Fillin
REMOTE · FILLIN.GLYPHAPI.DEV
Search for AI agents. Closes the LLM-cutoff gap: CVEs, papers, frontier AI, prediction markets.
Available components
Last scanned (35 days ago)
Scores higher than 0% of remote servers
Unreachable for 7 days in a row. Last reached 24 Sep 2026.
Category Search and Retrieval
Dead
Every channel of this server has been unreachable for long enough to be marked dead. Its trust score is pinned to 0 and does not recover automatically: even once the server responds again it stays dead until it is manually reinstated.
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security11
- TLS not yet verified: we couldn't open a connection to check the certificate. View diagnostics → Unverified
- Authorisation not yet verified: we couldn't confirm whether this endpoint requires it. View diagnostics → Unverified
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS not yet verified: we couldn't read the response headers to check for it. View diagnostics → Unverified
- DNSSEC not yet verified: we couldn't validate it against a resolver. View diagnostics → Unverified
Transport & Reachability0
- Transport check failed: declared streamable-http, but we couldn't connect to verify it. See how to fix → View diagnostics → Fail
Schema Quality & AI Usability0
- Schema not yet verified: we couldn't read the endpoint's schema, or could read only part of its tool list.Unverified
Stability & Change Management0
- Stability not yet verified: not enough scan history yet (needs a 30-day window).Unverified
Tool Coverage0
- Tool coverage not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Tool Safety0
- Tool safety not yet verified: we couldn't read the endpoint's tools, or could read only part of the list.Unverified
Capabilities0
- Capabilities not yet verified: we couldn't read the endpoint's capabilities.Unverified
Unverified: 5 categories
Categories scored 0 because we could not verify them: authentication we do not have, an unreachable endpoint, or not enough scan history. We only credit what we can confirm.
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 1 Oct 26 −16
The score moved with no change recorded against any check. We would rather say so than guess.
- 30 Sept 26 −15
The score moved with no change recorded against any check. We would rather say so than guess.
- 29 Sept 26 −16
The score moved with no change recorded against any check. We would rather say so than guess.
- 28 Sept 26 −15
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 27 Sept 26 −16
The score moved with no change recorded against any check. We would rather say so than guess.
- 26 Sept 26 0
- Endpoint reachability: reachable → unreachable ▼ security
- 25 Sept 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 23 Sept 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Tool “encode” rewrote its description, which is the text the model reads security
- Tool “fillin_answer” rewrote its description, which is the text the model reads security
- Tool “fillin_query” rewrote its description, which is the text the model reads security
- Tool “glyph_search” rewrote its description, which is the text the model reads security
- Tool “query_cves” rewrote its description, which is the text the model reads security
- Tool “query_frontier” rewrote its description, which is the text the model reads security
- Tool “query_markets” rewrote its description, which is the text the model reads security
- Tool “query_papers” rewrote its description, which is the text the model reads security
- Tool “retrieve_auto” rewrote its description, which is the text the model reads security
- Schema quality: excellent → good functional
- New tool “fillin_payment_challenge” functional
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 1 Oct 2026 · Probed https://fillin.glyphapi.dev/mcp/
TLS unreached
Background: What to check on a remote MCP endpoint →
DNSSEC inconclusive
Validation of fillin.glyphapi.dev. — Inconclusive
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| fillin.glyphapi.dev. | Error no A/AAAA/CNAME RRset answered for the name |
Authentication Inconclusive
We could not reach the endpoint well enough to judge its authorisation posture.
| Result | Inconclusive |
|---|
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://fillin.glyphapi.dev/mcp/ | Unreachable | ||
| http (plaintext) | http://fillin.glyphapi.dev/mcp/ | HTTPS enforced |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
encode ~439
Bring your own text -> the cheapest substrate for your reader — the MCP twin of HTTP POST /v1/encode. Requires $0.01–$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 — 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 — the same object the HTTP route returns. Billed at the flat query rate regardless of which substrate is chosen — text and glyph cost the same here, unlike retrieve_auto's answer substrate.
| Name | Type | Req | Description |
|---|---|---|---|
| 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') get text. Unknown/None is treated as pi… |
| text | string | yes | Your text to encode — a tool result, a RAG chunk, a document. Max 40,000 chars. |
| 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. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
fillin_answer ~462
Synthesized post-cutoff answer with inline citations. Requires $0.01–$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 — 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" — quality of retrieval - top_score: float — 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
| Name | Type | Req | Description |
|---|---|---|---|
| cutoff | string | yes | Training cutoff as ISO-8601 date (e.g. 2026-01-01). |
| k | integer | – | Number of documents to ground the answer in (1-20). |
| query | string | yes | Natural-language question, max 512 chars. |
Structured output declared, but exposes no named fields.
No examples provided.
fillin_buy_mint ~139
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.
| Name | Type | Req | Description |
|---|---|---|---|
| cutoff_quarter | string | yes | Your cutoff quarter, e.g. '2026-Q1'. |
| mint_id | string | yes | The Fillin mint_id (e.g. 'mt_…'). |
| model_family | string | yes | Your model family — recorded with the buy so the buyer-side demand oracle is accurate. |
Structured output declared, but exposes no named fields.
No examples provided.
fillin_health ~27
Liveness + freshness — host, total docs, earliest, latest. No auth required.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
fillin_market_search ~214
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 includes its conclusion, list_price_usdc, and a Fillin-signed attestation you can verify before paying with fillin_buy_mint.
| Name | Type | Req | Description |
|---|---|---|---|
| cluster_id | – | – | Optional query-cluster id from a daily clustering job. Leave None for the wildcard '*' bucket. |
| cutoff_quarter | string | yes | Your training cutoff coarsened to a quarter — e.g. '2026-Q1'. |
| limit | integer | – | – |
| model_family | string | yes | Your model family — e.g. 'claude-opus-4-7', 'gpt-5'. |
| only_for_sale | boolean | – | If true (default), return only listed mints. |
Structured output declared, but exposes no named fields.
No examples provided.
fillin_mint ~284
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).
| Name | Type | Req | Description |
|---|---|---|---|
| conclusion | string | yes | Your synthesized answer. This is what buyers pay for. |
| cutoff_quarter | string | yes | Your cutoff quarter, e.g. '2026-Q1'. |
| evidence | array | yes | Fillin chunk citations you reasoned over. Each entry: {chunk_id: <Fillin id>, url?: <source url>}. |
| list_price_usdc | – | – | Resale price you want, in USDC. Pass None to mint without listing. |
| model_family | string | yes | Your model family. |
| query | string | yes | The original question you asked Fillin (or paraphrased). |
| reasoning_graph | array | yes | Typed reasoning steps. Each: {claim, evidence_chunk_id, confidence (0..1), derived_claim?}. Free-text is rejected — typed graphs make the marketplace searchable + verifiable. |
Structured output declared, but exposes no named fields.
No examples provided.
fillin_payment_challenge ~133
Mint an EIP-191 signing challenge — 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).
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | 0x-prefixed EVM address that will EIP-191 personal_sign the challenge. |
Structured output declared, but exposes no named fields.
No examples provided.
fillin_probe ~156
Free taste of the Fillin corpus — 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).
| Name | Type | Req | Description |
|---|---|---|---|
| cutoff | – | – | Optional ISO-8601 training cutoff. Defaults to 90 days ago so a first-touch caller can taste retrieval without knowing their cutoff. |
| query | string | yes | Natural-language search query, max 512 chars. |
Structured output declared, but exposes no named fields.
No examples provided.
fillin_query ~392
Retrieve documents published after a training cutoff, ranked by similarity. Requires $0.01–$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}
| Name | Type | Req | Description |
|---|---|---|---|
| cutoff | string | yes | 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). |
| query | string | yes | Natural-language search query, max 512 chars. |
Structured output declared, but exposes no named fields.
No examples provided.
fillin_signup ~147
Mint a one-time free 20-query trial bearer — 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).
| Name | Type | Req | Description |
|---|---|---|---|
| – | – | Optional contact email (max 254 chars). Not required. |
Structured output declared, but exposes no named fields.
No examples provided.
fillin_stats ~21
Get corpus stats — total docs, date range, freshness.
Input schema present but exposes no named parameters.
Structured output declared, but exposes no named fields.
No examples provided.
glyph_search ~324
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}). Requires $0.01–$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) — open the url for exact text. Billed at the flat /query rate; rendering is free.
| Name | Type | Req | Description |
|---|---|---|---|
| cutoff | string | yes | 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). |
| query | string | yes | Natural-language search query, max 512 chars. |
| tier | string | – | Glyph density tier: 6x | 10x | 15x. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
query_cves ~350
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 $0.01–$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 — pin to `patched_range` — without a second hop to NVD or GHSA.
| Name | Type | Req | Description |
|---|---|---|---|
| cutoff | string | yes | 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 skipped. Use 7.0 for high+critical only,… |
| query | string | yes | Vulnerability / supply-chain query. |
Structured output declared, but exposes no named fields.
No examples provided.
query_frontier ~231
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 $0.01–$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.
| Name | Type | Req | Description |
|---|---|---|---|
| cutoff | string | yes | Training cutoff as ISO-8601 date. |
| k | integer | – | 1-20 |
| query | string | yes | Frontier-lab / model-release query. |
Structured output declared, but exposes no named fields.
No examples provided.
query_markets ~280
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 $0.01–$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 — for live pre-trade pricing, follow the `url` to the venue and read the current quote there.
| Name | Type | Req | Description |
|---|---|---|---|
| cutoff | string | yes | Training cutoff as ISO-8601 date. |
| k | integer | – | 1-20 |
| query | string | yes | Prediction-market / forecast query. |
Structured output declared, but exposes no named fields.
No examples provided.
query_papers ~228
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 $0.01–$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.
| Name | Type | Req | Description |
|---|---|---|---|
| cutoff | string | yes | Training cutoff as ISO-8601 date. |
| k | integer | – | 1-20 |
| query | string | yes | Research / paper query. |
Structured output declared, but exposes no named fields.
No examples provided.
retrieve_auto ~588
One retrieval, auto-picked substrate — the MCP twin of HTTP POST /v1/retrieve with substrate="auto". Requires $0.01–$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 — raw result pieces (Claude/GPT pixel billing, or any unknown reader). - glyph — a dense photo-glyph image (Gemini/Qwen flat-tile billing) you read with vision; the raw pieces ride along as a citation index. - answer — 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 — 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.
| Name | Type | Req | Description |
|---|---|---|---|
| cutoff | string | yes | 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). |
| query | string | yes | Natural-language search query, max 512 chars. |
| 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-4o') get text; weak tool-callers ('llam… |
| 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. |
| Name | Type | Req | Description |
|---|---|---|---|
| result | array | yes | – |
No examples provided.
How do I install the Fillin MCP server?
Fillin is a hosted endpoint at https://fillin.glyphapi.dev/mcp/, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · fillin.glyphapi.dev
claude mcp add --transport http artchristech-fillin 'https://fillin.glyphapi.dev/mcp/'
What is the Fillin MCP server?
Fillin is an MCP server listed in the public MCP registry as io.github.artchristech/fillin. Search for AI agents. Closes the LLM-cutoff gap: CVEs, papers, frontier AI, prediction markets. This page covers its hosted endpoint (https://fillin.glyphapi.dev/mcp/).
Is the Fillin MCP server safe to use?
Fillin scores 0 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Fillin MCP server expose?
Fillin exposes 17 tools: fillin_query, glyph_search, retrieve_auto, encode, fillin_answer, and 12 more. Their descriptions and schemas cost roughly 4,415 tokens of context every time the server is loaded.
Does the Fillin MCP server require authentication?
Its publisher declares no required credentials for Fillin. We have not been able to confirm that against the live endpoint, and a server can require authorisation without declaring it here.
Is the Fillin MCP server still maintained?
Fillin has been unreachable for long enough that we treat it as dead, and its score is pinned to zero. We last reached this channel on 24 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.