stochastic-parrot

endpoint

https://thestochasticparrot.com/api/mcp

protocol

streamable-http ·2025-06-18

authentication

none observed

public key

none — nobody has proven they own this listing · is it yours? claim it

karma

0 · newcomer

Is stochastic-parrot live?

Yes — it answered the hub's last check (checked 2h ago). It answered 99% of checks over the last 30 days.

Is stochastic-parrot free to use?

Yes — the hub reached it with no key and no payment.

What tools does stochastic-parrot have?

16 tools: verify_piece, submit_letter, whats_new, get_claim_ledger, report_error, search_corpus, propose_development, get_boxscore, ….

Is stochastic-parrot safe to connect?

The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.

Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.

• get_framing_index reads open 2h ago

  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.

  mcp-tool

  1234

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

  arguments 4 lines copy
• list_audits reads open 16h ago

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

  mcp-tool

  12345678910111213141516171819202122232425

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

  arguments 25 lines copy
• list_letters reads open 16h ago

  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.

  mcp-tool

  1234

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

  arguments 4 lines copy
• get_coverage_record reads open 2h ago

  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.

  mcp-tool

  1234

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

  arguments 4 lines copy
• list_corrections reads open 16h ago

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

  mcp-tool

  1234

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

  arguments 4 lines copy
• get_chain reads open 2h ago

  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).

  mcp-tool

  123456789

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

  arguments 9 lines copy
• verify_piece reads unknown never probed

  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.

  mcp-tool

  123456789101112

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

  arguments 12 lines copy
• submit_letter changes data unknown never probed

  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.

  mcp-tool

  123456789101112131415161718192021

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

  arguments 21 lines copy
• whats_new unknown never probed

  The desk's change window: the 20 most recently published pieces, newest first, with the desk's own dek, its computed split counts, and the story-chain ids each piece belongs to. This is the cheap 'what moved since I last looked' call — a few KB, not the multi-megabyte /feed.json — so a scheduled agent can poll it safely. Filter by date, kind, or chain. For anything older than the window, use list_audits with a date range.

  mcp-tool

  12345678910111213141516171819202122

  {
    "type": "object",
    "required": [],
    "properties": {
      "kind": {
        "type": "string",
        "description": "Only pieces of this kind: 'audit', 'coverage', 'dispatch', or 'solo'."
      },
      "chain": {
        "type": "string",
        "description": "Only pieces belonging to this story chain, by chain id (e.g. 'mcconnell'). Chain ids come from get_chain with no arguments."
      },
      "limit": {
        "type": "integer",
        "description": "Maximum items to return (default and ceiling: 20, the whole window)."
      },
      "since": {
        "type": "string",
        "description": "Only pieces dated on or after this day (YYYY-MM-DD). If it predates the window, the result says so in `truncated` rather than implying the corpus starts there."
      }
    }
  }

  arguments 22 lines copy
• get_claim_ledger reads unknown never probed

  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.

  mcp-tool

  123456789101112

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

  arguments 12 lines copy
• report_error changes data unknown never probed

  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.

  mcp-tool

  123456789101112131415161718192021

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

  arguments 21 lines copy
• search_corpus reads unknown 12h ago

  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.

  mcp-tool

  12345678910111213141516

  {
    "type": "object",
    "required": [
      "query"
    ],
    "properties": {
      "limit": {
        "type": "integer",
        "description": "Maximum results to return (default 25, hard cap 100)."
      },
      "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)."
      }
    }
  }

  arguments 16 lines copy
• propose_development changes data unknown never probed

  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.

  mcp-tool

  123456789101112131415161718192021

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

  arguments 21 lines copy
• get_boxscore reads unknown 12h ago

  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.

  mcp-tool

  123456789101112

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

  arguments 12 lines copy
• get_audit reads unknown 12h ago

  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.

  mcp-tool

  123456789101112

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

  arguments 12 lines copy
• get_storyboards reads unknown 9h ago

  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.

  mcp-tool

  123456789101112

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

  arguments 12 lines copy

Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.

0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.