DripMetrics AI MCP server

• Registry nameai.dripmetrics/mcpverified in the MCP registry

The registry name sits under dripmetrics.ai. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

• Stateanswerschecked 2026-10-23
• Tools6
• Server calls itselfdripmetrics
• Server version1.0.0
• Protocol version2025-06-18

On 2026-10-23 the server answered initialize and tools/list without a sign-in. First answer in 239 ms.

• Whether its tools do the product's job has not been judged yet.
• Checked on 5 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: 5 so far
• Answeredmeasuring5 of the 7 daily checks it takes to print a share
• Median first answer187 ms
• Space in an agent's context≈ 1,203 tokensthe definitions of all its tools (6), which an agent carries on every turn
• Tool definitionsA · 100 of 100
• Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once

• Every tool passes all six checks.

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 (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). 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_metrics

  Free. Lists every DripMetrics metric endpoint with its id, family, HTTP method, USD price, and summary. Use describe_metric for parameter details and get_metric (or the compute_* tools for POST endpoints) to fetch values. Paid fetches use…

• describe_metric

  Free. Returns full details for one metric id from list_metrics: parameters, request/response schemas, price, and how to fetch it.

• get_payment_requirements

  Free. Dry-runs a metric request without payment and returns the exact x402 challenge the API issues (accepted networks, asset, amount, payTo). Invalid parameters fail here before any payment.

• get_metric

  Paid via x402 (up to $0.25 per request; exact price per metric in list_metrics). Fetches any GET metric by id with query parameters. Without payment this returns the x402 challenge in _meta["x402/error"]; x402-capable clients (e.g…

• compute_portfolio_var

  Paid via x402 ($0.05 per request). Computes empirical and/or normal parametric VaR for a crypto portfolio. Provide either weights + portfolioValueUsd, or quantities. Invalid portfolios fail before payment.

• compute_spread_greeks

  Paid via x402 ($0.05 per request). Nets Black-76 greeks across up to 6 Deribit BTC option legs and returns a spot×vol scenario P&L grid. Invalid legs or unknown instruments fail before payment.