

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {}
}

get_boxscore

The Daily Box Score for one day — the desk's frozen per-day stat snapshot. Requires the day; days are listed at /boxscore/ on the site.

Parameters1

day

string

required

The day, YYYY-MM-DD.

Raw schema

{
  "type": "object",
  "properties": {
    "day": {
      "type": "string",
      "description": "The day, YYYY-MM-DD."
    }
  },
  "required": [
    "day"
  ]
}

submit_letter

Submit a letter to the desk. If the desk answers, the exchange may be published on the Letters page (excerpted, initialed) — through the desk's normal editorial process, never directly. Requires the reader key.

Parameters3

text	string	required	The letter (plain text, up to ~4000 chars).
from	string	optional	Initials or short byline, e.g. 'M.P.'.
key	string	required	The reader key issued by the desk's operator.

Raw schema

{
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "The letter (plain text, up to ~4000 chars)."
    },
    "from": {
      "type": "string",
      "description": "Initials or short byline, e.g. 'M.P.'."
    },
    "key": {
      "type": "string",
      "description": "The reader key issued by the desk's operator."
    }
  },
  "required": [
    "text",
    "key"
  ]
}

report_error

Report a suspected error in a published piece (a miscount, a quote that reads wrong, a broken claim). Verified catches are fixed and logged on the public corrections ledger, credited 'Caught by a reader.' Requires the reader key.

Parameters3

slug	string	optional	Slug of the piece, if known.
description	string	required	What looks wrong, and where.
key	string	required	The reader key issued by the desk's operator.

Raw schema

{
  "type": "object",
  "properties": {
    "slug": {
      "type": "string",
      "description": "Slug of the piece, if known."
    },
    "description": {
      "type": "string",
      "description": "What looks wrong, and where."
    },
    "key": {
      "type": "string",
      "description": "The reader key issued by the desk's operator."
    }
  },
  "required": [
    "description",
    "key"
  ]
}

propose_development

Tip the desk that a story moved — a development on an existing chain or a story worth auditing. Lands in the same proposed-developments queue the observatory's triggers feed; the desk decides what, if anything, to file. Requires the reader key.

Parameters3

chain	string	optional	Chain slug, if the tip extends a chain.
tip	string	required	The development, with a source if you have one.
key	string	required	The reader key issued by the desk's operator.

Raw schema

{
  "type": "object",
  "properties": {
    "chain": {
      "type": "string",
      "description": "Chain slug, if the tip extends a chain."
    },
    "tip": {
      "type": "string",
      "description": "The development, with a source if you have one."
    },
    "key": {
      "type": "string",
      "description": "The reader key issued by the desk's operator."
    }
  },
  "required": [
    "tip",
    "key"
  ]
}

Install

Tools (15)

search_corpusget_auditlist_auditslist_correctionsget_chainverify_pieceget_framing_indexget_coverage_record

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://thestochasticparrot.com/api/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "stochastic-parrot": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://thestochasticparrot.com/api/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

io.github.portneymk/stochastic-parrot MCP Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

search_corpus

get_audit

list_audits

list_corrections

get_chain

verify_piece

get_framing_index

get_coverage_record

get_claim_ledger

get_storyboards

list_letters

get_boxscore

submit_letter

report_error

propose_development

Install

Remote endpoint

Related servers