Veynor MCP Server (veynor-xyz/veynor-mcp) is an MCP server listed on the M8ven Trust Index. It scores 54 out of 100, grade D. It declares 24 tools. No publisher has claimed this listing.

D
Caution
54/100

Veynor MCP Server

Prediction market intelligence for AI agents, enabling real-time access to whale trades, market data, signals, and AI-synthesized analysis from Kalshi and Polymarket via a standardized protocol.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

Code Verified⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

veynor-xyz

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
🚨
Secret credentials may flow to a network call
4 flows detected: VEYNOR_API_URL. We can’t prove the destination matches the brand the credential belongs to.
⚠️
Known vulnerabilities in dependencies: 5 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
🔐
You'll be asked for 8 credentials: ANTHROPIC_API_KEY, CREDENTIAL_ENCRYPTION_KEY, KALSHI_PRIVATE_KEY, MCP_ADMIN_SECRET, POLY_BUILDER_API_KEY, POLY_BUILDER_SECRET, STRIPE_SECRET_KEY, STRIPE_WEBHOOK_SECRET
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes12 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

get_whale_feed

Returns recent large trades (≥$8,000 notional) across Polymarket and Kalshi. WHEN TO USE: User asks about "smart money", "whale activity", "large trades", "who's buying", "what are big traders doing", or wants to track directional conviction in any market. WHEN NOT TO USE: For market prices or disc

get_top_markets

Returns the top 20 most actively traded prediction markets, ranked by 24-hour volume. Covers both Kalshi and Polymarket. Each market includes title, YES price, 24h volume, category, and direct trading URL. WHEN TO USE: User asks "what's hot right now", "most active markets", "biggest markets today"

get_market

Fetches full details for one specific prediction market by ID. Returns prices, volume, open interest, order book summary, and resolution rules. WHEN TO USE: You already have a specific market ID and want full details — price, liquidity, resolution criteria. Also use this before placing a trade to c

get_alpha_signals

Returns three categories of alpha signals across Kalshi and Polymarket. Signal types: - wide_spreads: markets with unusually wide bid/ask (illiquid books — entry opportunity if you have a view) - price_movers: markets with the largest YES price moves in the last 24h (momentum or reversal setups) -

search_markets

Searches prediction markets by keyword across Polymarket and Kalshi. Returns matching markets with current YES prices, 24h volume, and direct trading URLs. WHEN TO USE: User wants markets about a specific topic, person, event, or keyword. Any time the user names something specific — a country, pers

get_usage

Returns current credit balance, tier, quota, and per-tool credit costs. Always free (0 credits). WHEN TO USE: User asks "how many credits do I have", "what's my balance", "am I on free tier", "how much does X cost", or before running an expensive query to check headroom. Also useful at the start of

get_price_history

Returns the rolling ~1-hour price history for one specific market (60-second snapshots). Includes pre-computed 5m, 15m, and 1h price moves. WHEN TO USE: User wants to see recent price trend, momentum, or whether a market is moving. Use after get_market or search_markets to drill into a specific mar

place_kalshi_order

Places a limit or market order on Kalshi using the user's registered API credentials. WHEN TO USE: User explicitly asks to buy or sell a Kalshi market. Requires the user to have registered their Kalshi credentials first via POST /v1/credentials/kalshi. WHEN NOT TO USE: For Polymarket orders — use s

submit_signed_order

Relays a pre-signed Polymarket order to the CLOB. No-custody: Veynor never holds private keys. The order must be signed client-side (EIP-712) before calling this tool. WHEN TO USE: User has already signed a Polymarket order and wants to submit it. This is step 3 of the Polymarket trading flow: get_

get_market_pulse

Returns a full AI-synthesized prediction market briefing. Covers top volume markets, whale activity, price movers, volume spikes, and wide spreads — all in one call. The 'summary' field is a ready-to-read paragraph written by Claude Haiku. Cost: 5 credits. WHEN TO USE: User wants a morning briefing

query_intelligence

Runs a natural-language query through the Veynor intelligence engine. Finds relevant prediction markets across Kalshi and Polymarket, then returns an AI-synthesized analysis calibrated to the query intent. Cost: 5 credits. Intent routing (automatic): - Topic/search queries (e.g. "what are markets s

get_topic_markets

Returns active markets for a curated topic tag, with an AI-synthesized summary of what the collective market is pricing in. Cross-venue: always includes both Kalshi and Polymarket. Cost: 3 credits. WHEN TO USE: User asks about a broad topic area — "geopolitics", "crypto markets", "Trump markets", "

// known CVEs in dependencies5 high1 medium9 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

high@modelcontextprotocol/sdk@1.10.2GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

high@modelcontextprotocol/sdk@1.10.2GHSA-8r9q-7v3j-jr4g

Anthropic's MCP TypeScript SDK has a ReDoS vulnerability

high@modelcontextprotocol/sdk@1.10.2GHSA-w48q-cv73-mx4w

Model Context Protocol (MCP) TypeScript SDK does not enable DNS rebinding protection by default

highnodemailer@6.9.0GHSA-p6gq-j5cr-w38f

Nodemailer: Message-level raw option bypasses disableFileAccess/disableUrlAccess, enabling arbitrary file read and full-response SSRF in the delivered message

highnodemailer@6.9.0GHSA-rcmh-qjqh-p98v

Nodemailer’s addressparser is vulnerable to DoS caused by recursive calls

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
🔐 secretANTHROPIC_API_KEYsk-ant-... # Required for AI synthesis tools
🔐 secretCREDENTIAL_ENCRYPTION_KEY
configDB_PATH
configKALSHI_API_KEY_ID
🔐 secretKALSHI_PRIVATE_KEY
configKALSHI_PRIVATE_KEY_PATH
🔐 secretMCP_ADMIN_SECRETyour-secret-here
configMCP_PORT
🔐 secretPOLY_BUILDER_API_KEY
configPOLY_BUILDER_PASSPHRASE
🔐 secretPOLY_BUILDER_SECRET
configSTRIPE_ADVANCED_PRICE_ID
configSTRIPE_PRO_PRICE_ID
🔐 secretSTRIPE_SECRET_KEY
🔐 secretSTRIPE_WEBHOOK_SECRET
configVEYNOR_API_URLThe server runs on port 3001 by default. The Next.js app must be running at — the MCP server reads data files from disk and calls the intelligence endpoint via localhost HTTP.
configWIDE_SPREADS_PATH
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

24/24 tools missing one or more hints — get_whale_feed (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_top_markets (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); get_market (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +21 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tests exist

No test files found

Add tests that exercise each declared tool.

Shell command execution

1 child_process call — runs shell commands

Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.

Secrets not logged

3 secret values sent to console.log

Redact or omit secret values from log output.

Production dependencies are patched

0 critical, 5 high severity in production deps — @modelcontextprotocol/sdk@1.10.2 (high), @modelcontextprotocol/sdk@1.10.2 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 7 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/veynor-xyz/veynor-mcp?variant=verified)](https://m8ven.ai/mcp/veynor-xyz/veynor-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: a32ecd603b93f6de446171209de5feff0871b19c
code hash: 3bee6b5328ea91876e94c32a5427f24c2f2efdf6de2e7f1fe04ece199a377e74
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client