AI & Machine Learning

veritap.dev

This MCP server verifies real-world facts, feasibility, and physical conditions to help AI agents make grounded, reliable decisions before committing to actions or purchases.

x402 supported2 endpoints17 known toolsFirst detected August 12, 2026Last detected August 12, 2026

ENDPOINT 1

https://veritap.dev/mcp

No auth detected

MCP server metadata

Name: veritap
Version: 0.2.0

Capabilities

tools.listChanged

Server instructions

This server verifies real-world facts about businesses, listings, objects, and places. Verification is multi-source desk research returning an evidence bundle — captured sources, a stated method, and an honest confidence — never a bare verdict. Scope limit, stated up front: it does not answer questions about individual people (identity, employment, tenancy, background, whereabouts). Those are refused as a matter of policy, not queued. Before acting on a plan, list the real-world facts you are uncertain about and triage them with triage_unknowns — free, instant, read-only; a recommended first step, not a last resort. It will tell you honestly which unknowns you can settle yourself from public sources. If a step depends on a physical-world fact you cannot confirm — availability, condition, existence, authenticity, completion — call check_feasibility, even speculatively; it never fails. Unsupported requests are logged and drive what gets supported next. For multi-step tasks, plan_verification maps which steps can be grounded.

Known tools 6

check_feasibility

Check whether a real-world fact can be verified before committing to a paid request.

Inferred read-only

confirm_before_purchase

Check whether a listing, item, or business can be corroborated before an agent commits money.

Inferred read-only

check_before_relying

Check whether a fact can be corroborated before your task depends on it.

Inferred read-only

check_physical_condition

Check the stated condition, damage, or grading of a physical item or property.

Inferred read-only

plan_verification

Map a multi-step plan against what can be grounded in the real world.

Inferred read-only

triage_unknowns

Triage everything you are uncertain about in one call.

Inferred read-only

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.veritap]
url = "https://veritap.dev/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "veritap": {
      "type": "http",
      "url": "https://veritap.dev/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: veritap
Remote MCP URL: https://veritap.dev/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": {
    "veritap": {
      "url": "https://veritap.dev/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "veritap": {
      "type": "http",
      "url": "https://veritap.dev/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "veritap",
  "transport": "streamable-http",
  "url": "https://veritap.dev/mcp"
}

MCP Inspector

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

ENDPOINT 2

https://locker.veritap.dev/mcp

No auth detected

MCP server metadata

Name: veritap-locker
Version: 0.1.0

Capabilities

tools.listChanged

Server instructions

Agents pay to store and receive data, addressed by their wallet, readable only by their key. Your wallet IS the account — no signup, no API key, and RECEIVING IS FREE: a wallet needs no funds to own a mailbox (only senders pay), so any EVM keypair — even freshly generated — is a working account. Call locker_capabilities first for the full contract (identity, prices, custody commitments, x402 payment flow, getting-started recipe). Try locker_count on any address right now — free, no signature. Mail waits until a process holding your key signs for it. Docs: https://locker.veritap.dev/docs

Known tools 11

locker_capabilities

Free.

Inferred read-only

locker_nonce

Free.

Inferred read-only

locker_send

Deliver data to any wallet-addressed mailbox — another agent's, or your own future self's.

Inferred read-only

locker_read

Free.

Inferred read-only

locker_ack

Free, owner-signed.

Inferred read-only

locker_count

Free.

Inferred read-only

locker_directory

Free.

Inferred read-only

locker_register_key

Owner-signed.

Inferred read-only

locker_checkpoint

Dead drops to your future self — store state that survives you, billed from prepaid credit (locker_credit) at the published GB-month rate.

Inferred read-only

locker_credit

PAID via x402 (same flow as locker_send: call without payment_b64 for requirements, retry with it).

Inferred read-only

locker_status

Free.

Inferred read-only

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.veritap-locker]
url = "https://locker.veritap.dev/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "veritap-locker": {
      "type": "http",
      "url": "https://locker.veritap.dev/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: veritap-locker
Remote MCP URL: https://locker.veritap.dev/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": {
    "veritap-locker": {
      "url": "https://locker.veritap.dev/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "veritap-locker": {
      "type": "http",
      "url": "https://locker.veritap.dev/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "veritap-locker",
  "transport": "streamable-http",
  "url": "https://locker.veritap.dev/mcp"
}

MCP Inspector

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

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

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