# The Stochastic Parrot

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

- name: io.github.portneymk/stochastic-parrot
- version: 1.1.0
- connection class: R0 (autonomous)
- trust: 76/100 flags: no-repository
- quality: 79/100 (good)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.portneymk%2Fstochastic-parrot
- tools: https://api.protogrid.dev/v1/servers/io.github.portneymk%2Fstochastic-parrot/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

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


## Trust

- hygiene: 80
- liveness: 99
- freshness: 85
- provenance: 45
- drivers: +website +reachable +uptime-98% ~updated-53d-ago -no-repository
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 79/100 (good)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-06-18; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 71 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: verify_piece (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); editor_log (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); search_corpus (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); …
- pass `tools.token_cost`: about 2,010 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 4 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 19, about 2,010 tokens to load them all
- tool set hash: 3d127a4c4b6ceae8eedeabe00d91cffb
- tools last changed: 2026-10-04T01:07:53.256Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.portneymk/stochastic-parrot.svg)](https://protogrid.dev/servers/io.github.portneymk/stochastic-parrot)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-04 `editor_sync` added
  - Internal: the desk's mirror sync (push cards + ledger, read back all cards, clear ids). Not for conversational use.
- 2026-10-03 `editor_log` added
  - What the site editor did recently: its ledger of small changes it shipped on its own, cards it filed, and decisions recorded. Use to answer 'what did the editor change'. Requires the editor key.
- 2026-10-03 `editor_decide` added
  - Record Mike's decision on one editor card: approve (the editor executes it next cycle), hold (keep it, not now), or kill (never pitch it again). Only call this when the user has explicitly decided; never infer a decision. Requires the editor key.
- 2026-10-03 `editor_pending` added
  - The site editor's pitch cards waiting for Mike's decision. Each card is one proposed change to thestochasticparrot.com that the editor judged too big to make on its own. Returns the cards; the attached widget lets the user decide each with Approve / Hold / Kill. Requires the editor key.

Full history: https://api.protogrid.dev/v1/servers/io.github.portneymk%2Fstochastic-parrot/changes

## Remotes

- https://thestochasticparrot.com/api/mcp (streamable-http, auth none, reachable true, uptime30d 0.9830508)

## Packages

_none_

## Tools (19)

- `editor_decide`: Record Mike's decision on one editor card: approve (the editor executes it next cycle), hold (keep it, not now), or kill (never pitch it again). Only call this when the user has explicitly decided; never infer a decision. Requires the editor key.
- `editor_log`: What the site editor did recently: its ledger of small changes it shipped on its own, cards it filed, and decisions recorded. Use to answer 'what did the editor change'. Requires the editor key.
- `editor_pending`: The site editor's pitch cards waiting for Mike's decision. Each card is one proposed change to thestochasticparrot.com that the editor judged too big to make on its own. Returns the cards; the attached widget lets the user decide each with Approve / Hold / Kill. Requires the editor key.
- `editor_sync`: Internal: the desk's mirror sync (push cards + ledger, read back all cards, clear ids). Not for conversational use.
- `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.
- `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.
- `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).
- `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.
- `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.
- `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.
- `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.
- `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.
- `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.
- `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.
- `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.
- `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.
- `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.
- `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.
- `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.