Koskamo

PRUVIQ MCP

A read-only MCP server that allows agents to access published crypto strategy backtest and verification verdicts. It serves static JSON data and citations, filtering out referral links, without exposing any write paths or trading tools.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

PRUVIQ MCP logo, by PRUVIQVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-06Operated by PRUVIQ
MCP endpoint (Streamable HTTP)
https://pruviq.com/mcp
Vendor documentation

What its tools do

6 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (6)

6 of 6 have a description · 6 of 6 declare behavior hints · 3 of 3 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to pruviq.com ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Retrieve crypto strategy backtest verdicts
  • Access verification records and citations
  • Read strategy metadata and scope

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: com.pruviq/verdicts@1.0.0Project website

Protocol and capabilities

Server
pruviq-verdicts 1.1.0
MCP protocol negotiated in check
2025-11-25
Tools
6 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

PRUVIQ publishes backtest and verification results for crypto trading strategies. There is no single market scope for everything: each result's citation.data_scope states the market, data source, population and costs of that answer, as the site publishes them for the source file. Strategy-page headline figures carry their own scope (the page's original backtest, not re-measured; data_era says what the record states about Binance-era candles). Use these tools BEFORE acting on a strategy: a high backtest number is not a verification. Read `verdict.tone` and `verdict.why` from get_strategy_verdict; 'verified' is the only tone that means the published record passed its verification battery, and even then the record is not permission to trade. Every result has a `citation` block (canonical_url, source_url, source_sha256, as_of, method_version, data_scope, fee_rate, referral: none). Quote it when you cite PRUVIQ. source_sha256 is the sha256 of the source_url bytes this answer read (null if unknown): fetch source_url and compare to check the file is unchanged. Fee rates may differ by result block: follow citation.fee_rate.field and citation.fee_rate.applies_to when present, and each block's own measurement scope; do not apply a re-measured fee to separately scoped headline figures. Nothing here is investment advice, a signal, or an exchange recommendation. This server has no trading tools and links to no exchange sign-up.

Tools

6 advertised

list_strategies — List strategies with research status
Advertised by the server during the last successful anonymous check.
Advertised read-only

List 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 re-measured — see each row's headline_scope), and the URL of the full record. Optional filter by status. Read-only.

list_strategies input schema
{
  "type": "object",
  "properties": {
    "status": {
      "enum": [
        "verified",
        "conditional",
        "testing",
        "live",
        "shelved",
        "killed"
      ],
      "type": "string",
      "description": "Only return strategies with this research status."
    }
  },
  "additionalProperties": false
}
list_strategies output schema
{
  "type": "object",
  "required": [
    "citation"
  ],
  "properties": {
    "citation": {
      "type": "object",
      "required": [
        "canonical_url",
        "source_url",
        "as_of",
        "method_version",
        "data_scope",
        "referral",
        "paid_placement",
        "not_investment_advice",
        "cite_as"
      ],
      "properties": {
        "as_of": {
          "type": [
            "string",
            "null"
          ]
        },
        "cite_as": {
          "type": "string"
        },
        "fee_rate": {},
        "referral": {
          "const": "none"
        },
        "reproduce": {},
        "data_scope": {
          "type": "object",
          "required": [
            "market",
            "scope_source"
          ],
          "properties": {
            "market": {
              "type": "string"
            },
            "scope_source": {
              "type": "string"
            }
          }
        },
        "source_url": {
          "type": "string"
        },
        "canonical_url": {
          "type": "string"
        },
        "source_sha256": {
          "type": [
            "string",
            "null"
          ],
          "pattern": "^[0-9a-f]{64}$"
        },
        "method_version": {
          "type": [
            "string",
            "null"
          ]
        },
        "paid_placement": {
          "const": false
        },
        "method_version_source": {
          "type": [
            "string",
            "null"
          ]
        },
        "not_investment_advice": {
          "const": true
        }
      }
    }
  }
}
list_strategies annotations
{
  "title": "List strategies with research status",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_strategy_verdict — Get one strategy's verdict
Advertised by the server during the last successful anonymous check.
Advertised read-only

Get 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 size (trades), fees included in the measurement, verification record and how to reproduce it. Use before acting on any backtest number. Read-only.

get_strategy_verdict input schema
{
  "type": "object",
  "required": [
    "strategy_id"
  ],
  "properties": {
    "strategy_id": {
      "type": "string",
      "pattern": "^[a-z0-9-]{1,64}$",
      "description": "Strategy id as returned by list_strategies, e.g. \"bb-squeeze-long\"."
    }
  },
  "additionalProperties": false
}
get_strategy_verdict output schema
{
  "type": "object",
  "required": [
    "citation"
  ],
  "properties": {
    "citation": {
      "type": "object",
      "required": [
        "canonical_url",
        "source_url",
        "as_of",
        "method_version",
        "data_scope",
        "referral",
        "paid_placement",
        "not_investment_advice",
        "cite_as"
      ],
      "properties": {
        "as_of": {
          "type": [
            "string",
            "null"
          ]
        },
        "cite_as": {
          "type": "string"
        },
        "fee_rate": {},
        "referral": {
          "const": "none"
        },
        "reproduce": {},
        "data_scope": {
          "type": "object",
          "required": [
            "market",
            "scope_source"
          ],
          "properties": {
            "market": {
              "type": "string"
            },
            "scope_source": {
              "type": "string"
            }
          }
        },
        "source_url": {
          "type": "string"
        },
        "canonical_url": {
          "type": "string"
        },
        "source_sha256": {
          "type": [
            "string",
            "null"
          ],
          "pattern": "^[0-9a-f]{64}$"
        },
        "method_version": {
          "type": [
            "string",
            "null"
          ]
        },
        "paid_placement": {
          "const": false
        },
        "method_version_source": {
          "type": [
            "string",
            "null"
          ]
        },
        "not_investment_advice": {
          "const": true
        }
      }
    }
  }
}
get_strategy_verdict annotations
{
  "title": "Get one strategy's verdict",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_daily_rankings — Get the daily strategy ranking
Advertised by the server during the last successful anonymous check.
Advertised read-only

Get 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 research record across all statuses, not the headline) and worst configurations by backtest over the published window, each with its research status, sample size and low-sample flag, plus the headline note about whether any verified configuration is ranked. A rank is not a verification. Read-only.

get_daily_rankings input schema
{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
get_daily_rankings output schema
{
  "type": "object",
  "required": [
    "citation"
  ],
  "properties": {
    "citation": {
      "type": "object",
      "required": [
        "canonical_url",
        "source_url",
        "as_of",
        "method_version",
        "data_scope",
        "referral",
        "paid_placement",
        "not_investment_advice",
        "cite_as"
      ],
      "properties": {
        "as_of": {
          "type": [
            "string",
            "null"
          ]
        },
        "cite_as": {
          "type": "string"
        },
        "fee_rate": {},
        "referral": {
          "const": "none"
        },
        "reproduce": {},
        "data_scope": {
          "type": "object",
          "required": [
            "market",
            "scope_source"
          ],
          "properties": {
            "market": {
              "type": "string"
            },
            "scope_source": {
              "type": "string"
            }
          }
        },
        "source_url": {
          "type": "string"
        },
        "canonical_url": {
          "type": "string"
        },
        "source_sha256": {
          "type": [
            "string",
            "null"
          ],
          "pattern": "^[0-9a-f]{64}$"
        },
        "method_version": {
          "type": [
            "string",
            "null"
          ]
        },
        "paid_placement": {
          "const": false
        },
        "method_version_source": {
          "type": [
            "string",
            "null"
          ]
        },
        "not_investment_advice": {
          "const": true
        }
      }
    }
  }
}
get_daily_rankings annotations
{
  "title": "Get the daily strategy ranking",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_coin_strategy_stats — Get per-strategy backtest stats for one coin
Advertised by the server during the last successful anonymous check.
Advertised read-only

Get 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. Read-only.

get_coin_strategy_stats input schema
{
  "type": "object",
  "required": [
    "symbol"
  ],
  "properties": {
    "symbol": {
      "type": "string",
      "maxLength": 32,
      "minLength": 1,
      "description": "Coin symbol: BTC, BTCUSDT, BTC-USDT-SWAP."
    }
  },
  "additionalProperties": false
}
get_coin_strategy_stats output schema
{
  "type": "object",
  "required": [
    "citation"
  ],
  "properties": {
    "citation": {
      "type": "object",
      "required": [
        "canonical_url",
        "source_url",
        "as_of",
        "method_version",
        "data_scope",
        "referral",
        "paid_placement",
        "not_investment_advice",
        "cite_as"
      ],
      "properties": {
        "as_of": {
          "type": [
            "string",
            "null"
          ]
        },
        "cite_as": {
          "type": "string"
        },
        "fee_rate": {},
        "referral": {
          "const": "none"
        },
        "reproduce": {},
        "data_scope": {
          "type": "object",
          "required": [
            "market",
            "scope_source"
          ],
          "properties": {
            "market": {
              "type": "string"
            },
            "scope_source": {
              "type": "string"
            }
          }
        },
        "source_url": {
          "type": "string"
        },
        "canonical_url": {
          "type": "string"
        },
        "source_sha256": {
          "type": [
            "string",
            "null"
          ],
          "pattern": "^[0-9a-f]{64}$"
        },
        "method_version": {
          "type": [
            "string",
            "null"
          ]
        },
        "paid_placement": {
          "const": false
        },
        "method_version_source": {
          "type": [
            "string",
            "null"
          ]
        },
        "not_investment_advice": {
          "const": true
        }
      }
    }
  }
}
get_coin_strategy_stats annotations
{
  "title": "Get per-strategy backtest stats for one coin",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_methodology — Explain the methodology and how to re-verify
Advertised by the server during the last successful anonymous check.
Advertised read-only

Explain 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. Read-only.

get_methodology input schema
{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
get_methodology output schema
{
  "type": "object",
  "required": [
    "citation"
  ],
  "properties": {
    "citation": {
      "type": "object",
      "required": [
        "canonical_url",
        "source_url",
        "as_of",
        "method_version",
        "data_scope",
        "referral",
        "paid_placement",
        "not_investment_advice",
        "cite_as"
      ],
      "properties": {
        "as_of": {
          "type": [
            "string",
            "null"
          ]
        },
        "cite_as": {
          "type": "string"
        },
        "fee_rate": {},
        "referral": {
          "const": "none"
        },
        "reproduce": {},
        "data_scope": {
          "type": "object",
          "required": [
            "market",
            "scope_source"
          ],
          "properties": {
            "market": {
              "type": "string"
            },
            "scope_source": {
              "type": "string"
            }
          }
        },
        "source_url": {
          "type": "string"
        },
        "canonical_url": {
          "type": "string"
        },
        "source_sha256": {
          "type": [
            "string",
            "null"
          ],
          "pattern": "^[0-9a-f]{64}$"
        },
        "method_version": {
          "type": [
            "string",
            "null"
          ]
        },
        "paid_placement": {
          "const": false
        },
        "method_version_source": {
          "type": [
            "string",
            "null"
          ]
        },
        "not_investment_advice": {
          "const": true
        }
      }
    }
  }
}
get_methodology annotations
{
  "title": "Explain the methodology and how to re-verify",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}
get_forward_verification_records — Get forward-test pre-registration and timestamp proofs
Advertised by the server during the last successful anonymous check.
Advertised read-only

Get 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.

get_forward_verification_records input schema
{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
get_forward_verification_records output schema
{
  "type": "object",
  "required": [
    "citation"
  ],
  "properties": {
    "citation": {
      "type": "object",
      "required": [
        "canonical_url",
        "source_url",
        "as_of",
        "method_version",
        "data_scope",
        "referral",
        "paid_placement",
        "not_investment_advice",
        "cite_as"
      ],
      "properties": {
        "as_of": {
          "type": [
            "string",
            "null"
          ]
        },
        "cite_as": {
          "type": "string"
        },
        "fee_rate": {},
        "referral": {
          "const": "none"
        },
        "reproduce": {},
        "data_scope": {
          "type": "object",
          "required": [
            "market",
            "scope_source"
          ],
          "properties": {
            "market": {
              "type": "string"
            },
            "scope_source": {
              "type": "string"
            }
          }
        },
        "source_url": {
          "type": "string"
        },
        "canonical_url": {
          "type": "string"
        },
        "source_sha256": {
          "type": [
            "string",
            "null"
          ],
          "pattern": "^[0-9a-f]{64}$"
        },
        "method_version": {
          "type": [
            "string",
            "null"
          ]
        },
        "paid_placement": {
          "const": false
        },
        "method_version_source": {
          "type": [
            "string",
            "null"
          ]
        },
        "not_investment_advice": {
          "const": true
        }
      }
    }
  }
}
get_forward_verification_records annotations
{
  "title": "Get forward-test pre-registration and timestamp proofs",
  "readOnlyHint": true,
  "openWorldHint": false,
  "idempotentHint": true,
  "destructiveHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (2 of 2 answered).

  1. 2026-11-06: 1 of 1 checks answered
  2. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
249 ms
95th percentile latency
249 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 249 ms · metadata changed · 6 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http pruviq-mcp https://pruviq.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add pruviq-mcp --url https://pruviq.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable pruviq-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "pruviq-mcp": {
      "url": "https://pruviq.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "pruviq-mcp": {
      "type": "streamableHttp",
      "url": "https://pruviq.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start pruviq-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "pruviq-mcp": {
      "type": "http",
      "url": "https://pruviq.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http pruviq-mcp https://pruviq.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://pruviq.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "pruviq-mcp": {
      "serverUrl": "https://pruviq.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like PRUVIQ MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 6,198

Do you run PRUVIQ MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing