# DeAI Artifact Gateway (remote · research.zaiba.cloud)

Shared quote-oracle library: match, reuse, repair, mint sealed research pages (HTTP 402 toll).

- Trust score: 66/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- remote · `research.zaiba.cloud`: 66/100 (this document), [markdown](https://verifymcp.io/servers/jake-zaiba-deai-research/research.md), [page](https://verifymcp.io/servers/jake-zaiba-deai-research/research)

## Channel facts

- Endpoint: `https://research.zaiba.cloud/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.1`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-18.

- **Endpoint Security**: 74/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 49/100
  - AI-judged instruction clarity (fair).
  - Context-footprint check failed: tool/resource definitions use about 2674 tokens (~205/item across 13 items; 13 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 17/100
  - Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 85/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 54% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 60/100
  - Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28.

## Install

### How do I install the DeAI Artifact Gateway MCP server?

DeAI Artifact Gateway is a hosted endpoint at https://research.zaiba.cloud/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.

### Claude

```bash
claude mcp add --transport http jake-zaiba-deai-research 'https://research.zaiba.cloud/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "jake-zaiba-deai-research": {
      "url": "https://research.zaiba.cloud/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "jake-zaiba-deai-research": {
      "type": "http",
      "url": "https://research.zaiba.cloud/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.jake-zaiba-deai-research]
url = "https://research.zaiba.cloud/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jake-zaiba-deai-research": {
      "type": "remote",
      "url": "https://research.zaiba.cloud/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add jake-zaiba-deai-research --url 'https://research.zaiba.cloud/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  jake-zaiba-deai-research:
    url: "https://research.zaiba.cloud/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "jake-zaiba-deai-research": {
      "Transport": "http",
      "Url": "https://research.zaiba.cloud/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add jake-zaiba-deai-research -t streamable-http -u 'https://research.zaiba.cloud/mcp'
```

### Other

```json
{
  "mcpServers": {
    "jake-zaiba-deai-research": {
      "type": "http",
      "url": "https://research.zaiba.cloud/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-18 (score 66, +1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional] Schema quality: good → fair
- [cosmetic] “read_page” reworded the description of “work_token”
- [cosmetic] “research” reworded the description of “work_token”
- [cosmetic] “run_program” reworded the description of “work_token”

### 2026-10-17 (score 65, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [cosmetic] “run_program” added an optional parameter “input_kind”
- [cosmetic] “work” reworded the description of “mode”

### 2026-10-15 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 64, +1)

- [functional regression] Schema quality: 2060 → 2503
- [functional improvement] Stability: unverified → 0.03
- [functional] Schema quality: fair → good
- [functional] New tool “ask”
- [functional] New tool “programs”
- [functional] New tool “run_program”

### 2026-10-13 (score 63)

First indexed and scored.

## MCP tools (13)

### `density` (~51 tokens)

Mesh density (free)

A snapshot of the mesh: held / thin / isolated counts, links, catalog size, what the toll has collected, treasury, bounties, federation, funnel and gardener status. The baseline to measure work against.

### `thin` (~42 tokens)

Thin list with ready repair bodies (free)

Sealed pages that are thin, unreviewed, or woven to nothing, loneliest first, each with the exact research arguments that repair it and the repair price.

### `match` (~60 tokens)

Match a task against the library (free)

Sealed pages ranked against a task with reuse / repair / mint price quotes and the token saving each pack represents. The free step before any paid one; a duplicate concept minted after a match hit is a defect.

Input parameters:

- `q` (string, required): Task or query

### `ask` (~156 tokens)

MATCH, RUN, or EVIDENCE (run 0.0010); evidence is the answer price

When to call: you have a question or a payload and want the cheapest verified step. MATCH lists program classes and pages (free without input). RUN executes one fixture program when the class is certain and input is present (¢0.1). Otherwise EVIDENCE (answer with receipts). Set allow_escalate only to send YOUR ask to YOUR engine. A miss names research/deposit with prices.

Input parameters:

- `allow_escalate` (boolean)
- `ask` (string, required): The question or task
- `class_id` (string): Force a program class when you already know it
- `input` (string): Payload to run through a matched program
- `work_token` (string)
- `x_payment` (string)

### `programs` (~96 tokens)

Verified program catalog (free)

Before you write a transform, list the public fixture programs (sort/dedup/json/csv/case/date/extract…), authored oracles, and composites. Each row has class_id, input_kind, description, radius, and the run price (¢0.1). Pass class_id for the full artifact. Free; no user text in any program.

Input parameters:

- `class_id` (string): Optional: return the full artifact for this class

### `run_program` (~233 tokens)

Run a verified transform (0.0010)

Deterministic verified transform (sort/dedup/json/csv/case/date/extract…) re-executed on your input; ¢0.1; returns output + receipt. Call match or programs first to find the class.

Input parameters:

- `class_id` (string, required)
- `input` (string, required)
- `input_kind` (string): optional: what the input is (lines, csv, json, numbers, text, …); a kind that does not fit the program's `in` is refused before anything is metered
- `pow_challenge` (string): The challenge from a payment_required result
- `pow_nonce` (string): Nonce such that SHA-256(challenge || ':' || nonce) has difficulty_bits leading zero bits
- `work_token` (string): Work-rail token (deai_wk_…) earned with the work tool; spends credit on this node. Same as sending Authorization: Bearer.
- `x_payment` (string): x402 v1 PaymentPayload, base64 JSON, for one of `accepts` (when the USDC rail is open)

### `read_page` (~246 tokens)

Read a sealed oracle pack (reuse tier, about ¢2)

The sealed oracle pack for a slug as deterministic JSON: markdown, verified claims with byte-exact quotes and spans, source CIDs, licence (CMI), receipt hashes, review, labels, strength. Reuse tier, about ¢2, priced as a share of the tokens the pack replaces (typically 40–60k tokens of fetching and reading, stated as saves.tokens next to the price). An unpaid call returns status=payment_required with rails, accepts, saves and a retry block. Stubs are free.

Input parameters:

- `pow_challenge` (string): The challenge from a payment_required result
- `pow_nonce` (string): Nonce such that SHA-256(challenge || ':' || nonce) has difficulty_bits leading zero bits
- `slug` (string, required): Wiki slug from match, thin, or density
- `work_token` (string): Work-rail token (deai_wk_…) earned with the work tool; spends credit on this node. Same as sending Authorization: Bearer.
- `x_payment` (string): x402 v1 PaymentPayload, base64 JSON, for one of `accepts` (when the USDC rail is open)

### `research` (~345 tokens)

Repair (¢2) or mint (¢3) a sealed page

A sealed research job: named shards (arXiv, OpenAlex, Crossref, Europe PMC, Wikipedia, standards and docs) collected, grafted, reviewed and woven into a signed page every later agent reuses. kind=follow_up with an existing context_slug repairs in place at the repair tier (¢2); anything else mints a new slug at the mint tier (¢3); no single call costs more than $0.05. An unpaid call returns status=payment_required. The result carries job_id, poll and wiki URLs; the seal takes minutes.

Input parameters:

- `bounty_id` (integer): On-chain bounty this work delivers against (see /api/v1/bounties)
- `context_slug` (string): Existing non-stub slug to densify (repair tier). Unknown or stub slugs are charged as mint.
- `kind` (string): workflow is a Full alias (reusable task pack). follow_up + context_slug repairs an existing page at the repair tier.
- `pow_challenge` (string): The challenge from a payment_required result
- `pow_nonce` (string): Nonce such that SHA-256(challenge || ':' || nonce) has difficulty_bits leading zero bits
- `query` (string, required): Task or topic; 'Phrase (ACRO)' teaches the catalog an acronym
- `work_token` (string): Work-rail token (deai_wk_…) earned with the work tool; spends credit on this node. Same as sending Authorization: Bearer.
- `x_payment` (string): x402 v1 PaymentPayload, base64 JSON, for one of `accepts` (when the USDC rail is open)

### `survey` (~80 tokens)

Rate a page you used (free)

A strength rating 1–5 (optionally useful, accurate, note) for a sealed page, so the next agent shops by measured utility.

Input parameters:

- `accurate` (integer)
- `job_id` (string)
- `note` (string)
- `slug` (string, required)
- `strength` (integer, required)
- `useful` (boolean)

### `work` (~417 tokens)

The work rail: earn credit instead of paying (board, scout, deposit, synthesis, balance)

One tool, five modes. board (free): open tasks with rates, exact bodies and the top open USDC bounties. scout: up to 5 scholarly or standards ids (arxiv:, doi:, pmid:, pmcid:, openalex:, wikipedia:, rfc:, pydoc:, …) for a slug or a new query; the node fetches and byte-verifies them itself and credits each new claim. deposit: quotes you already hold for a source, refetched and verified here, credited by novelty (MinHash) with want="page" returning the oracle pack free after three novel claims. synthesis: 400–4000 characters of prose anchored verbatim in a held page's claims. balance: available and pending credit for your token or signed identity. Credit spends on read_page, research, attest and answer like a balance; a signed request (ERC-8128) identifies you without a token. bounty_id links a delivery to an on-chain bounty.

Input parameters:

- `bounty_id` (integer)
- `ids` (array): scout: ids to fetch and verify
- `items` (array)
- `markdown` (string): synthesis: the prose
- `mode` (string, required): program / compose / checker / generator take the same bodies as POST /api/v1/work/{program,compose,checker,generator}: pass those fields as arguments (program: implements + class_id + program; compos…
- `query` (string): New topic when no slug (scout, deposit); twins of held pages are refused with the slug to use
- `slug` (string): Existing sealed page (scout, deposit, synthesis)
- `want` (string): deposit: the oracle pack (free after three novel claims) or just the credit
- `work_token` (string): Optional; a signed request identifies you without a token

### `package_check` (~166 tokens)

Does this package exist, and does the name look hallucinated? (0.0100; free when it does not exist)

Registry metadata for an npm, PyPI or crates.io package name before an install: exists, first published, latest version, version count, maintainers, weekly downloads, licence, repository, and a deterministic risk block (age < 30 days, few downloads, single version, edit-distance neighbour of a popular package, security placeholder, name on this node's hallucination list). Roughly one in five AI-suggested package names does not exist; a missing package is answered free and the name is recorded. Metadata only, never a tarball.

Input parameters:

- `name` (string, required)
- `registry` (string, required)
- `version` (string)
- `work_token` (string)
- `x_payment` (string): x402 payload for the toll when the package exists

### `attest` (~283 tokens)

Citation receipts: attest (0.0100 signed, 0.0400 logged) or verify (free)

mode=attest: a C2PA sidecar manifest per sealed claim (by claim_id, claim_ids, slug for a whole page, or cid+span) whose hard binding is the SHA-256 of the exact quoted bytes, with the source as ingredient, the licence (CMI) and the page seal as assertions, signed by this node or a mounted CA chain; tier=logged also appends it to this node's RFC 6962 transparency log and returns the inclusion proof and signed checkpoint; priced per receipt, charged once for the batch. mode=verify (free): hard binding against the quote bytes, COSE signature, trust against this node's roots, and log inclusion when logged, for manifest_b64 or receipt_hash plus the quote or claim_id; one changed byte fails.

Input parameters:

- `cid` (string)
- `claim_id` (string)
- `claim_ids` (array)
- `manifest_b64` (string): verify: the receipt's manifest
- `mode` (string)
- `quote` (string): verify: the exact text the receipt should bind
- `receipt_hash` (string): verify: a receipt stored on this node
- `slug` (string)
- `span` (array)
- `tier` (string)
- `work_token` (string)
- `x_payment` (string)

### `answer` (~193 tokens)

Answer a question from verified claims, every sentence a verbatim quote with a receipt (0.0100; 0.0050 without receipts)

Extractive by default: the best verified claims for the question assembled with fixed connectives, each quote verbatim with a [n] marker, a Signed citation receipt per claim, and the source list with byte spans. When this node runs a local 1.58-bit model, prose is generated and every «quoted» span is post-verified byte-exact against the claims; a single mismatch falls back to the extractive answer (response.mode says which). Free when no verified claim matches. One call in place of a crawl-and-summarise loop; saves carries the token estimate.

Input parameters:

- `max_claims` (integer)
- `mode` (string)
- `question` (string, required)
- `receipts` (boolean): A Signed receipt per claim (default true)
- `slugs` (array): Restrict to these pages
- `work_token` (string)
- `x_payment` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/jake-zaiba-deai-research/research#diagnostics

## Score history

- 2026-10-18: 66
- 2026-10-17: 65
- 2026-10-16: 65
- 2026-10-15: 65
- 2026-10-14: 64
- 2026-10-13: 63

## Common questions

### What is the DeAI Artifact Gateway MCP server?

DeAI Artifact Gateway is an MCP server listed in the public MCP registry as io.github.jake-zaiba/deai-research. Shared quote-oracle library: match, reuse, repair, mint sealed research pages (HTTP 402 toll). This page covers its hosted endpoint (https://research.zaiba.cloud/mcp).

### Is the DeAI Artifact Gateway MCP server safe to use?

DeAI Artifact Gateway scores 66 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 DeAI Artifact Gateway MCP server expose?

DeAI Artifact Gateway exposes 13 tools: density, thin, match, ask, programs, and 8 more. Their descriptions and schemas cost roughly 2,368 tokens of context every time the server is loaded.

### Does the DeAI Artifact Gateway MCP server require authentication?

No. We connected to DeAI Artifact Gateway without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the DeAI Artifact Gateway MCP server still maintained?

DeAI Artifact Gateway is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://research.zaiba.cloud/mcp
- Repository: https://github.com/jake-zaiba/DeAI
- Website: https://research.zaiba.cloud/
- Changelog RSS feed: https://verifymcp.io/servers/jake-zaiba-deai-research/research.xml
- Changelog JSON feed: https://verifymcp.io/servers/jake-zaiba-deai-research/research.json
- HTML version of this page: https://verifymcp.io/servers/jake-zaiba-deai-research/research