このMCPでできること
Searches post-cutoff documents covering AI developments, research papers, prediction markets, and CVE or supply-chain advisories, with optional cited answer synthesis.
機能
ツール
17
ツール
encode
Bring your own text -> the cheapest substrate for your reader â the MCP twin of
HTTP POST /v1/encode.
Requires $0.01â$0.05 USDC (x402) or an Authorization Bearer trial/paid key.
On payment_required, call fillin_probe then fillin_signup (POST /v1/signup)
for a free 20-query trial, or fillin_payment_challenge then retry with
X-Payer-Address, X-Payer-Nonce, X-Payer-Signature (or Bearer).
POST /v1/probe for 1 free taste/IP/day.
Not a search-result rendering trick: this is Glyph as a language anyone can speak.
Give it a tool result, a RAG chunk, a document â it comes back as whichever form
(dense photo-glyph image or plain text) is genuinely cheaper for your reader model's
token billing, with the honest manifest attached. The trailing JSON block always
carries a `selection` object {substrate, reader, reader_class, tier, rationale,
estimates} so the choice is auditable from the token math â the same object the
HTTP route returns.
Billed at the flat query rate regardless of which substrate is chosen â text and
glyph cost the same here, unlike retrieve_auto's answer substrate.
読み取り専用
外部アクセスあり
冪等
入力スキーマ
{'type': 'object', 'title': 'encodeArguments', 'required': ['text'], 'properties': {'text': {'type': 'string', 'title': 'Text', 'maxLength': 40000, 'minLength': 1, 'description': 'Your text to encode â\x80\x94 a tool result, a RAG chunk, a document. Max 40,000 chars.'}, 'reader': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Reader', 'default': None, 'description': "Your reader model â\x80\x94 used to pick the cheapest legible substrate. Flat-tile billers ('gemini', 'qwen') can get a dense glyph; pixel billers ('claude', 'gpt-4o') get text. Unknown/None is treated as pixel-billed â\x80\x94 the safe default (text), never an overclaimed saving."}, 'verbatim': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'title': 'Verbatim', 'default': None, 'description': 'Set true if this text must stay exact (code, hashes, quotes) â\x80\x94 it then never picks glyph, which paraphrases. None (default) auto-detects fenced code blocks.'}}}
出力スキーマ
{'type': 'object', 'title': 'encodeOutput', 'required': ['result'], 'properties': {'result': {'type': 'array', 'items': {}, 'title': 'Result'}}}
fillin_answer
Synthesized post-cutoff answer with inline citations.
Requires $0.01â$0.05 USDC (x402) or an Authorization Bearer trial/paid key.
On payment_required, call fillin_probe then fillin_signup (POST /v1/signup)
for a free 20-query trial, or fillin_payment_challenge then retry with
X-Payer-Address, X-Payer-Nonce, X-Payer-Signature (or Bearer).
POST /v1/probe for 1 free taste/IP/day.
Use this when your model is small / cheap / weaker at tool-result
synthesis (Llama, Gemini Flash, Mistral, Nemotron, Qwen). Fillin runs
a server-side LLM pass over the retrieved post-cutoff documents and
returns a 150-250 word answer with [title](url) citations already
embedded â you can quote it directly.
Premium models (Opus, Sonnet, GPT-4o) usually get better results from
`fillin_query` and synthesizing themselves, but this tool works for
any caller. Costs more than fillin_query because of the synthesis pass.
Returns:
A dict with:
- answer: the synthesized paragraph (str | None)
- citations: list of {title, url} extracted from the answer
- corpus_match: "strong" | "weak" | "none" â quality of retrieval
- top_score: float â top reranked similarity score
- model: the synthesizer model used (e.g. claude-haiku-4-5)
- reason: set when answer is None (e.g. "no_relevant_docs")
- results: raw post-cutoff documents (same shape as fillin_query)
- cutoff, query, gap_days: echoes for context
読み取り専用
外部アクセスあり
冪等
入力スキーマ
{'type': 'object', 'title': 'fillin_answerArguments', 'required': ['query', 'cutoff'], 'properties': {'k': {'type': 'integer', 'title': 'K', 'default': 5, 'maximum': 20, 'minimum': 1, 'description': 'Number of documents to ground the answer in (1-20).'}, 'query': {'type': 'string', 'title': 'Query', 'maxLength': 512, 'minLength': 1, 'description': 'Natural-language question, max 512 chars.'}, 'cutoff': {'type': 'string', 'title': 'Cutoff', 'pattern': '^\\d{4}-\\d{2}-\\d{2}(T.*)?$', 'description': 'Training cutoff as ISO-8601 date (e.g. 2026-01-01).'}}}
出力スキーマ
{'type': 'object', 'title': 'fillin_answerDictOutput', 'additionalProperties': True}
fillin_buy_mint
Buy a listed mint. Debits your bearer balance, credits the seller
(minus Fillin's rake), records the transaction, and returns the full
mint payload including the previously-paywalled reasoning_graph.
Requires FILLIN_API_KEY with sufficient balance for the mint's list price.
外部アクセスあり
入力スキーマ
{'type': 'object', 'title': 'fillin_buy_mintArguments', 'required': ['mint_id', 'model_family', 'cutoff_quarter'], 'properties': {'mint_id': {'type': 'string', 'title': 'Mint Id', 'maxLength': 64, 'minLength': 1, 'description': "The Fillin mint_id (e.g. 'mt_â\x80¦')."}, 'model_family': {'type': 'string', 'title': 'Model Family', 'maxLength': 64, 'minLength': 1, 'description': 'Your model family â\x80\x94 recorded with the buy so the buyer-side demand oracle is accurate.'}, 'cutoff_quarter': {'type': 'string', 'title': 'Cutoff Quarter', 'pattern': '^\\d{4}-Q[1-4]$', 'description': "Your cutoff quarter, e.g. '2026-Q1'."}}}
出力スキーマ
{'type': 'object', 'title': 'fillin_buy_mintDictOutput', 'additionalProperties': True}
fillin_health
Liveness + freshness â host, total docs, earliest, latest. No auth required.
読み取り専用
外部アクセスあり
冪等
入力スキーマ
{'type': 'object', 'title': 'fillin_healthArguments', 'properties': {}}
出力スキーマ
{'type': 'object', 'title': 'fillin_healthDictOutput', 'additionalProperties': True}
fillin_market_search
Search the Fillin marketplace for minted (data + reasoning) assets
matching your fingerprint. A mint is another agent's typed reasoning
over Fillin's corpus â buying one is often cheaper than re-running
the underlying retrieval + reasoning yourself.
Returns {fingerprint, mints[]}. Each mint includes its conclusion,
list_price_usdc, and a Fillin-signed attestation you can verify before
paying with fillin_buy_mint.
読み取り専用
外部アクセスあり
冪等
入力スキーマ
{'type': 'object', 'title': 'fillin_market_searchArguments', 'required': ['model_family', 'cutoff_quarter'], 'properties': {'limit': {'type': 'integer', 'title': 'Limit', 'default': 20, 'maximum': 100, 'minimum': 1}, 'cluster_id': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Cluster Id', 'default': None, 'description': "Optional query-cluster id from a daily clustering job. Leave None for the wildcard '*' bucket."}, 'model_family': {'type': 'string', 'title': 'Model Family', 'maxLength': 64, 'minLength': 1, 'description': "Your model family â\x80\x94 e.g. 'claude-opus-4-7', 'gpt-5'."}, 'only_for_sale': {'type': 'boolean', 'title': 'Only For Sale', 'default': True, 'description': 'If true (default), return only listed mints.'}, 'cutoff_quarter': {'type': 'string', 'title': 'Cutoff Quarter', 'pattern': '^\\d{4}-Q[1-4]$', 'description': "Your training cutoff coarsened to a quarter â\x80\x94 e.g. '2026-Q1'."}}}
出力スキーマ
{'type': 'object', 'title': 'fillin_market_searchDictOutput', 'additionalProperties': True}
fillin_mint
Mint a (data + reasoning) asset on the Fillin marketplace. Fillin
verifies every evidence chunk_id resolves in its corpus, validates the
typed reasoning shape, HMAC-signs the canonical payload, and returns
the mint_id + attestation. Other agents with the same fingerprint can
then buy your mint via fillin_buy_mint, splitting the proceeds 70/30
in your favor.
Requires FILLIN_API_KEY (a Fillin bearer token).
外部アクセスあり
入力スキーマ
{'type': 'object', 'title': 'fillin_mintArguments', 'required': ['query', 'model_family', 'cutoff_quarter', 'evidence', 'reasoning_graph', 'conclusion'], 'properties': {'query': {'type': 'string', 'title': 'Query', 'maxLength': 512, 'minLength': 1, 'description': 'The original question you asked Fillin (or paraphrased).'}, 'evidence': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'title': 'Evidence', 'description': 'Fillin chunk citations you reasoned over. Each entry: {chunk_id: <Fillin id>, url?: <source url>}.'}, 'conclusion': {'type': 'string', 'title': 'Conclusion', 'minLength': 1, 'description': 'Your synthesized answer. This is what buyers pay for.'}, 'model_family': {'type': 'string', 'title': 'Model Family', 'maxLength': 64, 'minLength': 1, 'description': 'Your model family.'}, 'cutoff_quarter': {'type': 'string', 'title': 'Cutoff Quarter', 'pattern': '^\\d{4}-Q[1-4]$', 'description': "Your cutoff quarter, e.g. '2026-Q1'."}, 'list_price_usdc': {'anyOf': [{'type': 'number'}, {'type': 'null'}], 'title': 'List Price Usdc', 'default': None, 'description': 'Resale price you want, in USDC. Pass None to mint without listing.'}, 'reasoning_graph': {'type': 'array', 'items': {'type': 'object', 'additionalProperties': True}, 'title': 'Reasoning Graph', 'description': 'Typed reasoning steps. Each: {claim, evidence_chunk_id, confidence (0..1), derived_claim?}. Free-text is rejected â\x80\x94 typed graphs make the marketplace searchable + verifiable.'}}}
出力スキーマ
{'type': 'object', 'title': 'fillin_mintDictOutput', 'additionalProperties': True}
fillin_payment_challenge
Mint an EIP-191 signing challenge â MCP twin of POST /v1/payment/challenge.
No bearer required. Returns {nonce, message, expires_at,
signing_scheme: eip-191-personal-sign}. Sign `message`, then retry
fillin_query with headers X-Payer-Address, X-Payer-Nonce, X-Payer-Signature.
Probe and trial signup are fillin_probe / fillin_signup (PR #12).
外部アクセスあり
入力スキーマ
{'type': 'object', 'title': 'fillin_payment_challengeArguments', 'required': ['address'], 'properties': {'address': {'type': 'string', 'title': 'Address', 'pattern': '^0x[0-9a-fA-F]{40}$', 'maxLength': 42, 'minLength': 42, 'description': '0x-prefixed EVM address that will EIP-191 personal_sign the challenge.'}}}
出力スキーマ
{'type': 'object', 'title': 'fillin_payment_challengeDictOutput', 'additionalProperties': True}
fillin_probe
Free taste of the Fillin corpus â MCP twin of POST /v1/probe.
No bearer and no x402. k is forced to 1. Quota is 1 request per IP per
UTC day (same table as HTTP /v1/probe). On success: QueryOut JSON
(results, corpus_match, substrate_estimate). On exhausted quota: isError
with a probe_exhausted JSON object (same fields as HTTP 429).
読み取り専用
外部アクセスあり
入力スキーマ
{'type': 'object', 'title': 'fillin_probeArguments', 'required': ['query'], 'properties': {'query': {'type': 'string', 'title': 'Query', 'maxLength': 512, 'minLength': 1, 'description': 'Natural-language search query, max 512 chars.'}, 'cutoff': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Cutoff', 'default': None, 'description': 'Optional ISO-8601 training cutoff. Defaults to 90 days ago so a first-touch caller can taste retrieval without knowing their cutoff.'}}}
出力スキーマ
{'type': 'object', 'title': 'fillin_probeDictOutput', 'additionalProperties': True}
fillin_query
Retrieve documents published after a training cutoff, ranked by similarity.
Requires $0.01â$0.05 USDC (x402) or an Authorization Bearer trial/paid key.
On payment_required, call fillin_probe then fillin_signup (POST /v1/signup)
for a free 20-query trial, or fillin_payment_challenge then retry with
X-Payer-Address, X-Payer-Nonce, X-Payer-Signature (or Bearer).
POST /v1/probe for 1 free taste/IP/day.
Call this whenever the user asks about events, releases, papers, issues,
or news that might post-date your training data. Fillin only returns
documents published AFTER `cutoff`, so nothing returned is redundant
with what the model already knows.
Args:
query: Natural-language search query (e.g. "rust async runtimes").
Max 512 characters.
cutoff: ISO-8601 date representing the agent's training cutoff
(e.g. "2026-01-01"). Documents on or before this date are
excluded from results.
k: Number of documents to retrieve, 1-20. Defaults to 5.
Returns:
A dict with:
- cutoff: echoed cutoff (ISO timestamp)
- query: echoed query
- gap_days: days between cutoff and now
- results: list of {id, source, url, published_at, title, text, score}
読み取り専用
外部アクセスあり
冪等
入力スキーマ
{'type': 'object', 'title': 'fillin_queryArguments', 'required': ['query', 'cutoff'], 'properties': {'k': {'type': 'integer', 'title': 'K', 'default': 5, 'maximum': 20, 'minimum': 1, 'description': 'Number of documents to retrieve (1-20).'}, 'query': {'type': 'string', 'title': 'Query', 'maxLength': 512, 'minLength': 1, 'description': 'Natural-language search query, max 512 chars.'}, 'cutoff': {'type': 'string', 'title': 'Cutoff', 'pattern': '^\\d{4}-\\d{2}-\\d{2}(T.*)?$', 'description': 'Training cutoff as ISO-8601 date (e.g. 2026-01-01). Documents on or before this date are excluded.'}}}
出力スキーマ
{'type': 'object', 'title': 'fillin_queryDictOutput', 'additionalProperties': True}
fillin_signup
Mint a one-time free 20-query trial bearer â MCP twin of POST /v1/signup.
No bearer and no x402. One key per IP per UTC day (same `trial:` quota
as HTTP /v1/signup). Success is a JSON object with `key` (shown once),
`trial`, `balance_usdc`, `queries_at_base_price`. Retry paid tools with
Authorization: Bearer <key> on the MCP HTTP request. On exhausted
quota: isError with a trial_exhausted JSON object (same fields as HTTP 429).
外部アクセスあり
入力スキーマ
{'type': 'object', 'title': 'fillin_signupArguments', 'properties': {'email': {'anyOf': [{'type': 'string', 'maxLength': 254}, {'type': 'null'}], 'title': 'Email', 'default': None, 'description': 'Optional contact email (max 254 chars). Not required.'}}}
出力スキーマ
{'type': 'object', 'title': 'fillin_signupDictOutput', 'additionalProperties': True}
fillin_stats
Get corpus stats â total docs, date range, freshness.
読み取り専用
外部アクセスあり
冪等
入力スキーマ
{'type': 'object', 'title': 'fillin_statsArguments', 'properties': {}}
出力スキーマ
{'type': 'object', 'title': 'fillin_statsDictOutput', 'additionalProperties': True}
glyph_search
Same as fillin_query, but returns the result pieces rendered as **photo
glyph** image(s) â dense, vision-readable pages â followed by a JSON
citation index ({n, source, url, title, published_at, page}).
Requires $0.01â$0.05 USDC (x402) or an Authorization Bearer trial/paid key.
On payment_required, call fillin_probe then fillin_signup (POST /v1/signup)
for a free 20-query trial, or fillin_payment_challenge then retry with
X-Payer-Address, X-Payer-Nonce, X-Payer-Signature (or Bearer).
POST /v1/probe for 1 free taste/IP/day.
Read the image(s) directly with your vision capability; use the citation
index to attribute or follow up. Glyphs are for comprehension and
fact-extraction, not verbatim quotes (vision models paraphrase) â open the
url for exact text. Billed at the flat /query rate; rendering is free.
読み取り専用
外部アクセスあり
冪等
入力スキーマ
{'type': 'object', 'title': 'glyph_searchArguments', 'required': ['query', 'cutoff'], 'properties': {'k': {'type': 'integer', 'title': 'K', 'default': 6, 'maximum': 12, 'minimum': 1, 'description': 'Number of documents to retrieve (1-12).'}, 'tier': {'type': 'string', 'title': 'Tier', 'default': '10x', 'pattern': '^(6|10|15)x$', 'description': 'Glyph density tier: 6x | 10x | 15x.'}, 'query': {'type': 'string', 'title': 'Query', 'maxLength': 512, 'minLength': 1, 'description': 'Natural-language search query, max 512 chars.'}, 'cutoff': {'type': 'string', 'title': 'Cutoff', 'pattern': '^\\d{4}-\\d{2}-\\d{2}(T.*)?$', 'description': 'Training cutoff as ISO-8601 date (e.g. 2026-01-01). Documents on or before this date are excluded.'}}}
出力スキーマ
{'type': 'object', 'title': 'glyph_searchOutput', 'required': ['result'], 'properties': {'result': {'type': 'array', 'items': {}, 'title': 'Result'}}}
query_cves
Daily snapshot of CVE / supply-chain advisories from NVD, GitHub
Security Advisories, and OSV. Use before merging dependency updates,
when triaging an alert, or when a user asks "is package X compromised".
Requires $0.01â$0.05 USDC (x402) or an Authorization Bearer trial/paid key.
On payment_required, call fillin_probe then fillin_signup (POST /v1/signup)
for a free 20-query trial, or fillin_payment_challenge then retry with
X-Payer-Address, X-Payer-Nonce, X-Payer-Signature (or Bearer).
POST /v1/probe for 1 free taste/IP/day.
Each result row carries a structured `affected` list (one entry per
affected package: ecosystem, name, vulnerable_range, patched_range) and
a numeric `severity_score` (CVSS baseScore, nullable on OSV-only rows).
A buyer can act on the returned row â pin to `patched_range` â without
a second hop to NVD or GHSA.
読み取り専用
外部アクセスあり
冪等
入力スキーマ
{'type': 'object', 'title': 'query_cvesArguments', 'required': ['query', 'cutoff'], 'properties': {'k': {'type': 'integer', 'title': 'K', 'default': 5, 'maximum': 20, 'minimum': 1, 'description': '1-20'}, 'query': {'type': 'string', 'title': 'Query', 'maxLength': 512, 'minLength': 1, 'description': 'Vulnerability / supply-chain query.'}, 'cutoff': {'type': 'string', 'title': 'Cutoff', 'pattern': '^\\d{4}-\\d{2}-\\d{2}(T.*)?$', 'description': 'Training cutoff as ISO-8601 date.'}, 'min_severity': {'anyOf': [{'type': 'number', 'maximum': 10.0, 'minimum': 0.0}, {'type': 'null'}], 'title': 'Min Severity', 'default': None, 'description': 'Optional CVSS baseScore floor (0.0-10.0). When set, rows with a populated severity_score below this value are dropped, and rows whose severity is unknown are skipped. Use 7.0 for high+critical only, 9.0 for critical only.'}}}
出力スキーマ
{'type': 'object', 'title': 'query_cvesDictOutput', 'additionalProperties': True}
query_frontier
Daily snapshot of frontier AI lab announcements + HuggingFace
trending model releases. Sources: OpenAI / DeepMind / Meta / Mistral
blog RSS, Anthropic + HF blogs (via shared rss corpus), and the HF
trending models API. Use when a user asks "what model dropped" or
"did <lab> announce X".
Requires $0.01â$0.05 USDC (x402) or an Authorization Bearer trial/paid key.
On payment_required, call fillin_probe then fillin_signup (POST /v1/signup)
for a free 20-query trial, or fillin_payment_challenge then retry with
X-Payer-Address, X-Payer-Nonce, X-Payer-Signature (or Bearer).
POST /v1/probe for 1 free taste/IP/day.
読み取り専用
外部アクセスあり
冪等
入力スキーマ
{'type': 'object', 'title': 'query_frontierArguments', 'required': ['query', 'cutoff'], 'properties': {'k': {'type': 'integer', 'title': 'K', 'default': 5, 'maximum': 20, 'minimum': 1, 'description': '1-20'}, 'query': {'type': 'string', 'title': 'Query', 'maxLength': 512, 'minLength': 1, 'description': 'Frontier-lab / model-release query.'}, 'cutoff': {'type': 'string', 'title': 'Cutoff', 'pattern': '^\\d{4}-\\d{2}-\\d{2}(T.*)?$', 'description': 'Training cutoff as ISO-8601 date.'}}}
出力スキーマ
{'type': 'object', 'title': 'query_frontierDictOutput', 'additionalProperties': True}
query_markets
Active prediction markets across Polymarket, Kalshi, Manifold, and
Metaculus. Use when a user asks "is there a market on X", "what odds
is the market giving Y", or before any agent action that should be
informed by a market price.
Requires $0.01â$0.05 USDC (x402) or an Authorization Bearer trial/paid key.
On payment_required, call fillin_probe then fillin_signup (POST /v1/signup)
for a free 20-query trial, or fillin_payment_challenge then retry with
X-Payer-Address, X-Payer-Nonce, X-Payer-Signature (or Bearer).
POST /v1/probe for 1 free taste/IP/day.
Each result row carries the question, venue, close date, volume, and
a first-sight price snapshot embedded in `text`. Prices in the corpus
are point-in-time at first ingestion â for live pre-trade pricing,
follow the `url` to the venue and read the current quote there.
読み取り専用
外部アクセスあり
冪等
入力スキーマ
{'type': 'object', 'title': 'query_marketsArguments', 'required': ['query', 'cutoff'], 'properties': {'k': {'type': 'integer', 'title': 'K', 'default': 5, 'maximum': 20, 'minimum': 1, 'description': '1-20'}, 'query': {'type': 'string', 'title': 'Query', 'maxLength': 512, 'minLength': 1, 'description': 'Prediction-market / forecast query.'}, 'cutoff': {'type': 'string', 'title': 'Cutoff', 'pattern': '^\\d{4}-\\d{2}-\\d{2}(T.*)?$', 'description': 'Training cutoff as ISO-8601 date.'}}}
出力スキーマ
{'type': 'object', 'title': 'query_marketsDictOutput', 'additionalProperties': True}
query_papers
Daily snapshot of new research relevant to AI/ML/agents. Union of
arXiv (cs.AI/cs.LG/cs.CL/cs.CR/cs.DC), HuggingFace daily papers (with
upvote signal in title), and bioRxiv. Use when a user asks about a
new technique, paper, or benchmark.
Requires $0.01â$0.05 USDC (x402) or an Authorization Bearer trial/paid key.
On payment_required, call fillin_probe then fillin_signup (POST /v1/signup)
for a free 20-query trial, or fillin_payment_challenge then retry with
X-Payer-Address, X-Payer-Nonce, X-Payer-Signature (or Bearer).
POST /v1/probe for 1 free taste/IP/day.
読み取り専用
外部アクセスあり
冪等
入力スキーマ
{'type': 'object', 'title': 'query_papersArguments', 'required': ['query', 'cutoff'], 'properties': {'k': {'type': 'integer', 'title': 'K', 'default': 5, 'maximum': 20, 'minimum': 1, 'description': '1-20'}, 'query': {'type': 'string', 'title': 'Query', 'maxLength': 512, 'minLength': 1, 'description': 'Research / paper query.'}, 'cutoff': {'type': 'string', 'title': 'Cutoff', 'pattern': '^\\d{4}-\\d{2}-\\d{2}(T.*)?$', 'description': 'Training cutoff as ISO-8601 date.'}}}
出力スキーマ
{'type': 'object', 'title': 'query_papersDictOutput', 'additionalProperties': True}
retrieve_auto
One retrieval, auto-picked substrate â the MCP twin of HTTP POST /v1/retrieve with
substrate="auto".
Requires $0.01â$0.05 USDC (x402) or an Authorization Bearer trial/paid key.
On payment_required, call fillin_probe then fillin_signup (POST /v1/signup)
for a free 20-query trial, or fillin_payment_challenge then retry with
X-Payer-Address, X-Payer-Nonce, X-Payer-Signature (or Bearer).
POST /v1/probe for 1 free taste/IP/day.
Runs a single post-cutoff retrieval, then returns whichever delivery substrate is
cheapest AND legible for your `reader` model's token billing:
- text â raw result pieces (Claude/GPT pixel billing, or any unknown reader).
- glyph â a dense photo-glyph image (Gemini/Qwen flat-tile billing) you read with
vision; the raw pieces ride along as a citation index.
- answer â a pre-cited synthesized paragraph (weak tool-callers; needs a server LLM key).
The trailing JSON block always carries a `selection` object
{substrate, reader, reader_class, tier, rationale, estimates} so the choice is
auditable from the honest token math â the same object the HTTP route returns. When the
pick is glyph, the page image(s) precede that JSON block.
Pricing matches /v1/retrieve: text/glyph bill the flat /query rate, answer bills the
answer rate. The answer rate is charged up front and the delta is refunded when the
pick resolves to text/glyph, so you always pay exactly the right rate.
読み取り専用
外部アクセスあり
冪等
入力スキーマ
{'type': 'object', 'title': 'retrieve_autoArguments', 'required': ['query', 'cutoff'], 'properties': {'k': {'type': 'integer', 'title': 'K', 'default': 6, 'maximum': 12, 'minimum': 1, 'description': 'Number of documents to retrieve (1-12).'}, 'query': {'type': 'string', 'title': 'Query', 'maxLength': 512, 'minLength': 1, 'description': 'Natural-language search query, max 512 chars.'}, 'cutoff': {'type': 'string', 'title': 'Cutoff', 'pattern': '^\\d{4}-\\d{2}-\\d{2}(T.*)?$', 'description': 'Training cutoff as ISO-8601 date (e.g. 2026-01-01). Documents on or before this date are excluded.'}, 'reader': {'anyOf': [{'type': 'string'}, {'type': 'null'}], 'title': 'Reader', 'default': None, 'description': "Your reader model â\x80\x94 used to auto-pick the cheapest legible substrate. Flat-tile billers ('gemini', 'qwen') can get a dense glyph; pixel billers ('claude', 'gpt-4o') get text; weak tool-callers ('llama', 'mistral', 'gemini-flash') get a synthesized answer. Unknown/None is treated as pixel-billed â\x80\x94 the safe default (text), never an overclaimed saving."}, 'verbatim': {'anyOf': [{'type': 'boolean'}, {'type': 'null'}], 'title': 'Verbatim', 'default': None, 'description': 'Set true if you need exact/verbatim text or code (auto then never picks glyph, which paraphrases). None (default) auto-detects from result sources/content.'}}}
出力スキーマ
{'type': 'object', 'title': 'retrieve_autoOutput', 'required': ['result'], 'properties': {'result': {'type': 'array', 'items': {}, 'title': 'Result'}}}
履歴
最近のツール変更
変更
query_markets
2026年9月25日2:48
変更
query_frontier
2026年9月25日2:48
変更
query_papers
2026年9月25日2:48
変更
query_cves
2026年9月25日2:48
追加
fillin_payment_challenge
2026年9月25日2:48
追加
fillin_signup
2026年9月25日2:48
追加
fillin_probe
2026年9月25日2:48
変更
fillin_answer
2026年9月25日2:48
変更
encode
2026年9月25日2:48
変更
retrieve_auto
2026年9月25日2:48
変更
glyph_search
2026年9月25日2:48
変更
fillin_query
2026年9月25日2:48
追加
fillin_buy_mint
2026年9月17日12:40
追加
fillin_mint
2026年9月17日12:40
追加
fillin_market_search
2026年9月17日12:40
追加
query_markets
2026年9月17日12:40
追加
query_frontier
2026年9月17日12:40
追加
query_papers
2026年9月17日12:40
追加
query_cves
2026年9月17日12:40
追加
fillin_health
2026年9月17日12:40
追加
fillin_stats
2026年9月17日12:40
追加
fillin_answer
2026年9月17日12:40
追加
encode
2026年9月17日12:40
追加
retrieve_auto
2026年9月17日12:40
追加
glyph_search
2026年9月17日12:40
追加
fillin_query
2026年9月17日12:40
関連MCP
類似のMCPサーバー
osint-terminal
com.thetempleofdoom.osint-mcp/osint-terminal
Provides keyless OSINT and reconnaissance tools for domains, DNS, IPs, breach exposure, threat intelligence, and related lookups.
tollbooth
io.github.huwhitememes/tollbooth
Provides paid OSINT, web intelligence, security threat and vulnerability lookups, prediction-market analysis, financial data, leg…
TunnelMind Data API
ai.tunnelmind/data
Aggregates web, routing, supply-chain, tracker, threat, and agent-registry intelligence into risk verdicts, evidence, receipts, a…
DataNexus MCP
com.datanexusmcp/mcp-server
Enables public-data research across domains, patents, government contracts, nonprofits, compliance registries, and software secur…
website-search
com.zeltser/website-search
Provides security article search and structured guidance, templates, frameworks, and review criteria for incident response, threa…
1cent Web Intelligence for AI Agents
ru.maxzoa/1cent
Performs SSRF-safe public web inspection, URL extraction, metadata and content analysis, accessibility checks, feed and sitemap d…
x402 Checker (AI Nock)
io.github.nock-for-mak/x402-checker
Offers paid x402 utilities for blockchain, crypto markets, academic and news search, DNS and email checks, CVE lookups, geocoding…
Urlscan Io
io.github.pipeworx-io/urlscan-io
Searches urlscan.io historical scan results by domain or IP address and returns URLs, verdicts, screenshots, and scan metadata.