Skip to content
Blue Cap Technologies logo

Blue Cap Technologies MCP server

Which MCP servers are Blue Cap Technologies's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-21

← Back to Blue Cap Technologies

Whose server it is
  • Registry nameio.soundiq/bluecap-evidence-verifyverified in the MCP registry

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

When we asked itchecked 2026-10-21
  • Stateanswerschecked 2026-10-21
  • Tools7
  • Server calls itselfbluecap-public-capabilities
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-21 the server answered initialize and tools/list without a sign-in. First answer in 2187 ms.

Should an agent connect itConnect it
  • Its tools do every use case we checked: verify supplied structured evidence records and their references; validate JSON data against a supported JSON Schema subset; compute reproducible SHA-256 digests for supplied bytes.

Once connected

  • For "verify supplied structured evidence records and their references", the likely first call is evidence_verify.
  • For "validate JSON data against a supported JSON Schema subset", the likely first call is schema_validate.
  • For "compute reproducible SHA-256 digests for supplied bytes", the likely first call is hash_compute.
  • Parameters are untyped or undescribed in 7 of 7 tools: check arguments before calling.

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.

Measured dailydaily checks: 7, the first on 2026-10-21
  • INITE MCP score95 of 100answers 99 · does the job 100 · definitions 79 · context 100 · connects 100
  • What an agent can do with it3 of 3 use cases
  • Answered100% of days7 of 7 daily checks
  • Median first answer1086 ms
  • Space in an agent's context≈ 1,135 tokensthe definitions of all its tools (7), which an agent carries on every turn
  • Tool definitionsB · 79 of 100
  • Typed results7 of 7 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a type: in 2 of 7
  • Parameters without a description: in 7 of 7

What an agent can do with it

  • can do · verify supplied structured evidence records and their references
  • can do · validate JSON data against a supported JSON Schema subset
  • can do · compute reproducible SHA-256 digests for supplied bytes

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 (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 →

Tools it offers7 tools · read 2026-10-21
  • evidence_verify

    Verify supplied structured evidence and return a machine-readable verification result.

  • agent_wallet

    Provision a free Blue Cap machine wallet (Base Mainnet, USDC).

  • schema_validate

    Validate supplied structured data against a customer-supplied JSON Schema Draft 2020-12 supported subset. Returns a deterministic machine-readable validity result and bounded errors through a receipted external execution.

  • hash_compute

    Compute a SHA-256 digest for customer-supplied UTF-8 or base64-decoded bytes through a stable machine endpoint. Returns the reproducible digest through a receipted external execution.

  • evidence_verify_mpp

    Return a Stripe MPP payment link for this Blue Cap capability. POST the same arguments to paymentLink to receive the HTTP 402 challenge and complete payment.

  • schema_validate_mpp

    Return a Stripe MPP payment link for this Blue Cap capability. POST the same arguments to paymentLink to receive the HTTP 402 challenge and complete payment.

  • hash_compute_mpp

    Return a Stripe MPP payment link for this Blue Cap capability. POST the same arguments to paymentLink to receive the HTTP 402 challenge and complete payment.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "bluecap-evidence-verify": {
      "type": "http",
      "url": "https://machine.soundiq.io/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http soundiq https://machine.soundiq.io/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://machine.soundiq.io/mcp as a custom connector in the settings.

OpenAPI spec

1 paths, read 2026-10-21. 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.