Fillin

io.github.artchristech/fillin

Bridges the knowledge cutoff gap by searching current information across CVE databases, academic papers, frontier AI developments, and prediction markets. When your LLM doesn't know about the latest security vulnerability, recent research, or breaking AI news, this server pulls fresh data to fill those gaps. The streamable HTTP transport means you can hook it up remotely without local installation. Essentially a real-time search layer that keeps AI agents current on technical developments they wouldn't otherwise know about. Reach for it when you need Claude to reason about events, exploits, or research published after its training data ends.

tools: 11
transport: HTTP
last updated: May 23, 2026

Open website

Tools

11 tools

Public tool metadata for what this MCP can expose to an agent.

fillin_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...3 params

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...

Parameters* required

cutoffstring

Training cutoff as ISO-8601 date (e.g. 2026-01-01). Documents on or before this date are excluded.

kinteger

Number of documents to retrieve (1-20).default: 5

querystring

Natural-language search query, max 512 chars.

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 w...3 params

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 w...

Parameters* required

cutoffstring

Training cutoff as ISO-8601 date (e.g. 2026-01-01).

kinteger

Number of documents to ground the answer in (1-20).default: 5

querystring

Natural-language question, max 512 chars.

fillin_statsGet corpus stats — total docs, date range, freshness.

Get corpus stats — total docs, date range, freshness.

No parameter schema in public metadata yet.

fillin_healthLiveness + freshness — host, total docs, earliest, latest. No auth required.

Liveness + freshness — host, total docs, earliest, latest. No auth required.

No parameter schema in public metadata yet.

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 aff...4 params

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 aff...

Parameters* required

cutoffstring

Training cutoff as ISO-8601 date.

kinteger

1-20default: 5

min_severityvalue

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...

querystring

Vulnerability / supply-chain query.

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.3 params

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.

Parameters* required

cutoffstring

Training cutoff as ISO-8601 date.

kinteger

1-20default: 5

querystring

Research / paper query.

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> an...3 params

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> an...

Parameters* required

cutoffstring

Training cutoff as ISO-8601 date.

kinteger

1-20default: 5

querystring

Frontier-lab / model-release query.

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, c...3 params

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, c...

Parameters* required

cutoffstring

Training cutoff as ISO-8601 date.

kinteger

1-20default: 5

querystring

Prediction-market / forecast query.

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...5 params

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...

Parameters* required

cluster_idvalue

Optional query-cluster id from a daily clustering job. Leave None for the wildcard '*' bucket.

cutoff_quarterstring

Your training cutoff coarsened to a quarter — e.g. '2026-Q1'.

limitinteger

default: 20

model_familystring

Your model family — e.g. 'claude-opus-4-7', 'gpt-5'.

only_for_saleboolean

If true (default), return only listed mints.default: true

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 t...7 params

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 t...

Parameters* required

conclusionstring

Your synthesized answer. This is what buyers pay for.

cutoff_quarterstring

Your cutoff quarter, e.g. '2026-Q1'.

evidencearray

Fillin chunk citations you reasoned over. Each entry: {chunk_id: <Fillin id>, url?: <source url>}.

list_price_usdcvalue

Resale price you want, in USDC. Pass None to mint without listing.

model_familystring

Your model family.

querystring

The original question you asked Fillin (or paraphrased).

reasoning_grapharray

Typed reasoning steps. Each: {claim, evidence_chunk_id, confidence (0..1), derived_claim?}. Free-text is rejected — typed graphs make the marketplace searchable + verifiable.

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.3 params

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.

Parameters* required

cutoff_quarterstring

Your cutoff quarter, e.g. '2026-Q1'.

mint_idstring

The Fillin mint_id (e.g. 'mt_…').

model_familystring

Your model family — recorded with the buy so the buyer-side demand oracle is accurate.

Details

Website: fillin.glyphapi.dev
Categories: AI & LLM Tools, Search & Web Crawling
Transport: HTTP
Registry: MCP registry, active

Related AI & LLM Tools MCP servers

View all

Agenttrustbch1212/agenttrust-mcpTrust scores & reputation for the agent-to-agent economy. Verify A2A counterparties.0stars

Memoirbighippoman/memoir-mcpStructured session journals for AI agents. Persistent memory across sessions.0stars

Apollo Intelligence Networkbnmbnmai/mcp-proxy54 AI agent tools: OSINT, intel feeds, DeFi, crypto, weather, DNS, proxies. x402 micropayments.0stars

Clyptbonsai-tech-llc/clypt-mcpAI-native link intelligence — shorten, track, and manage links from any AI agent0stars

ChainMemorychaelynet/chainmemory-mcpVerifiable, portable AI memory. Optional vault: encrypted on your machine, 12 words only you hold.0stars

Logicnodes Mcpcmdenney/logicnodes-mcp-bridgeRemote MCP for LogicNodes: Signed PII-Shield flagship + payable x402 agent tools on Base.0stars