Search for AI agents. Closes the LLM-cutoff gap: CVEs, papers, frontier AI, prediction markets.
Inferred from the transports this listing declares (streamable-http). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read from a real MCP initialize → tools/list handshake against the declared endpoint. No tool was ever invoked — tools/list is the read-only introspection call the protocol defines for this. It reflects what the server advertised at that moment; a hosted endpoint is not pinned to any version and can change without notice.
https://fillin.glyphapi.dev/mcp/14 tools · 280msfillin_queryRetrieve documents published after a training cutoff, ranked by similarity.
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 wh…Retrieve documents published after a training cutoff, ranked by similarity. 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 wh…
| Parameter | Type | Description |
|---|---|---|
| query* | string | Natural-language search query, max 512 chars. |
| cutoff* | string | Training cutoff as ISO-8601 date (e.g. 2026-01-01). Documents on or before this date are excluded. |
| k | integer | Number of documents to retrieve (1-20). |
glyph_searchSame as fillin_query, but returns the result pieces rendered as **photo
glyph** image(s) — dense, vision-readable pages — followed by a JSON
citation index ({n, source, url, title, published_at, page}).
Read the image(s) directly with your vision capability; use the citation
index to attribute…Same as fillin_query, but returns the result pieces rendered as **photo glyph** image(s) — dense, vision-readable pages — followed by a JSON citation index ({n, source, url, title, published_at, page}). Read the image(s) directly with your vision capability; use the citation index to attribute…
| Parameter | Type | Description |
|---|---|---|
| query* | string | Natural-language search query, max 512 chars. |
| cutoff* | string | Training cutoff as ISO-8601 date (e.g. 2026-01-01). Documents on or before this date are excluded. |
| k | integer | Number of documents to retrieve (1-12). |
| tier | string | Glyph density tier: 6x | 10x | 15x. |
retrieve_autoOne retrieval, auto-picked substrate — the MCP twin of HTTP POST /v1/retrieve with
substrate="auto".
Runs a single post-cutoff retrieval, then returns whichever delivery substrate is
cheapest AND legible for your `reader` model's token billing:
- text — raw result pieces (Claude/GPT pixel bil…One retrieval, auto-picked substrate — the MCP twin of HTTP POST /v1/retrieve with substrate="auto". Runs a single post-cutoff retrieval, then returns whichever delivery substrate is cheapest AND legible for your `reader` model's token billing: - text — raw result pieces (Claude/GPT pixel bil…
| Parameter | Type | Description |
|---|---|---|
| query* | string | Natural-language search query, max 512 chars. |
| cutoff* | string | Training cutoff as ISO-8601 date (e.g. 2026-01-01). Documents on or before this date are excluded. |
| reader | — | Your reader model — used to auto-pick the cheapest legible substrate. Flat-tile billers ('gemini', 'qwen') can get a dense glyph; pixel billers ('claude', 'gpt… |
| k | integer | Number of documents to retrieve (1-12). |
| verbatim | — | 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. |
encodeBring your own text -> the cheapest substrate for your reader — the MCP twin of
HTTP POST /v1/encode.
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 — it comes back as whichever form
(dense photo-glyph image or…Bring your own text -> the cheapest substrate for your reader — the MCP twin of HTTP POST /v1/encode. 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 — it comes back as whichever form (dense photo-glyph image or…
| Parameter | Type | Description |
|---|---|---|
| text* | string | Your text to encode — a tool result, a RAG chunk, a document. Max 40,000 chars. |
| reader | — | Your reader model — used to pick the cheapest legible substrate. Flat-tile billers ('gemini', 'qwen') can get a dense glyph; pixel billers ('claude', 'gpt-4o')… |
| verbatim | — | Set true if this text must stay exact (code, hashes, quotes) — it then never picks glyph, which paraphrases. None (default) auto-detects fenced code blocks. |
fillin_answerSynthesized post-cutoff answer with inline citations.
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 […Synthesized post-cutoff answer with inline citations. 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 […
| Parameter | Type | Description |
|---|---|---|
| query* | string | Natural-language question, max 512 chars. |
| cutoff* | string | Training cutoff as ISO-8601 date (e.g. 2026-01-01). |
| k | integer | Number of documents to ground the answer in (1-20). |
fillin_statsGet corpus stats — total docs, date range, freshness.Get corpus stats — total docs, date range, freshness.
No input schema was published for this tool.
fillin_healthLiveness + freshness — host, total docs, earliest, latest. No auth required.Liveness + freshness — host, total docs, earliest, latest. No auth required.
No input schema was published for this tool.
query_cvesDaily 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".
Each result row carries a structured `affected` list (one entry per
affected package: ec…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". Each result row carries a structured `affected` list (one entry per affected package: ec…
| Parameter | Type | Description |
|---|---|---|
| query* | string | Vulnerability / supply-chain query. |
| cutoff* | string | Training cutoff as ISO-8601 date. |
| k | integer | 1-20 |
| min_severity | — | 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 s… |
query_papersDaily 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.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.
| Parameter | Type | Description |
|---|---|---|
| query* | string | Research / paper query. |
| cutoff* | string | Training cutoff as ISO-8601 date. |
| k | integer | 1-20 |
query_frontierDaily 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".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".
| Parameter | Type | Description |
|---|---|---|
| query* | string | Frontier-lab / model-release query. |
| cutoff* | string | Training cutoff as ISO-8601 date. |
| k | integer | 1-20 |
query_marketsActive 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.
Each result row carries the question, venue, close date, volume…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. Each result row carries the question, venue, close date, volume…
| Parameter | Type | Description |
|---|---|---|
| query* | string | Prediction-market / forecast query. |
| cutoff* | string | Training cutoff as ISO-8601 date. |
| k | integer | 1-20 |
fillin_market_searchSearch the Fillin marketplace for minted (data + reasoning) assets
matching your fingerprint. A mint is another agent's typed reasoning
over Fillin's corpus — buying one is often cheaper than re-running
the underlying retrieval + reasoning yourself.
Returns {fingerprint, mints[]}. Each mint in…Search the Fillin marketplace for minted (data + reasoning) assets matching your fingerprint. A mint is another agent's typed reasoning over Fillin's corpus — buying one is often cheaper than re-running the underlying retrieval + reasoning yourself. Returns {fingerprint, mints[]}. Each mint in…
| Parameter | Type | Description |
|---|---|---|
| model_family* | string | Your model family — e.g. 'claude-opus-4-7', 'gpt-5'. |
| cutoff_quarter* | string | Your training cutoff coarsened to a quarter — e.g. '2026-Q1'. |
| cluster_id | — | Optional query-cluster id from a daily clustering job. Leave None for the wildcard '*' bucket. |
| only_for_sale | boolean | If true (default), return only listed mints. |
| limit | integer | — |
fillin_mintMint 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…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…
| Parameter | Type | Description |
|---|---|---|
| query* | string | The original question you asked Fillin (or paraphrased). |
| model_family* | string | Your model family. |
| cutoff_quarter* | string | Your cutoff quarter, e.g. '2026-Q1'. |
| evidence* | array | Fillin chunk citations you reasoned over. Each entry: {chunk_id: <Fillin id>, url?: <source url>}. |
| reasoning_graph* | array | Typed reasoning steps. Each: {claim, evidence_chunk_id, confidence (0..1), derived_claim?}. Free-text is rejected — typed graphs make the marketplace searchabl… |
| conclusion* | string | Your synthesized answer. This is what buyers pay for. |
| list_price_usdc | — | Resale price you want, in USDC. Pass None to mint without listing. |
fillin_buy_mintBuy 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.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.
| Parameter | Type | Description |
|---|---|---|
| mint_id* | string | The Fillin mint_id (e.g. 'mt_…'). |
| model_family* | string | Your model family — recorded with the buy so the buyer-side demand oracle is accurate. |
| cutoff_quarter* | string | Your cutoff quarter, e.g. '2026-Q1'. |
14 of 14 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
Search for AI agents. Closes the LLM-cutoff gap: CVEs, papers, frontier AI, prediction markets.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
This entry publishes no npm package, so Forge has no dependency tree for it. That is a gap in coverage — not a statement that it has no dependencies.