MCP servers › app.kellian › kellian

MCP server · registry snapshot 2026-11-01 · last tested 2026-11-01

app.kellian/kellian

by kellian.app · domain (the registry's namespace rule)npm ↗Website ↗

Smart money on every Polymarket market: top traders' positions and fresh moves, research, news. — the publisher's description

4 of 6 record checks metRead-only · tools listed 2026-11-01version 1.0.1MITstandard input/output, streamable HTTP39 tools

Summary

app.kellian/kellian is a remote and local MCP server listed in the official MCP registry at version 1.0.1, under the namespace of the domain kellian.app. On 2026-11-01 ProtocolProbe connected to it in read-only mode and read its inventory: 39 tools, 7 resources and 0 prompts.

Record checks

4 of 6 record checks met · 3 do not apply

met: Registry entry is active and says how to run it
not met: Source repository link opens
not applicable: Repository is not archived
not applicable: Code pushed to the repository in the 90 days before our check
not applicable: Repository publishes a security policy (SECURITY.md)
met: Package names its licence with a standard (SPDX) identifier
met: The version the registry lists can be installed and is not withdrawn
not met: npm package carries build provenance (attestation)
met: No known critical or high advisory in the package or its dependencies

#17,310 of 18,234 packages by monthly downloads, tied with 16 others
Not ranked by stars: no public GitHub repository

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Operate this server? Correct a fact · README badge · Run the checks yourself

Key facts

Runs: remote and local package
Transport: standard input/output, streamable HTTP
Your own values: none declared (not a guarantee)
Sign-in: none needed to open a session
Package: npm · listed version current
License: MIT
Dependencies: no known high or critical advisories
Tools: 39
Last tested: 2026-11-01

Tool list size

15,290 tokens on Claude Opus 5.5

Added to every request that loads this server's tools (39 tools). Counted with Anthropic's token counter on 2026-11-01, from the tool list we read on 2026-11-01. Median across 25,738 counted servers: 2,858 tokens. How it is counted

How a client gets in

Connects without signing in

Read from the server's public metadata on 2026-11-01 (mcp.kellian.app), in our read-only connection; no tool was called. It may have changed since. How it is read

Tool list at the three APIs

Not sent yet for this version (1.0.1).

Add to your client

How fresh this is

Live-tested

yes, a real session (not a text-only review)

Last tested

2026-11-01

Mode

read-only (no tool calls)

Latest version

1.0.1, published 2026-10-31 (registry, as of the 2026-11-01 snapshot)

First listed version

2026-10-31 (earliest version still in the registry; older removed versions would be earlier)

Version history

2 versions listed, all on 2026-10-31; 2 in the 90 days before the 2026-11-01 snapshot.

Most recent 2 versions

1.0.1 · 2026-10-31
1.0.0 · 2026-10-31

(versions still listed in the registry only)

Registry data

snapshot 2026-11-01

Package and repository

checked 2026-11-01

Engine

mcp-runtime-engine@0.1.0 · sdk@1.32.0

Dead or stale signals

None found in the records we hold

Looked for and not found: deprecated in the registry; listed version cannot be installed or is withdrawn. Does not apply: repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.

Changes since the last refresh

Version 1.0.0 (published 2026-10-31) → 1.0.1 (published 2026-10-31), between the registry lists of 2026-10-31 and 2026-11-01.

No release note: the registry entry links no GitHub repository.

Source: the official MCP Registry list on 2026-10-31 and on 2026-11-01; release notes from the GitHub Releases API, checked 2026-11-01.

What it is

What does this server offer?

Observed inventory

39tools

7resources

0prompts

None of its 39 tools are described as changing anything. For 39 the reading was uncertain, so no mark is shown.

kellian_get_market_research
“Read dated research, sources and published AI analyst takes for a binary market.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
- addressstringrequired“Checksummed or lowercase 20-byte EVM address (0x + 40 hex).”
- chainIdinteger
kellian_get_forecaster_record
“Read a forecaster's public record: its score against the price, open and settled forecasts.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
- addressstringrequired“The forecaster: its wallet address, or its agent id (GET /me) when it has no wallet.”
- openCursorstring“The open forecasts' next page: `open.nextCursor` from a prior response.”
- settledCursorstring“The settled forecasts' next page: `settled.nextCursor` from a prior response.”
kellian_get_forecaster
“Read a forecaster's public record: its score against the price, open and settled forecasts, a person's or an AI agent's, scored alike.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
- addressstringrequired“The forecaster: its wallet address, or its agent id (GET /me) when it has no wallet.”
- openCursorstring“The open forecasts' next page: `open.nextCursor` from a prior response.”
- settledCursorstring“The settled forecasts' next page: `settled.nextCursor` from a prior response.”
kellian_get_market_news
“Read a market's recent news headlines (last 7 days, newest first): title, link to the publisher, outlet, label (official, wire, local) and the market terms each title matched.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
- addressstringrequired“Checksummed or lowercase 20-byte EVM address (0x + 40 hex).”
- chainIdinteger
kellian_get_perp_index_bars
“Read the Kellian Perps index (the underlying stock, index, commodity or coin price, recorded every minute Kellian saw whole) as bars for a window: open, high, low, close and how many minutes each bar…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs, 2 required
- symbolstringrequired
- fromstringrequired“Start of the window (inclusive).”
- tostring“End of the window (exclusive).”
- intervalstring“Bar length.”
kellian_get_context
“Every market's research in one call, one compact record per market: the market (question, rules, chance, 24h move, close, Polymarket link), the newest headlines, the AI analysts' average, gap and one…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
8 inputs
- segmentstring“A topic, as the Traders board names it: politics, ai, economy, culture, movies, tech, weather, or a list such as ai-model-lab-rankings.”
- categorystring“The market's arena.”
- idsarray“Market ids (base:0x…), instead of segment or category.”
- allboolean“Every open market, paged.”
- sincestring“Only markets whose record changed after this time.”
- limitinteger“Records per page (default 25).”
- cursorstring“The nextCursor of the previous page.”
- viewstring“full (default): the whole record.”
kellian_get_context_changes
“Only what changed since your last call, newest first: new headlines, AI analyst views that moved, big price moves, new and closing markets, and (API Pro) top-trader moves with their price and size.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
6 inputs, 1 required
- sincestringrequired“Your last call's until (ISO 8601), up to 7 days back.”
- typesarray
- segmentstring“A topic, as the Traders board names it: politics, ai, economy, culture, movies, tech, weather, or a list such as ai-model-lab-rankings.”
- idsarray
- cursorstring
- viewstring“full (default): the whole record.”
kellian_get_smart_money
“Smart money on a Polymarket question (its slug or event id) or one option (condition id): per open option, how many Tier 1-3 traders hold each side (Tier 1 = the topic's top 10 by profit, Tier 2 = th…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs
- questionstring“A covered Polymarket question: its slug (polymarket.com/event/<slug>) or its event id.”
- optionstring“One option instead: its condition id (0x…).”
- detailstring“'rows': on Plus and API Pro, also each holder's shares, average entry and last move, and each move's shares.”
kellian_get_server_time
“Return the protocol server wall-clock time as Unix epoch milliseconds.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
kellian_list_capabilities
“List protocol capabilities available at the authenticated agent tier (endpoint catalog for the current key).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
kellian_list_chains
“List all supported blockchain networks”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
kellian_get_token_release
“Return the active versioned participation-token profile, deployment evidence, test/production stage, and distributor release IDs.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.

Show 27 more tools

kellian_list_collateral
“List public launch collateral tokens (symbol, address, decimals, chainId).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input
- chainIdinteger“Optional only when exactly one chain is active; required when multiple chains are active.”
kellian_get_contracts
“Canonical per-chain collateral capabilities and addresses (per-collateral MarketRouter proxies, the shared OutcomeToken1155, and factories) plus the exact one-time approvals for collaterals with trad…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs
- chainIdinteger“Optional chainId.”
- collateralstring“Optional reviewed collateral symbol or token address filter.”
kellian_get_fees
“Canonical two-lane fee schedule read from live factory defaults: LMSR (buy 0% / sell+claim exit) and ORDERBOOK (place 0% / taker fee charged to the economic taker on BOTH wallet-router market orders …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
kellian_get_rules
“Canonical public protocol facts: resolution timing, final review, bonds, fund flows and actor conditions.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
kellian_list_leaderboard
“Ranked public leaderboard, the same data people see.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
7 inputs
- sort“PNL, VOLUME (traders).”
- categorystring“Market category for PNL and VOLUME.”
- collateral“Collateral symbol whose board to read.”
- period“7d (this calendar week from Monday 00:00 UTC), 30d (this calendar month), 3m, 6m or 1y (trailing from 00:00 UTC of today minus 91, 182 or 365 days), or all (th…”
- generationstring“Pin the generation from the preceding leaderboard response.”
- limitinteger
- offsetinteger
kellian_get_market_state
“Get marketState, lifecycleStage, stageDeadline, tradingEndsAt and outcome.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
- marketAddressstringrequired
- chainIdnumber
kellian_discover_renderers
“List the built-in market surface renderer types with data schemas and examples.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
kellian_list_markets
“List prediction markets on Kellian.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
11 inputs
- categorystring
- marketState“Exact canonical market-state filter.”
- pageSizeinteger
- cursorstring“Keyset cursor from a prior response nextCursor.”
- chainIdnumber
- creator“Filter to markets whose on-chain creator wallet matches this address.”
- sourceConditionIdstring“Source market condition ID: lists the markets whose `resolutionSource` is `{type: 'polymarket', conditionId}` with this ID.”
- sourceTokenIdstring“Source outcome token ID, in decimal as the source market's orders name it: lists the market that follows it, each row carrying `sourceToken.side`, the order si…”
- searchstring“Free-text search over the market question.”
- sortstring“Sort order.”
- pricingModelstring“Filter by pricing engine: 'ORDERBOOK' = central limit order book markets; 'automated' = automated-market-maker markets.”
kellian_get_market
“Get detailed information about a specific prediction market”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
- addressstringrequired
- chainIdnumber
kellian_list_market_comments
“Read human comments on a market (newest first, read-only): comment body + timestamps, the commenter wallet, their black-box reputation tier, and the position they held plus the market prices frozen w…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
- addressrequired“Market contract address.”
- limitinteger
- cursorstring“nextCursor from a prior call.”
kellian_get_market_depth
“5-level market depth for a market: a simulated LMSR buy ladder (kind: 'amm') or a live aggregated order-book snapshot (kind: 'orderbook'), discriminated by `kind`.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
- addressrequired“Market contract address.”
- chainIdinteger“Chain id; probes enabled chains if omitted.”
kellian_get_market_chart
“Get price history + latest for a market.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
- addressstringrequired
- windowstring
- chainIdnumber
kellian_get_market_trades
“Recent trades for a market (newest first): buy/sell side, size (wei), post-trade price (0..1), and the trader wallet.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
- addressrequired“Market contract address.”
- chainIdinteger“Chain id; probes enabled chains if omitted.”
- limitinteger
kellian_get_market_holders
“Kellian's own play-money holders of one Kellian market: distinct holders, verified-human count, whale count, and total shares held per outcome (open interest).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
- addressrequired“Market contract address.”
- chainIdinteger“Chain id; probes enabled chains if omitted.”
kellian_discover_resolution_sources
“Describe the opaque `resolutionSource` envelope shape and the conventions agents use.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
kellian_get_market_resolution_state
“Per-market public resolution state: stage, reason, deadlines, available action flags and final outcome.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
- addressrequired“Market contract address.”
- chainIdinteger“Chain id; probes enabled chains if omitted.”
kellian_list_pending_resolution_markets
“List markets in the canonical resolution pipeline.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs
- categorystring“Optional market category filter.”
- marketState“Optional canonical market-state filter.”
- cursor“Opaque pagination cursor from a prior response.”
- limitinteger“Page size (1–100).”
kellian_list_related_markets
“List related markets in the same category and chain (canonical discovery set).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 2 required
- addressrequired“Anchor market contract address.”
- chainIdrequired“Chain id for the market address.”
- limitinteger“Max related markets (1–20, default 4).”
kellian_discover_market_data
“Describe the canonical market-data lanes for agents: the public WebSocket (subscribe via query params, channel catalog, client/server message shapes), REST snapshot/quote/orderbook lanes, the consume…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
kellian_get_trade_status
“Look up a submitted trade by transaction hash — the by-tx path for crash recovery.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 2 required
- txHashstringrequired“Transaction hash to look up (0x + 64 hex).”
- chainIdintegerrequired“Active chain the transaction was broadcast on.”
kellian_list_trade_fills
“List a wallet's fills for history and P&L.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs, 2 required
- walletAddressstringrequired“Wallet to list fills for (0x + 40 hex).”
- chainIdintegerrequired“Active chain to query.”
- cursorstring“Opaque cursor from a previous response.”
- limitinteger“Page size (1–100, default 50).”
kellian_get_positions
“Get token positions for a wallet address: share balances + cost-basis ledger (totalSpent/totalReceived in collateral smallest units, per-outcome cost basis, sell-realized P&L).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
6 inputs, 1 required
- walletAddressstringrequired
- marketAddressstring
- chainIdinteger
- limitinteger
- cursorstring
- includestring“Set to "valuation" to add currentPrices (0-1) and markValue per position.”
kellian_get_balance
“Get collateral balances for a wallet (PM by default; include="all" returns every active supported collateral on the chain).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
- walletAddressstringrequired“Wallet to check (0x + 40 hex).”
- chainIdinteger“Active chain to query.”
- includestring“default returns the PM balance only.”
kellian_list_event_types
“List every protocol WebSocket event type, its description, and its webhook equivalent (if bridged).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
kellian_discover_events
“Describe the Agent WebSocket transport (URL, auth schemes, message shapes, reconnect/replay protocol), the WS↔webhook taxonomy bridge, wallet-scoped auto-delivered channels (execution.report), and we…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
kellian_list_webhook_event_types
“List the event types agents can subscribe a webhook to, with payload shape hints, the walletFilters matching field, and the source realtime/WebSocket event each is bridged from.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
kellian_discover_webhooks
“Describe the Standard Webhooks signing scheme (headers, HMAC-SHA256 algorithm, envelope shape, replay tolerance) and the url_verification handshake, so a receiver can verify deliveries without readin…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-11-01.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).

Counted from the listing

Parameters with a description: 73% of 93
Tools with a description: 100% of 39
Typical description length: 302 characters

The tool set

Counted from the listing

Tools: 39
Size of the list: about 59,976 tokens for an agent to load (characters ÷ 4)
Naming: 39 of 39 names use snake_case

AI reading: easy to mix up

No pair found.

The AI items cover 0 of 39 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the npm package kellian-mcp

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below. The command runs the publisher’s code on your machine.

Claude Desktop · claude_desktop_config.json (Settings → Developer → Edit Config)

{
  "mcpServers": {
    "kellian": {
      "command": "npx",
      "args": [
        "-y",
        "kellian-mcp@1.0.2",
        "serve"
      ]
    }
  }
}

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "kellian": {
      "command": "npx",
      "args": [
        "-y",
        "kellian-mcp@1.0.2",
        "serve"
      ]
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "kellian": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "kellian-mcp@1.0.2",
        "serve"
      ]
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"kellian","type":"stdio","command":"npx","args":["-y","kellian-mcp@1.0.2","serve"]}'

Claude Code

claude mcp add --transport stdio kellian -- npx -y kellian-mcp@1.0.2 serve

Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)

{
  "mcpServers": {
    "kellian": {
      "command": "npx",
      "args": [
        "-y",
        "kellian-mcp@1.0.2",
        "serve"
      ],
      "disabled": false,
      "autoApprove": []
    }
  }
}

Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project

{
  "mcpServers": {
    "kellian": {
      "command": "npx",
      "args": [
        "-y",
        "kellian-mcp@1.0.2",
        "serve"
      ]
    }
  }
}

OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project

[mcp_servers.kellian]
command = "npx"
args = ["-y", "kellian-mcp@1.0.2", "serve"]

Zed · Zed settings file (command: zed: open settings file)

{
  "context_servers": {
    "kellian": {
      "command": "npx",
      "args": [
        "-y",
        "kellian-mcp@1.0.2",
        "serve"
      ]
    }
  }
}

Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+

npx @modelcontextprotocol/inspector@2.11.0 -- npx -y kellian-mcp@1.0.2 serve

Arguments are written as the registry entry gives them; a named one as “--name value”, the form the registry documentation shows.
Optional settings the entry also lists (left out above): KELLIAN_API_KEY.
This runs the publisher's code on your machine (npx). Read its README first.
The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

From the remote endpoint (Streamable HTTP)

We connected to this URL on 2026-11-01 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai

Settings → Connectors → Add custom connector, then paste:
https://mcp.kellian.app/

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "kellian": {
      "url": "https://mcp.kellian.app/"
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "kellian": {
      "type": "http",
      "url": "https://mcp.kellian.app/"
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"kellian","type":"http","url":"https://mcp.kellian.app/"}'

Claude Code

claude mcp add --transport http kellian https://mcp.kellian.app/

Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)

{
  "mcpServers": {
    "kellian": {
      "type": "streamableHttp",
      "url": "https://mcp.kellian.app/",
      "disabled": false,
      "autoApprove": []
    }
  }
}

Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project

{
  "mcpServers": {
    "kellian": {
      "httpUrl": "https://mcp.kellian.app/"
    }
  }
}

OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project

[mcp_servers.kellian]
url = "https://mcp.kellian.app/"

Zed · Zed settings file (command: zed: open settings file)

{
  "context_servers": {
    "kellian": {
      "url": "https://mcp.kellian.app/"
    }
  }
}

Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+

npx @modelcontextprotocol/inspector@2.11.0 --server-url https://mcp.kellian.app/ --transport http

Optional settings the entry also lists (left out above): Authorization.
The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Can it be installed, and is it up to date?

Version pin · advisories

Listed version

Registry lists: 1.0.2
Latest stable: 1.0.2
Status: current
Withdrawn: no

Source: registry.npmjs.org · 2026-11-01. About the version the registry lists; a manual install may resolve to a different one.

Dependency advisories

Counted in the full dependency tree as resolved on 2026-11-01 (npm audit; each bar counts packages with an advisory, not advisories). Bars share one scale. The package itself has no known vulnerability (OSV.dev).

Integrity, provenance, license

Integrity: sha512-fQRjDWHtYNhA0pY+M…
Signature: signed
License: MIT

Source: the package registry · 2026-11-01.

Usage

Downloads: 61 in the last month

Source: api.npmjs.org · 2026-11-01.

Does the registry listing match what we found?

Feature #6

The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.

Registry says	We found	Result	Source · date
Remote endpoint mcp.kellian.app/	Session opened	matches	our test · 2026-11-01
No credential declared as required	Opened a session without any credential	matches	our test · 2026-11-01
Version 1.0.2 on npm	Exists and can be installed	matches	npm · 2026-11-01

Tool list changes

Our reads compared · no tool called

Hosted endpoint mcp.kellian.app

1 of 1 comparison between consecutive reads showed a change (2 reads, 2026-10-31 to 2026-11-01; versions 1.0.0 to 1.0.1).

Last change seen between our reads on 2026-10-31 (version 1.0.0) and 2026-11-01 (version 1.0.1).

Added (2):

kellian_get_forecasterkellian_get_smart_money

Changed (3):

kellian_get_context: description, input schemakellian_get_context_changes: description, input schemakellian_get_market_holders: description

Compared from the tool lists our read-only connection recorded, separately for each hosted endpoint and each package: each tool's name, title, description, input schema and annotations (the order of keys and of tools is ignored). We see a list only when we read it: a change is shown between the two reads where we first saw it, and anything after 2026-11-01 is not known yet. No tool was called. How it is compared

Choosing

Record checks

Public records · not a safety rating

4 of 6 record checks met · 3 do not apply

#17,310 of 18,234 packages by monthly downloads, tied with 16 others
Not ranked by stars: no public GitHub repository

MetRegistry entry is active and says how to run itActive, with a package or a remote address.
Not metSource repository link opensThe registry entry gives no repository link.What changes this check: This check opens the repository link in the registry entry. GitHub's documentation describes changing a repository's visibility in its Settings, under Danger Zone, Change visibility. GitHub: setting repository visibility
Does not applyRepository is not archivedNo public GitHub repository to read.
Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
MetPackage names its licence with a standard (SPDX) identifierMIT
MetThe version the registry lists can be installed and is not withdrawnThe listed version exists and is current.
Not metnpm package carries build provenance (attestation)Signed by npm, but no build attestation.What changes this check: npm's documentation describes publishing with provenance from a cloud-hosted runner of a supported CI/CD provider, using npm CLI 9.5.0 or newer and npm publish --provenance. npm: generating provenance statements
MetNo known critical or high advisory in the package or its dependenciesNone known in the package or its dependency tree.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-01. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral

Common questions about app.kellian/kellian

Answered from the data above

Who publishes app.kellian/kellian?

The registry ties the namespace app.kellian to the domain kellian.app; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.

Is app.kellian/kellian safe to install?

We do not rate servers as safe or unsafe. 4 of its 6 applicable record checks are met (facts from public records, each listed on this page). What the records show: The listed version is the latest stable release. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has no known advisory. These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Does app.kellian/kellian need an API key or sign-in?

It opened a session without any credential on 2026-11-01. The registry entry declares no required credential; no declaration is not a guarantee.

Has app.kellian/kellian been security tested?

Partly. 4 of the 15 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. ProtocolProbe publishes no security verdict for a named server.

Is the listed version current?

Yes. The registry lists 1.0.2, the latest stable release on npm.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Not probed (we call no server's tools)

We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-11-01

Inventory: exercised
Hidden instructions: exercised
Real execution: not run · our policy
Secret leak: not run · nothing to check it against
Internal addresses: not run · our policy
Unconfirmed changes: not run · our policy
Bad input: not run · our policy
Model requests: not run · nothing to check it against
Sensitive questions: not run · nothing to check it against
Folder boundary: not run · our policy
Log leaks: not run · nothing to check it against
Hidden content: exercised
Fake assistant turns: not applicable
Token passthrough: not applicable
Token audience: not applicable
Sign-in redirect: not run · our policy
Consent handling: not testable from outside
Sign-in metadata: exercised

4 exercised11 not run (reason given)3 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 4 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 4

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
12Hidden content
audience-hidingChecks resources that hide content from the user.exercised
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised

Not run, with the reason · 11

3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy
11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy
17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside

Does not apply to this server · 3

13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable
14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable
15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable

Source: our own test, 2026-11-01, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

0 msStarted a read-only session with the server's remote endpoint
1,416 msConnected after 0 redirects. No credential was sent or needed.
Read the inventory: 39 tools, 7 resources, 0 prompts.
9,673 msFinished: 4 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified

pending: added in the weekly update

listed 2026-11-01; not classified yet

Pricing modelAI-classified

pending: added in the weekly update

the website is not read yet

Programming language

does not apply

no existing GitHub repository (server declares no repository link, so there is nothing to fetch)

Hosting type

remote and local package

registry · 2026-11-01

MCP capability

resources, tools

our test · 2026-11-01

Transport

standard input/output, streamable HTTP

registry · 2026-11-01

Required credentials

none declared

registry · 2026-11-01 · no declaration is not a guarantee

Package registry

npm

registry · 2026-11-01

Freshness

0–30 days

registry updatedAt · 2026-11-01

Lifecycle status

active

registry · 2026-11-01

License class

permissive

package registry · 2026-11-01

Integrity hash

declared (sri)

package registry · 2026-11-01

Signature / provenance

signed

package registry · 2026-11-01

Dependency advisories

none known

npm audit · 2026-11-01

Popularity

61 downloads a month

package registry · 2026-11-01

Publisher signals

not stated

no readable GitHub owner to describe

Maintenance

does not apply

server declares no repository link, so there is nothing to fetch

Environment

either (remote or your machine)

where it runs, from the hosting type · 2026-11-01

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “app.kellian/kellian: MCP server record.” Data checked 2026-11-01. https://protocolprobe.com/mcp/servers/app.kellian/kellian

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/app.kellian/kellian)](https://protocolprobe.com/mcp/servers/app.kellian/kellian)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology