MCP servers › io.github.polyrank › polyrank-mcp
MCP server · registry snapshot 2026-11-15 · last tested 2026-11-15
polyrank-mcp MCP server
Registry name io.github.polyrank/polyrank-mcp
Polyrank — the publisher's title
by polyrank · GitHub account (the registry's namespace rule)repository: same ownerSource ↗npm ↗Website ↗
Polymarket trader analytics for AI agents: rank wallets, read trader metrics, backtest strategies. — the publisher's description
Summary
io.github.polyrank/polyrank-mcp is a remote and local MCP server listed in the official MCP registry at version 0.5.1, under the namespace of the GitHub account polyrank. Its linked repository, github.com/polyrank/PolyRank-MCP, belongs to the same GitHub account. On 2026-11-15 ProtocolProbe connected to it in read-only mode and read its inventory: 36 tools, 0 resources and 0 prompts.
Record checks
- met: Registry entry is active and says how to run it
- met: Source repository link opens
- met: Repository is not archived
- met: Code pushed to the repository in the 90 days before our check
- not met: 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- met: The version the registry lists can be installed and is not withdrawn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
- #5,614 of 20,610 packages by monthly downloads, tied with 13 others
- Not ranked by stars: 2 stars (ranked from 10)
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 · Claim it
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
- Repository
- public
- Tools
- 36
- Last tested
- 2026-11-15
Tool list size
12,832 tokens on Claude Opus 5.5
Added to every request that loads this server's tools (36 tools). Counted with Anthropic's token counter on 2026-11-15, from the tool list we read on 2026-11-15. Median across 28,560 counted servers: 2,657 tokens. How it is counted
How a client gets in
Connects without signing in
Read from the server's public metadata on 2026-11-15 (mcp.polyrank.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 (0.5.1).
Observed fact
This server accepted a session without any credential and lists 2 tools whose name or declaration suggests they change data (polyrank_create_strategy, polyrank_update_strategy). That is our reading of the names; we did not call them. Source: our connection, 2026-11-15.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-11-15
- Mode
- read-only (no tool calls)
- Latest version
- 0.5.1, published 2026-11-14 (registry, as of the 2026-11-15 snapshot)
- First listed version
- 2026-11-07 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 2 versions listed, 2026-11-07 to 2026-11-14; 2 in the 90 days before the 2026-11-15 snapshot.(versions still listed in the registry only)
Most recent 2 versions
0.5.1· 2026-11-140.5.0· 2026-11-07
- Registry data
- snapshot 2026-11-15
- Package and repository
- checked 2026-11-15
- 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; 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 0.5.0 (published 2026-11-07) → 0.5.1 (published 2026-11-14), between the registry lists of 2026-11-14 and 2026-11-15.
The publisher published no GitHub release note for this version: its repository publishes no GitHub releases.
Source: the official MCP Registry list on 2026-11-14 and on 2026-11-15; release notes from the GitHub Releases API, checked 2026-11-15.
What it is
What does this server offer?
Observed inventoryNone of its 36 tools are described as changing anything. For 36 the reading was uncertain, so no mark is shown.
- polyrank_get_leaderboard
“Top Polymarket traders ranked by genuine SKILL (calibration/Brier, alpha-vs-mid, risk-adjusted return) — not vanity P&L or win rate.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
presetstring“Ranking preset id (default "polyrank-default", the calibration-heavy headline ranking).”limitinteger“Rows to return (max 25).”
- polyrank_get_trader_skill
“A single Polymarket wallet’s skill profile: composite rank, P&L, win-rate, volume, trades/markets, and commodity percentiles.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
addressstringrequired“Proxy wallet address (0x + 40 hex).”
- polyrank_get_trader_calibration
“A wallet’s 10-bin reliability diagram (predicted probability vs observed outcome rate).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
addressstringrequired“Proxy wallet address (0x + 40 hex).”
- polyrank_get_market_consensus
“Skill-weighted holder consensus on a Polymarket market vs the market mid (the Polyrank-vs-mid delta), plus 24h volume/fills, positioner counts, and top holders.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
marketstringrequired“conditionId (0x + 64 hex) or market slug.”
- polyrank_get_pulse
“Live Polymarket activity: big wins just banked (realized profit), sharp-money moves, the biggest recent trades, trending markets by volume, and markets where Polyrank consensus diverges most from the…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- polyrank_get_platform_stats
“Live Polyrank coverage and the canonical skill-metric count: wallets scored (`wallets`), raw fill events indexed (`trades`), markets covered, the number of skill metrics in the catalog, and the earli…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- polyrank_get_top_roi_trades
“The biggest return-on-cost RESOLVED Polymarket bets (won positions with a real cost floor) — a hall-of-fame of single trades by ROI multiple.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
limitinteger“Rows to return (max 100, default 50).”categorystring“Market category filter, e.g.”since_daysinteger“Only trades resolved within the last N days.”sortstring“Sort key (default "roi").”dirstring“Sort direction (default "desc").”
- polyrank_get_movers
“Traders whose skill rank climbed or fell the most recently (leaderboard momentum).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
presetstring“Ranking preset id (default "polyrank-default").”lookback_daysinteger“Lookback window in days (max 30, default 7).”limitinteger“Rows per direction (max 10, default 5).”
- polyrank_get_smart_money_reports
“The archive of Polyrank weekly Skill Reports (published each week): a list of report ids/weeks with summaries.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
limitinteger“How many recent reports to list (max 104, default 52).”
- polyrank_get_smart_money_report
“One Polyrank weekly Skill Report in full: big wins, skill-rank movers, new entrants, the calibration leader, consensus divergence, and the editorial intro.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
weekstringrequired“Report/week id from the archive, e.g.”
- polyrank_get_trader_by_tid
“Look up a trader by the opaque masked id (tid) returned in leaderboard / pulse / movers / top-ROI rows — those masked surfaces omit the raw wallet, so use the tid to follow a trader.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
tidstringrequired“Opaque trader id (tid) from a masked row.”
- polyrank_get_trader_calibration_by_tid
“A trader’s 10-bin reliability diagram (predicted probability vs observed outcome rate) keyed by the opaque masked id (tid) from a leaderboard / pulse / movers / top-ROI row.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
tidstringrequired“Opaque trader id (tid) from a masked row.”
Show 24 more tools
- polyrank_get_custom_ranking
“A published Polyrank Builder ranking: masked top-25 + the weight/filter definition.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
slugstringrequired“Published ranking slug from a /r/<slug> share link.”
- polyrank_get_traders_batch
“Fetch the free masked skill teaser for several traders at once by their opaque masked ids (tids).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
tidsarrayrequired“Opaque trader ids (tids) from masked rows (max 10).”
- polyrank_get_metrics_catalog
“The full catalog of displayable Polyrank metrics (84): id, name, description, category, direction (higher/lower is better), the windows each is available at, and whether it is advanced.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- polyrank_get_metric_windows
“Which metric exists at which window (lifetime / 90d / 30d / 7d / 24h), whether it can be weighted, gated or filtered, the copy-engine and entry-timing ids (lifetime-pinned), and what a back-dated boa…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- polyrank_list_ranking_templates
“The Ranking Builder's goals (e.g.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- polyrank_resolve_tid
“Resolve an opaque masked id (tid) to the underlying proxy wallet address.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
tidstringrequired“Opaque trader id (tid) from a masked row.”
- polyrank_rank_wallets
“Rank every Polymarket wallet with your own composite — exactly what the Ranking Builder runs (POST /v1/rankings/custom).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
17 inputs
requestobject“A complete POST /v1/rankings/custom body (e.g.”weightsobject“metric id → weight, or → {weight, window}.”windowstring“Default window for every weight given as a bare number (default lifetime).”filtersobject“Ranking filters (see description).”as_ofstring“Rank the board as it stood on this day (ISO date).”na_policystringsort_bystring“composite (default), metric:<id>, pctile:<id>, engine:<id>, timing:<id>, or a board column.”sort_dirstringlimitinteger“Rows (default 100, max 500).”offsetintegerinclude_breakdownboolean“Per-metric percentile cells per row.”include_rawboolean“Raw values beside the percentiles (dollars, hours).”include_verdictboolean“The copy verdict the trader page shows.”extra_metricsarray“More metric columns to project.”extra_engine_metricsarray“Copy-engine columns to project.”dedupe_clustersboolean“Keep one wallet per wallet-farm cluster.”explainboolean“How many wallets each filter dropped.”
- polyrank_get_trader_metrics
“One trader's every metric displayable at a window (lifetime / 90d / 30d / 7d / 24h): the raw value and its percentile in that window's cohort — the cells a board ranked at that window scores.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
addressstring“Proxy wallet address (0x + 40 hex).”tidstring“Masked trader id from a public board (resolved with your key).”windowstring“Default lifetime.”scopestring
- polyrank_list_lab_templates
“The AI Lab's templates: research strategy families as editable strategy specs, each with its as-of evidence (SIMULATED, per $10 copied) and caveats.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- polyrank_get_backtest
“A backtest by id: its status (queued / running / done / failed) and, when done, the full SIMULATED report (per-$10 P&L, copies, the no-selection control, without-best-wallet, capacity, funnel, per wa…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
idstringrequired
- polyrank_get_paper_run
“A paper run by id with the grader's stats (copies, resolved, P&L per $10, entry vs the leader, the paper gate) and its copies, each with its fate (copied / no_fill / leader_sold / capped / skipped + …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs, 1 required
idstringrequiredoutcomestringlimitintegeroffsetinteger
- polyrank_list_strategies
“Your saved strategies, newest first, each with its state and its latest backtest's headline (per $10 copied, copies; SIMULATED).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
statusstringinclude_archivedboolean
- polyrank_get_strategy
“One of your strategies by id: its name, state and full strategy spec (wallet source, market, entry, sizing, exit).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
idstringrequired
- polyrank_list_backtests
“Your recent backtests (all, or one strategy's), newest first, with status and headline (SIMULATED).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
strategy_idstringlimitinteger
- polyrank_get_lab_limits
“Your plan's AI Lab limits and what is used now: backtests a day and today's, backtests waiting, paper runs at once, saved strategies, the assistant chats answering at once (lab_agent_concurrent) agai…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- polyrank_lab_list_chats
“Your AI Lab assistant chats, most recent first (at most 100): id, title, status (idle / queued / working / failed).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
- polyrank_lab_get_chat
“One of your AI Lab assistant chats: its status, the questions and the assistant's answers with their notices and result cards (backtests, shortlists, strategies, tables).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
idstringrequiredlastinteger“Only the last N messages (default all).”
- polyrank_create_strategy
“Writes to the user's AI Lab: ask the user before calling, then pass confirm: true.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 2 required
namestringrequiredspecobject“A strategy spec (see polyrank_list_lab_templates).”template_idstringconfirmbooleanrequired“Required: true, and only after the user agreed to this call in the conversation.”
- polyrank_run_backtest
“Uses one of the plan's daily backtests: ask the user before calling, then pass confirm: true.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
6 inputs, 3 required
strategy_idstringspecobjectfromstringrequiredtostringrequiredcutsarrayconfirmbooleanrequired“Required: true, and only after the user agreed to this call in the conversation.”
- polyrank_start_paper
“Writes to the user's AI Lab: ask the user before calling, then pass confirm: true.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
3 inputs, 2 required
strategy_idstringrequiredrun_daysinteger or null“How many days the run lasts (default 10); null = no end, it runs until the user stops it.”confirmbooleanrequired“Required: true, and only after the user agreed to this call in the conversation.”
- polyrank_update_strategy
“Writes to the user's AI Lab: ask the user before calling, then pass confirm: true.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
4 inputs, 2 required
idstringrequirednamestringspecobjectconfirmbooleanrequired“Required: true, and only after the user agreed to this call in the conversation.”
- polyrank_lab_ask
“Spends the account's AI credits: ask the user before calling, then pass confirm: true.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 2 required
messagestringrequireddeepbooleanwait_secondsintegerconfirmbooleanrequired“Required: true, and only after the user agreed to this call in the conversation.”
- polyrank_lab_reply
“Spends the account's AI credits: ask the user before calling, then pass confirm: true.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
4 inputs, 3 required
idstringrequiredmessagestringrequiredwait_secondsintegerconfirmbooleanrequired“Required: true, and only after the user agreed to this call in the conversation.”
- polyrank_lab_stop
“Stop the AI Lab assistant answering in one of your chats: a question still queued is withdrawn; a running answer stops within about a second and keeps what it finished.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
1 input, 1 required
idstringrequired
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 2026-11-15.
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
- 58% of 79
- Tools with a description
- 100% of 36
- Typical description length
- 362 characters
The tool set
Counted from the listing
- Tools
- 36
- Size of the list
- about 9,280 tokens for an agent to load (characters ÷ 4)
- Naming
- 36 of 36 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 36 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 @polyrank/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": {
"polyrank-mcp": {
"command": "npx",
"args": [
"-y",
"@polyrank/mcp@0.5.1"
]
}
}
}Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"polyrank-mcp": {
"command": "npx",
"args": [
"-y",
"@polyrank/mcp@0.5.1"
]
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"polyrank-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@polyrank/mcp@0.5.1"
]
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"polyrank-mcp","type":"stdio","command":"npx","args":["-y","@polyrank/mcp@0.5.1"]}'Claude Code
claude mcp add --transport stdio polyrank-mcp -- npx -y @polyrank/mcp@0.5.1
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"polyrank-mcp": {
"command": "npx",
"args": [
"-y",
"@polyrank/mcp@0.5.1"
],
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"polyrank-mcp": {
"command": "npx",
"args": [
"-y",
"@polyrank/mcp@0.5.1"
]
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.polyrank-mcp] command = "npx" args = ["-y", "@polyrank/mcp@0.5.1"]
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"polyrank-mcp": {
"command": "npx",
"args": [
"-y",
"@polyrank/mcp@0.5.1"
]
}
}
}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 @polyrank/mcp@0.5.1
- Optional settings the entry also lists (left out above): POLYRANK_API_BASE, POLYRANK_AGENT_BASE, POLYRANK_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 2026-11-15 (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.polyrank.app/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"polyrank-mcp": {
"url": "https://mcp.polyrank.app/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"polyrank-mcp": {
"type": "http",
"url": "https://mcp.polyrank.app/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"polyrank-mcp","type":"http","url":"https://mcp.polyrank.app/mcp"}'Claude Code
claude mcp add --transport http polyrank-mcp https://mcp.polyrank.app/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"polyrank-mcp": {
"type": "streamableHttp",
"url": "https://mcp.polyrank.app/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"polyrank-mcp": {
"httpUrl": "https://mcp.polyrank.app/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.polyrank-mcp] url = "https://mcp.polyrank.app/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"polyrank-mcp": {
"url": "https://mcp.polyrank.app/mcp"
}
}
}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.polyrank.app/mcp --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
- 0.5.1
- Latest stable
- 0.5.1
- Status
- current
- Withdrawn
- no
Source: registry.npmjs.org · 2026-11-15. 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 2026-11-15 (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-gc6FmsOKFxkzC0AFY…
- Signature
- signed
- License
- MIT
Source: the package registry · 2026-11-15.
Usage
- Downloads
- 755 in the last month
Source: api.npmjs.org · 2026-11-15.
What do the published files and outside lists say?
Read as text · nothing run · no tool called
Package files
- Install-time script (npm). No install-time script in the published package.json (version 0.5.1). Source: read 2026-11-15.
- Operating systems and processors (npm). The npm package sets no os or cpu limit (package.json). Source: read 2026-11-15.
- Node.js version (npm). Needs Node 20 or later (engines.node
>=20). Source: read 2026-11-15. - MCP SDK in the package files. Lists
@modelcontextprotocol/server,@modelcontextprotocol/nodeas a dependency (package.json). Source: read 2026-11-15. - Build workflow. No build provenance published for this version. Source: read 2026-11-15.
Registry entry
- Same package in other registry entries. No other registry entry lists this entry's npm or PyPI package at a newer version. Source: own registry snapshot · read 2026-11-15.
Outside lists
- CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-15. This product uses the NVD API but is not endorsed or certified by the NVD.
- GitHub advisories. No GitHub advisory names this entry's listed package. Source: read 2026-11-15. GitHub Advisory Database, CC BY 4.0
- Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-15. Source: read 2026-11-15.
- Cline marketplace. Not in the Cline marketplace on 2026-11-15. Source: read 2026-11-15.
Own host
- security.txt. No security.txt at https://mcp.polyrank.app/.well-known/ (HTTP 404, 2026-11-15). No security.txt at https://docs.polyrank.app/.well-known/ (HTTP 404, 2026-11-15). Source: mcp.polyrank.app/.well-known/security.txt · read 2026-11-15.
- A2A agent card. No A2A agent card at https://mcp.polyrank.app/.well-known/ (HTTP 404, 2026-11-15). No A2A agent card at https://docs.polyrank.app/.well-known/ (HTTP 404, 2026-11-15). Source: mcp.polyrank.app/.well-known/agent-card.json · read 2026-11-15.
Read as text from published files and outside lists. Nothing was installed or run, and no tool was called. A fact, not a rating. How each fact is read
Does the registry listing match what we found?
Feature #6The 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.polyrank.app/mcp | Session opened | matches | our test · 2026-11-15 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-11-15 |
| Version 0.5.1 on npm | Exists and can be installed | matches | npm · 2026-11-15 |
| Repository github.com/polyrank/PolyRank-MCP | Opens publicly | matches | api.github.com · 2026-11-15 |
Who made it?
Feature #7 · lineage
Facts about the publisher. We do not turn them into a trust score.
- Namespace
- io.github.polyrank
- GitHub owner
- an organization (polyrank)
- Build record
- signed
- Repository
- github.com/polyrank/PolyRank-MCP
- Stars
- 2
- Repository age
- 91–180 days
- Last push
- 0–30 days ago
- Archived
- no
- Security policy
- none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)
Source: the registry entry and api.github.com · 2026-11-15; security policy read from GitHub · 2026-11-08.
Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.
Tool list changes
Our reads compared · no tool calledHosted endpoint mcp.polyrank.app/mcp
1 of 1 comparison between consecutive reads showed a change (2 reads, 2026-11-08 to 2026-11-15; versions 0.5.0 to 0.5.1).
Last change seen between our reads on 2026-11-08 (version 0.5.0) and 2026-11-15 (version 0.5.1).
Changed (36) (25 shown):
polyrank_create_strategy: title, description, annotationspolyrank_get_backtest: title, annotationspolyrank_get_custom_ranking: annotationspolyrank_get_lab_limits: title, description, annotationspolyrank_get_leaderboard: annotationspolyrank_get_market_consensus: annotationspolyrank_get_metric_windows: annotationspolyrank_get_metrics_catalog: annotationspolyrank_get_movers: annotationspolyrank_get_paper_run: title, annotationspolyrank_get_platform_stats: annotationspolyrank_get_pulse: annotationspolyrank_get_smart_money_report: annotationspolyrank_get_smart_money_reports: annotationspolyrank_get_strategy: title, annotationspolyrank_get_top_roi_trades: annotationspolyrank_get_trader_by_tid: annotationspolyrank_get_trader_calibration: annotationspolyrank_get_trader_calibration_by_tid: annotationspolyrank_get_trader_metrics: annotationspolyrank_get_trader_skill: annotationspolyrank_get_traders_batch: annotationspolyrank_lab_ask: title, description, annotationspolyrank_lab_get_chat: title, description, annotationspolyrank_lab_list_chats: title, description, annotationsand 11 more.
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 2026-11-15 is not known yet. No tool was called. How it is compared
Choosing
Record checks
Public records · not a safety rating7 of 9 record checks met
- #5,614 of 20,610 packages by monthly downloads, tied with 13 others
- Not ranked by stars: 2 stars (ranked from 10)
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- MetSource repository link opensThe linked GitHub repository is public.
- MetRepository is not archivedNot archived.
- MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
- Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.What changes this check: GitHub's documentation describes adding a SECURITY.md from the repository's security settings: under Reporting, Security policy, Start setup. GitHub: adding a security policy
- 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 2026-11-15 (security policy 2026-11-08). 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 io.github.polyrank/polyrank-mcp
Answered from the data aboveWho publishes io.github.polyrank/polyrank-mcp?
The registry ties the namespace io.github.polyrank to the GitHub account polyrank; only its owner can publish under it. Its linked repository, github.com/polyrank/PolyRank-MCP, belongs to the same GitHub account. These are facts from the registry and GitHub, not a rating.
Is io.github.polyrank/polyrank-mcp safe to install?
We do not rate servers as safe or unsafe. 7 of its 9 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. 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 io.github.polyrank/polyrank-mcp need an API key or sign-in?
It opened a session without any credential on 2026-11-15. The registry entry declares no required credential; no declaration is not a guarantee.
Has io.github.polyrank/polyrank-mcp been security tested?
Partly. 3 of the 15 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. ProtocolProbe publishes no security verdict for a named server.
Does io.github.polyrank/polyrank-mcp publish a security policy?
We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.
Is the listed version current?
Yes. The registry lists 0.5.1, the latest stable release on npm.
Where is the source code of io.github.polyrank/polyrank-mcp?
In github.com/polyrank/PolyRank-MCP, which opens publicly.
Found this page useful?
Anonymous · no sign-inA 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
Open without sign-in
It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. No security score is given; a check we did not run is never counted as passed.
- 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: not run · nothing to check it against
- 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
3 exercised12 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). 3 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised
- 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, except for a server whose operator has claimed it and given permission (that server's page says so); 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, except for a server whose operator has claimed it and given permission (that server's page says so); 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, except for a server whose operator has claimed it and given permission (that server's page says so); 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, except for a server whose operator has claimed it and given permission (that server's page says so); 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, except for a server whose operator has claimed it and given permission (that server's page says so); 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 - 12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or 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
- 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, 2026-11-15, 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
- 2,052 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 36 tools, 0 resources, 0 prompts.
- 5,941 msFinished: 3 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.
“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. “io.github.polyrank/polyrank-mcp: MCP server record.” Data checked 2026-11-15. https://protocolprobe.com/mcp/servers/io.github.polyrank/polyrank-mcp
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
[](https://protocolprobe.com/mcp/servers/io.github.polyrank/polyrank-mcp)
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, except for a server whose operator has claimed it and given permission (that server's page says so).
Write to hello@protocolprobe.com · corrections log · methodology