Polyrank
Polymarket trader analytics for AI agents: rank wallets, read trader metrics, backtest strategies.
Description from the maker (original English)
Agent tools for discovery, payment safety, data extraction, and DeFi.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://agents.samedaydesk.com/mcpRun this in your terminal
claude mcp add --transport http x402-data-gateway https://agents.samedaydesk.com/mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"x402-data-gateway": {
"url": "https://agents.samedaydesk.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"x402-data-gateway": {
"type": "http",
"url": "https://agents.samedaydesk.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
https://agents.samedaydesk.com/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 6, 2026. The maker wrote them, not us; we show them as plain text.
careers_boardRead one configured public careers board and return title, location or null, posting URL, source, fetchedAt, and explicit coverage. Use `careers_board_cold` for the acquired free recipe. Partial, missing, duplicate, listed, empty, and changed stay explicit. A source failure is un
extractFetch a public HTTP(S) page and return compact extraction signals for programmatic inspection: title, meta description, Open Graph/Twitter metadata, JSON-LD, headings, links, text excerpt, and AI-readiness flags. Use `read` instead when you need the page body as LLM-ready Markdow
extract_batchFetch one to five public HTTPS URLs and return bounded structured fields for each source in one paid attempt. Supply `urls` as a JSON array and optional unique `fields`. Use `extract` for a single URL when you do not need batch accounting. Charge is one flat introductory 0.01 USD
lockfile_pin_deltaInspect two caller-supplied npm package-lock.json objects and return added, removed, and changed name+version+integrity+resolved pins. Supply JSON `before` and `after` lockfile objects, not filesystem paths, URLs, or commands. An identical pin set is informational, not a failure.
readFetch a public HTTP(S) page and return its readable body as cleaned Markdown for LLM context, preserving headings, links, and lists while dropping navigation, ads, scripts, headers, footers, asides, and forms. Use `extract` instead when you need metadata, JSON-LD, Open Graph/Twit
scanStatic supply-chain security scan of a public GitHub repo before an agent installs/runs it. Flags exfil sinks, obfuscation, credential reads, install-time curl|bash. risk=clean|suspicious|dangerous. Payment challenge and credentials are bound to GET https://agents.samedaydesk.com
schemaforgeAnalyze a public business site and return a deterministic, paste-ready JSON-LD template plus the live structured-data gap diff and ranked fixes. Use `deep_audit` instead when the same call must also return company, technology, contact, and DNS/email evidence. Generated markup con
enrichInspect a public company domain and return structured identity, technology, social, contact, DNS, email-infrastructure, and AI-readiness evidence. Use `schemaforge` instead for a paste-ready JSON-LD template and remediation diff, or `deep_audit` when both outputs are required tog
wallet_enrichInspect a public Base or EVM address and return an agent-ready on-chain profile: EOA or contract type, native and curated token holdings, token/NFT metadata, proxy evidence, activity, and a derived profile label. Use `enrich` for a company domain; the two tools accept different i
deep_auditRun one read-only AI-search-readiness audit for a public business domain: company, technology, contact, and DNS/email evidence from `enrich`, plus the live structured-data gap analysis and paste-ready JSON-LD template from `schemaforge`. Use `enrich` for company facts only or `sc
morpho_positionInspect one Base borrower across Morpho markets and return position balances, LTV, health factor, liquidation headroom, direct-RPC verification, and caller-selected collateral-price stress scenarios. Use `morpho_protection` when you need exact repay or add-collateral amounts and
morpho_protectionCalculate two alternative protection plans for one Base Morpho borrower under a selected collateral-price shock and target health factor: partial repayment or added collateral. Each plan includes the bounded asset amount, expected stressed health factor, evidence basis, and unsig
morpho_market_underwriteUnderwrite one Base Morpho market with independent GraphQL, REST, and direct-RPC evidence for configuration integrity, liquidity, utilization, concentration, borrower health bands, recent history, bad debt, and PreLiquidation availability. Use `morpho_position` or `morpho_protect
morpho_preliquidation_replayReconstruct one successful Base Morpho PreLiquidation transaction from its receipt and the exact block state, returning repaid and seized assets, protocol-oracle valuation, gross incentive, configured health window, and transaction gas before off-chain costs. Use `morpho_market_u
opportunity_preflightAgent work opportunity -> deterministic attempt, verify-first, or abandon preflight using caller-supplied cost and selection assumptions plus dated platform evidence. Returns break-even probability, expected surplus, hard gates, and source-linked evidence. No claim, bid, payment,
agent_discoverability_auditMeasure one service's brand-blind rank, source-family coverage, expected-route presence, canonical-vs-alias listing identity, duplicate records, competitors, and exact-price drift across ten public machine-service discovery views. Supply `runtimeUrl` with an exact GET route to de
payment_offer_preflightCompare x402 and MPP payment challenges, terms, and seller-declared JSON success-response readiness for one exact public HTTPS GET route before buyer authorization, including URL and realm binding, expiry, cross-protocol economic parity, and exact-route OpenAPI evidence. Use `age
seller_integrity_auditUse this after a buyer integration fails, a seller changes a paid route, or before the next paid retry or release. Audit one exact paid GET or POST seller route against buyer-required JSON success paths. GET verifies constructible non-secret input, exact request binding, live x40
contract_qualified_searchSearch Agent402 and the official MPP catalog for paid machine services that both match a capability intent and guarantee buyer-required JSON response paths. Use `agent_discoverability_audit` when you are measuring one known seller's catalog reach or rank, `seller_integrity_audit`
agent_surface_budget_auditMeasure one public service's credential-free MCP tools/list, OpenAPI, or both declared discovery surfaces before any tool call or target payment. Use `agent_discoverability_audit` for catalog reach and rank, `seller_integrity_audit` for one exact operation's response contract, or
settlement_proofVerify one claimed canonical Base USDC settlement after execution by matching a successful transaction receipt to the exact recipient, atomic amount, and optional payer. Use `payment_offer_preflight` before authorization when you need to inspect an unpaid x402 or MPP offer instea
transaction_receiptInspect one Base or Ethereum transaction hash and return normalized success or revert status, block time, gas and fee fields, decoded ERC-20 Transfer events, and canonical USDC transfers. Use `settlement_proof` instead when you must verify an exact canonical Base USDC recipient,
solana_transaction_receiptInspect one finalized Solana mainnet transaction signature and return normalized success or failure status, slot, block time, fee, SPL-token owner deltas, and canonical USDC deltas. Supply recipient, amount, and optional payer when an exact settlement claim must be verified; use
wallet_policy_conformanceEvaluate safe standardized allow, deny, and error observations from an agent wallet or delegated signer. Use this after running a bounded provider policy test matrix to distinguish explicit provider-policy enforcement from validation or generic provider failures and to test exact
stateful_wallet_policy_conformanceEvaluate safe standardized observations from wallet policies that track prior or concurrent requests. Use `wallet_policy_conformance` instead for one-request action shape, method, chain, token, recipient, amount, and function controls. This tool separately tests sequential cumula
page_changeCompare two already-held extract-batch JSON artifacts. charged is false. Not a paid SKU. Does not fetch, pay, or schedule a second observation. Compare only the explicitly selected data keys present on both matched rows. Missing keys are coverage unknown, not deletions; explicit
careers_board_coldReturn the acquired cold careers-board recipe and its public tests. This tool is free: charged is false, it does not fetch a live board, and it does not accept payment. Use `careers_board` when you need one named-board observation. Direct free execution remains available.
report_caller_resultOptionally state whether the current paid morpho_position result was useful or not_useful. This tool is free: charged is false, it does not repay, and it does not change the delivered purchase. Read the capability only from the paid result meta samedaydesk/mcp-caller-result. Sche
trial_readRead one public HTTP(S) page as bounded Markdown through the existing walletless trial. Read and extract share the same original authority, remaining hops, expiry and one concurrent operation. No separate reader allowance. Optional markdownLimitChars is an integer from 1 through
recover_paid_resultRead the stored outcome of an earlier native paid call using its original input and credential. This call cannot execute or pay.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account epistemedeus, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 181 ms (HTTP 200)
No sign-in needed
Read 30 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 3 of 3 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
The GitHub repo last changed –, and the latest version (1.23.55) reached the registry 7 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: Polyrank, Agent Data Tools: Prices and DeFi, Agent Data Tools: Chain data
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Polymarket trader analytics for AI agents: rank wallets, read trader metrics, backtest strategies.
50 tools: token prices, wallet and contract risk, liquidity pools, FX. 25 free calls.
360 tools: balances, blocks, gas, txs and logs on 5 EVM chains, plus Bitcoin. 25 free calls.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Paid GET /extract and GET /read (and MCP extract / read) return a typed record after settlement. Merchant HTTP 200 is delivery of that record, not proof that the source succeeded or that the page is complete. The JSON keeps requestedUrl, observed finalUrl (also copied to url for compatibility), source HTTP status, sourceOk, a nullable error, and a capture object that labels the no-JavaScript GET, body/excerpt limits, charset, and truncation. A 403/404 with block text is not an empty 200. Observational HTTP delivery evidence may classify schema conformance, source refusal, and truncation; that is not buyer usefulness or a sold guarantee. The extract text field is a bounded excerpt. Omitted requests keep 1,200 characters. Optional textExcerptLimitChars from 1 through 40,000 is rejected before payment when it is not an integer in that range; the price stays the same and /read is not fetched. 40,000 matches the /read Markdown ceiling because the body was already capped at 3 MB. Batch requests use the same parser and a tighter ceiling so five excerpts cannot pass admission and then exceed the 128 KiB response cap. Use /read for longer Markdown. Neither route executes JavaScript, so missing discussion text is not proof of absence. Script data islands and comments are stripped; this is not a full-discussion reader. Production source connections validate and pin public IPv4 DNS answers, revalidate up to three redirects, and reject URL credentials, private addresses, IPv6 and compressed responses that ignore the requested identity encoding. Header/meta charset labels select a decoder; capture.charset names the decoder actually used. Unknown labels fall back to UTF-8 with an explicit fallback marker.
Batch rows retain requested source slots, including duplicates and failures. Each captured row's provenance.capture records the no-JavaScript method, actual byte allowance and 1,200-character text limit when text is requested. A known body or text cutoff is partial, not complete. This does not detect undisclosed missing content. Source refusal remains a failed row even when its error page has text. The in-process fetch/timeout test hooks have no HTTP, MCP or environment input binding and do not change settlement or authorization middleware.
EXTRACT_BATCH_ENABLED=1 adds POST /extract/batch and MCP extract_batch at an introductory 0.01 USDC per admitted batch of 1–5 public HTTPS URLs. The default is off: 25 paid HTTP operations and 22 MCP tools; enabled: 26 and 23. This price is not a measured margin guarantee. Use one server process and persistent COMMERCE_DATA_DIR; unknown settlement is quarantined, not automatically charged again. Bounded partial output does not promise every source or requested field.
LOCKFILE_PIN_DELTA_ENABLED=1 adds POST /lockfile-pin-delta and MCP lockfile_pin_delta for two caller-supplied npm package-lock.json objects. The default is off. Production already has EXTRACT_BATCH_ENABLED=1 (26 paid HTTP / 23 MCP tools). Enabling lockfile beside that envelope is 27 / 24. Default-off catalogs remain 25 / 22. Default price is $0.005 (LOCKFILE_PIN_DELTA_PRICE), matching live GET /extract. Margin is not proven. Initial live release accepts x402 only; existing MPP routes including extract_batch are unchanged. HTTP JSON only: no filesystem paths, arbitrary commands, or network fetch. Identical pins are informational, not engine failure. The signed deployment statement is not rewritten here. The lockfile MCP tool's challenge resource is https://agents.samedaydesk.com/lockfile-pin-delta, not mcp:// and not /extract/batch.
The extract_batch MCP tool projects the existing HTTP payment and durable replay handler. Its challenge resource is https://agents.samedaydesk.com/extract/batch, not mcp://: first call without payment, then reuse the returned HTTP resource and exact arguments with _meta["x402/payment"]. MPP callers may use the unmodified www-authenticate challenge in result _meta["samedaydesk/http"].headers and send its credential as HTTP Authorization. That metadata also carries the HTTP status and receipt headers. Never translate an MCP-resource credential. Existing MCP tools retain their existing native MCP payment boundary.
The signed statement declares 25 standard route capabilities in either flag state (Circle is separate); it does not claim that a disabled route is available or authorize payment. Live discovery excludes disabled batch extraction.
Every paid HTTP response advertises /.well-known/agent-payment-evidence.json through the standard HTTP describedby link relation. The bounded free manifest joins each exact method and route to its seller-declared read-only effect, recursively guaranteed JSON paths, response-schema digest, exact replay binding, receipt behavior, and the existing signed deployment statement. It does not change x402 or MPP terms and is not authorization to spend; buyers must still verify the live challenge, paid output, receipt, and settlement.
Twenty pay-per-call tools for deterministic agent-work opportunity preflight, machine-service discoverability, payment-offer preflight, Morpho borrower and market decisions, protection plans, URL extraction, Markdown reading, repository security scans, company and wallet enrichment, structured data generation, transaction receipt evidence, delegated-signer policy conformance, settlement proof, and AI-search readiness audits.
plugins/samedaydesk-x402 (not marketplace-listed).claude-plugin/marketplace.json plus plugins/samedaydesk-extract (samedaydesk-extract@samedaydesk-claude; not an Anthropic official directory listing)goose/ (YAML, session flag, and deeplink; not a Goose installer)hermes/ plus portable plugins/samedaydesk-x402/skills (AgentSkills SKILL.md drop-in; not a Hermes plugin or installer)GET /defi/morpho-position?address=0x...&shocks=-10,-20,-30GET /defi/morpho-protection?address=0x...&targetHealthFactor=1.25&protectAgainstShockPct=-10GET /defi/morpho-market-underwrite?marketId=0x...GET /defi/morpho-preliquidation-replay?transactionHash=0x...GET /work/opportunity-preflight?rewardUsd=10&hours=0.25&hourlyCostUsd=4&selectionProbabilityPct=20GET /distribution/agent-discoverability-audit?origin=https://example.com&intent=extract+a+public+website+into+structured+JSON&route=/extract&method=GET&runtimeUrl=https%3A%2F%2Fexample.com%2Fextract%3Furl%3Dhttps%253A%252F%252Fexample.org&surfaceAudit=true&materializationAudit=trueGET /commerce/payment-offer-preflight?url=https://example.com/paid-routeGET /commerce/seller-integrity-audit?origin=https://seller.example&route=/paid-route&method=GET&requiredPaths=data.attributesreferral=r1_ derived from its complete seller-signed x402 settlement receipt. This creates a declared acquisition label, not verified proof. POST /commerce/referral-recheck accepts that receipt plus one downstream seller-signed settlement receipt from a distinct payer and transaction, then atomically grants at most one free changed-state recheck. The receipts prove neither an application HTTP 200 response nor output delivery or validity, and public posting or broadcasting is optional. A file matching Agent402 PR 1070's observable capture contract (bare pretty JSON receipt, no bundled Agent402 source) is already a drop-in input after ordinary JSON.parse; see docs/agent-outcome-referral-experiment.md and agent402-receipt-interop.test.mjs.node discovery-drift.mjs observe --url 'https://agent-economy-signal-x402-mainnet.bronzetti-andrea.workers.dev/premium/agent-brief' --bazaar-pay-to '0xbda48b29607b9dc66ef7e38b68ad53f2b17efb23'GET /commerce/contract-qualified-search?query=service+domain+ownership+code+provenance&requiredPaths=data.sourceRepository returns a bounded advisory OpenAPI repair plan for missing buyer-required paths without mutating seller files or inferring undeclared property types.GET /commerce/settlement-proof?transactionHash=0x...&recipient=0x...&amountAtomic=5000GET /chain/transaction-receipt?transactionHash=0x...&network=basePOST /security/wallet-policy-conformanceGET /schemas/wallet-policy-conformance-v1.jsonPOST /security/stateful-wallet-policy-conformanceGET /schemas/stateful-wallet-policy-conformance-v1.jsonPOST /integrations/agoragentic/ai-readiness-auditPOST /integrations/the402/webhookNo API key or subscription is required. Every paid HTTP route advertises x402 and native MPP Payment authentication in the same 402 response. Both protocols settle the same exact USDC amount to the same Base mainnet merchant wallet. MCP tool calls remain x402-gated.
The Morpho route is read-only. It calculates LTV, LLTV, health factor, liquidation headroom, and collateral-price shock scenarios from integer protocol values, then cross-checks indexed collateral, borrow shares, and oracle price against direct Base RPC state. Scenarios are calculations rather than probabilities or transaction recommendations. The separate protection route uses a fresh direct-RPC oracle read and direct confirmation of collateral and borrow shares to calculate exact partial-repay and add-collateral amounts. It returns unsigned token-approval and Morpho-call templates, explicit execution buffers, revalidation requirements, and economic postconditions. It never accesses a wallet, signs, broadcasts, or takes custody.
The service also keeps a privacy-safe demand telescope on a persistent Railway volume. It records route families, query key names whose runtime values pass the shared GET presence test, challenge/success classes, and pseudonymous repeat-use signals. External fetches are acquisition signals, not verified buyers, because unidentified automated indexers can remain. Recognized crawler and agent-indexer user agents are reduced at ingestion to a controlled source l
Only the beginning is shown; read the rest in the repo