
PRUVIQ MCP server
Which servers in the official MCP registry are PRUVIQ's own, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.
read 2026-10-25
- Registry namecom.pruviq/verdictsverified in the MCP registry
The registry name sits under pruviq.com. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.
- Stateanswerschecked 2026-10-25
- Tools6
- Server calls itselfpruviq-verdicts
- Server version1.0.0
- Protocol version2025-06-18
On 2026-10-25 the server answered initialize and tools/list without a sign-in. First answer in 49 ms.
- Whether its tools do the product's job has not been judged yet.
- Checked on 1 of the 7 days it takes to judge reliability.
Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.
- INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
- Answeredmeasuring1 of the 7 daily checks it takes to print a share
- Median first answer77 ms
- Space in an agent's context≈ 798 tokensthe definitions of all its tools (6), which an agent carries on every turn
- Tool definitionsA · 100 of 100
- Typed results6 of 6 toolsdeclared outputSchema: results come typed, read once
- Every tool passes all six checks.
What an agent can do with it
- not sure · backtest crypto trading strategies on historical prices with fees
- not sure · compare drawdowns and individual trades across strategy settings
- not sure · check strategy results across in-sample and out-of-sample periods
Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?
Worth a look
None of the five warning signs in these definitions.
A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (30%), doing the product's job (25%), definitions (20%), context (10%) and use (15%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →
list_strategiesList every strategy PRUVIQ publishes, with its research status (verified / conditional / testing / live / shelved / killed), the simulator preset verdict, headline metrics as the strategy page shows them (original backtest, not…
get_strategy_verdictGet the published verdict for one strategy: tone (verified / caution / negative, or no_definition) and the reasons, re-measured metrics and the strategy page's headline metrics (each block with its own scope), measurement date, sample…
get_daily_rankingsGet PRUVIQ's published daily ranking snapshot: the headline (headline_slots: up to 3 configurations labelled verified, in ranking order with their full-ranking rank; empty slots say no verified setting), the best (top3 = PF-ordered…
get_coin_strategy_statsGet per-strategy backtest statistics (trades, win rate, profit factor, total return, exit reasons, data window) for one OKX USDT-SWAP perpetual, e.g. "BTC", "BTCUSDT" or "BTC-USDT-SWAP". Cells below the minimum sample are flagged…
get_methodologyExplain how PRUVIQ measures and labels strategies (ranking criteria, research status definitions, verification criteria version, research-ledger arbiter and cost) and give the exact steps and public tools to re-verify a claim yourself…
get_forward_verification_recordsGet the forward (out-of-sample, real-time) verification program records: pre-registration files with sha256, OpenTimestamps proof state (bitcoin block heights), program status and verdict dates. Read-only.
How to connect
Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:
{
"mcpServers": {
"verdicts": {
"type": "http",
"url": "https://pruviq.com/mcp"
}
}
}Add it
Claude Code, in a terminal
claude mcp add --transport http pruviq https://pruviq.com/mcpclaude.ai, ChatGPT and other clients: add https://pruviq.com/mcp as a custom connector in the settings.
OpenAPI spec
41 paths, read 2026-10-25. Open the spec ↗
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.