Security & Testing

provebeforeact.com

Creates and verifies blockchain certifications for files with confidence scoring.

1 endpoint13 known toolsFirst detected August 10, 2026Last detected August 10, 2026

ENDPOINT 1

https://provebeforeact.com/mcp

No auth detected

MCP server metadata

Name: prove-before-act
Version: 1.3.0

Capabilities

tools.listChangedresources.listChanged

Known tools 13

register_trial

START HERE if you have no API key.

Inferred read-only

certify_file

Create a blockchain certification for a file.

Potential side effects

certify_with_confidence

Create a staged blockchain certification with a confidence score.

Potential side effects

verify_proof

Verify an existing xproof certification.

Inferred read-only

get_proof

Retrieve a proof in structured JSON or Markdown format.

Inferred read-only

discover_services

Discover available xproof certification services, pricing, and capabilities.

Inferred read-only

audit_agent_session

Certify an AI agent's work session on the MultiversX blockchain BEFORE executing any critical action (trade, deploy, data access).

Potential side effects

check_attestations

Check domain-specific attestations for an AI agent wallet on xproof.

Inferred read-only

investigate_proof

Reconstruct the full 4W audit trail for a contested agent action.

Inferred read-only

submit_outcome

Submit the actual outcome for a decision previously anchored with metadata.confidence_level.

Inferred read-only

get_calibration

Query an agent's calibration quality over time: mean confidence gap, variance, bias label (overconfident / underconfident / calibrated), and per-decision time series.

Inferred read-only

check_coherence

Anchor your agent's reasoning as an immutable WHY proof BEFORE executing an action.

Inferred read-only

require_coherence_anchor

Policy gate: verify a valid, unexpired coherence anchor (WHY proof) exists for a given intent BEFORE allowing an action to execute.

Potential side effects

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.prove-before-act]
url = "https://provebeforeact.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "prove-before-act": {
      "type": "http",
      "url": "https://provebeforeact.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: prove-before-act
Remote MCP URL: https://provebeforeact.com/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "prove-before-act": {
      "url": "https://provebeforeact.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "prove-before-act": {
      "type": "http",
      "url": "https://provebeforeact.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "prove-before-act",
  "transport": "streamable-http",
  "url": "https://provebeforeact.com/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for provebeforeact.com was fetched 2026-08-21T17:35:41.402Z.

Trust status Neutral

provebeforeact.com is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.