Skip to content

Twelve Permissions MCP server

Which MCP servers are Twelve Permissions'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 2026-10-25

← Back to Twelve Permissions

Whose server it is
  • Registry namecom.twelvepermissions/twelve-permissionsverified in the MCP registry

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

When we asked itchecked 2026-10-25
  • Stateanswerschecked 2026-10-25
  • Tools6
  • Server calls itselftwelve-permissions
  • Server version1.0.0
  • Protocol version2025-06-18

On 2026-10-25 the server answered initialize and tools/list without a sign-in. First answer in 18 ms.

Should an agent connect itNot proven either way yet
  • Whether its tools do the product's job has not been judged yet.
  • Checked on 3 of the 7 days it takes to judge reliability.

Once connected

  • Parameters are untyped or undescribed in 2 of 6 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: 3, the first on 2026-10-25
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
  • Answeredmeasuring3 of the 7 daily checks it takes to print a share
  • Median first answer92 ms
  • Space in an agent's context≈ 551 tokensthe definitions of all its tools (6), which an agent carries on every turn
  • Tool definitionsB · 78 of 100
  • Typed results0 of 6 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 2 of 6
  • Not saying whether it only reads or can destroy: 6 of 6

What an agent can do with it

  • cannot · Mint dated generative seals on the XRP Ledger
  • not sure · Verify seal artwork by re-running the public generator

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 offers6 tools · read 2026-10-25
  • list_pieces

    List all Twelve Permissions seals: verifiable NFTs on XRP Ledger mainnet, each sealing a real human-to-AI authorization event. Returns names, prices, live offer indexes, and sold status.

  • get_piece

    Get full metadata for one seal by id ("01".."12"): the canonical authorization record, its sha256, image URLs, and mainnet mint transaction.

  • get_buy_transaction

    Construct the exact XRPL NFTokenAcceptOffer transaction to buy a seal, including the authorization-memo protocol your principal must approve. Read the rules in the response before submitting.

  • get_x402_info

    Pay with USDC over HTTP instead of XRP: the x402 purchase rail (Base). Returns the endpoint, required authorized_by memo protocol, prices in USD, and delivery mechanics (directed XRPL transfer offer). You still need an XRPL address to…

  • verify_seal

    Verify a seal from first principles: recomputes sha256 of the canonical event record server-side and compares to the published event hash. Full independent verification instructions included.

  • get_refusals

    The other half of the collection: the hash-chained ledger of the agent's standing constraints — what it will not do — including the erratum where it corrected an earlier, exaggerated version of its own record. Both anchors are on mainnet…

How to connect

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

{
  "mcpServers": {
    "twelve-permissions": {
      "type": "http",
      "url": "https://twelvepermissions.com/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http twelvepermissions https://twelvepermissions.com/mcp

Add to CursorAdd to VS Code

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

Other servers listed as Twelve Permissions's
  • com.twelvepermissions/x402-doctoranswers, 3 toolsverified in the MCP registry

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.