Span-grounded audits of how US outlets covered the same story, quotes checkable at the source.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
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.
The piece's URL slug, e.g. 'mcconnell-proof-of-life-photo'.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
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.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The piece's URL slug, e.g. 'mcconnell-proof-of-life-photo'. |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "The piece's URL slug, e.g. 'mcconnell-proof-of-life-photo'."
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| day* | string | The day, YYYY-MM-DD. |
{
"type": "object",
"required": [
"day"
],
"properties": {
"day": {
"type": "string",
"description": "The day, YYYY-MM-DD."
}
}
}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).
| Argument | Type | Description |
|---|---|---|
| chain_id | string | A chain id from the no-argument listing. Omit to list all chains. |
{
"type": "object",
"properties": {
"chain_id": {
"type": "string",
"description": "A chain id from the no-argument listing. Omit to list all chains."
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| chain* | string | Chain slug, e.g. 'mcconnell' or 'fauci'. |
{
"type": "object",
"required": [
"chain"
],
"properties": {
"chain": {
"type": "string",
"description": "Chain slug, e.g. 'mcconnell' or 'fauci'."
}
}
}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.
No arguments.
{
"type": "object",
"properties": {}
}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.
No arguments.
{
"type": "object",
"properties": {}
}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.
| Argument | Type | Description |
|---|---|---|
| chain* | string | Chain slug, e.g. 'fauci'. |
{
"type": "object",
"required": [
"chain"
],
"properties": {
"chain": {
"type": "string",
"description": "Chain slug, e.g. 'fauci'."
}
}
}List published pieces (summaries: slug, title, kind, date, counts of hard contradictions and naming/framing splits), newest first. All filters optional and combinable.
| Argument | Type | Description |
|---|---|---|
| kind | string | Only pieces of this kind: 'audit' (discrepancy audit), 'coverage' (coverage brief), 'dispatch', or 'solo' (solo audit). |
| limit | integer | Maximum results to return (default 25, hard cap 100). |
| since | string | Only pieces dated on or after this ISO date (YYYY-MM-DD). |
| until | string | Only pieces dated on or before this ISO date (YYYY-MM-DD). |
| outlet | string | Only pieces whose sources include this outlet, matched exactly but case-insensitively, e.g. 'Reuters' or 'Fox News'. |
{
"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'."
}
}
}The desk's public corrections ledger: every logged error on a published piece — what was wrong, what changed, and when — in original ledger order.
No arguments.
{
"type": "object",
"properties": {}
}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.
No arguments.
{
"type": "object",
"properties": {}
}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.
| Argument | Type | Description |
|---|---|---|
| key* | string | The reader key issued by the desk's operator. |
| tip* | string | The development, with a source if you have one. |
| chain | string | Chain slug, if the tip extends a chain. |
{
"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."
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| key* | string | The reader key issued by the desk's operator. |
| slug | string | Slug of the piece, if known. |
| description* | string | What looks wrong, and where. |
{
"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."
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| limit | integer | Maximum results to return (default 25, hard cap 100). |
| query* | string | Search terms, e.g. 'McConnell hospital photo'. Terms are matched as whole words, all required; plain words work best (no special query syntax needed). |
{
"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)."
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| key* | string | The reader key issued by the desk's operator. |
| from | string | Initials or short byline, e.g. 'M.P.'. |
| text* | string | The letter (plain text, up to ~4000 chars). |
{
"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)."
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| slug* | string | The piece's URL slug, e.g. 'mcconnell-proof-of-life-photo'. |
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"description": "The piece's URL slug, e.g. 'mcconnell-proof-of-life-photo'."
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| kind | string | Only pieces of this kind: 'audit', 'coverage', 'dispatch', or 'solo'. |
| chain | string | Only pieces belonging to this story chain, by chain id (e.g. 'mcconnell'). Chain ids come from get_chain with no arguments. |
| limit | integer | Maximum items to return (default and ceiling: 20, the whole window). |
| since | string | 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. |
{
"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."
}
}
}