The Stochastic Parrot is answering right now. Last checked 9 min ago. It exposes 16 tools.
Span-grounded audits of how US outlets covered the same story, quotes checkable at the source.
Uptime history
73 days of history · worst day 92%
73 days agonow
100.0%
Uptime 24h
91 of 91 checks
16
Tools
read from the server
342 ms
Response time
average over 24h
open, no key
Access
streamable-http
What changed 9
Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 3 October 2026. No other catalogue keeps this.
21 Oct
4 tools disappeared
editor_decide, editor_log, editor_pending and 1 more
21 Oct
a tool appeared
whats_new
3 Oct
4 tools appeared
editor_decide, editor_log, editor_pending and 1 more
The Stochastic Parrot missed 2 checks this week
Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.
Connect this server
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 9 min ago.
run in your terminal
claude mcp add stochastic-parrot --transport http https://thestochasticparrot.com/api/mcpSettings → Connectors → Add custom connector, then paste this address
https://thestochasticparrot.com/api/mcp~/.codex/config.toml
[mcp_servers.stochastic-parrot]
url = "https://thestochasticparrot.com/api/mcp".cursor/mcp.json
{
"mcpServers": {
"stochastic-parrot": {
"url": "https://thestochasticparrot.com/api/mcp"
}
}
}.vscode/mcp.json
{
"servers": {
"stochastic-parrot": {
"type": "http",
"url": "https://thestochasticparrot.com/api/mcp"
}
}
}Available tools 16
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
audit
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.
audits
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.
boxscore
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.
chain
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).
claim
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.
corpus
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.
corrections
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.
coverage
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.
framing
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.
letters
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
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
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.
storyboards
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.
submit
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
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.
whats
whats_new
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.
Tools removed
Tools this server used to expose. Anything built against them stopped working on the day they went.
editor_decide
removed 21 Oct 2026
editor_log
removed 21 Oct 2026
editor_pending
removed 21 Oct 2026
editor_sync
removed 21 Oct 2026
Endpoints
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://thestochasticparrot.com/api/mcp | streamable-http | answering | 381 ms | 9 min ago |
Alternatives to The Stochastic Parrot
same job, measured the same wayThinkPattern
by thinkpattern
Grounded, attributed news: what happened, which outlets reported it, and how many covered it.
C
Countersign
by llpro-countersign
Independent, signed check of AI work: math, quotes, sources, links, code. Public verifiable log.
Zaxy
by syndicalt
Event-sourced, auditable agent memory over MCP: cited checkout, replayable provenance.
Site
by backgroundcheckquotes
Background Check Quotes: the site's own MCP server — dataset, enquiry (enquiry = a human...
HORIZON SHIELD: construction and renovation estimate auditor
by ogasurfproject-jpg
Fair-price checks for Japanese renovation quotes, with sources and recomputable records.
Studydiff
by nickjlamb
Explain why two scientific papers disagree, every claim grounded in a verbatim source quote.
quotecheck
by feenmile
Check that a quoted passage appears word for word in its cited source (URL, DOI or PubMed ID).
Chet
by meetchet
Contractor quotes for US homeowners: start a request, see cost ranges with their sources.
The Stochastic Parrot — questions
Answers built from our own checks of this server.
What can The Stochastic Parrot do?
It exposes 16 tools, read directly from the server on our last check. Among them: get_audit, get_boxscore, get_chain, get_claim_ledger, get_coverage_record, get_framing_index and 10 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README.
How MCP servers expose tools in the first place →
Is The Stochastic Parrot working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 342 ms. The bar chart above shows every period we have measured.
Did The Stochastic Parrot ever remove tools?
Yes. editor_decide, editor_log, editor_pending, editor_sync are no longer exposed — we recorded the date each one disappeared. A tool vanishing usually means a breaking change for anything that depended on it.
How do I connect The Stochastic Parrot?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does The Stochastic Parrot need an API key?
No. The Stochastic Parrot completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 16 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is The Stochastic Parrot?
It answers our handshake in 342 ms on average, which is faster than 41% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.