Skip to content
satledger logo

satledger MCP server

Which MCP servers are satledger'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 2026-10-27

← Back to satledger

Whose server it is
  • Registry nameorg.satledger/timestamp-receiptverified in the MCP registry

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

When we asked itchecked 2026-10-27
  • Stateanswerschecked 2026-10-27
  • Tools14
  • Server calls itselfsatledger
  • Server version0.21.4
  • Protocol version2025-06-18

On 2026-10-27 the server answered initialize and tools/list without a sign-in. First answer in 516 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: record agent credit grants and spending as signed events; export a signed usage bundle for customers; let customers verify agent action logs offline.
  • Checked on 6 of the 7 days it takes to judge reliability.

Once connected

  • For "export a signed usage bundle for customers", the likely first call is export_agent.
  • create_agent change data without a sign-in: anyone with the address can call them.
  • Parameters are untyped or undescribed in 9 of 14 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: 6, the first on 2026-10-27
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 6 so far
  • What an agent can do with it3 of 3 use cases
  • Answeredmeasuring6 of the 7 daily checks it takes to print a share
  • Median first answer518 ms
  • Space in an agent's context≈ 2,224 tokensthe definitions of all its tools (14), which an agent carries on every turn
  • Tool definitionsC · 73 of 100
  • Typed results0 of 14 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 9 of 14
  • Not saying whether it only reads or can destroy: 14 of 14

What an agent can do with it

  • can do · record agent credit grants and spending as signed events
  • can do · export a signed usage bundle for customers
  • can do · let customers verify agent action logs offline

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

  • Tools that change data, on a server that answers without a sign-in: create_agent

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 offers14 tools · read 2026-10-27
  • timestamp_receipt

    Submit a SHA-256 digest and receive a Time-Stamp Authority's signed RFC 3161 token over it: evidence that the data you hashed existed at that time, verifiable against the authority without trusting or contacting this service. Hash your…

  • provision_workspace

    Buy a workspace: a tamper-evident usage and action ledger for your agents, every event ed25519-signed and hash-chained, with an export your own customers verify offline. Pay over x402 in _meta[x402/payment]: 0.50 USDC for 2,500 units…

  • top_up_workspace

    Add units to a workspace you already hold. Send its API key in _meta[satledger/api-key] (or the api_key argument) and the payment in _meta[x402/payment]: 0.50 USDC for 2,500 units (starter), 15.00 USDC for 100,000 units (block). The units…

  • create_agent

    Create an agent in your workspace: a named ledger whose every event is ed25519-signed and hash-chained. `initial_credits` mints supply to the workspace issuer, not to the agent - fund_agent moves credits across when you need usage…

  • record_action

    Append what an agent did - a tool call, a decision, a message - as a signed, hash-chained entry. This is the thing the workspace is for. Costs 1 unit. Authenticate with the workspace key in _meta[satledger/api-key].

  • fund_agent

    Move credits from the workspace issuer to an agent's own account, so record_usage can burn them. Costs 1 unit. Authenticate with the workspace key in _meta[satledger/api-key].

  • record_usage

    Burn credits from an agent's account, as a signed ledger event. Costs 1 unit. Authenticate with the workspace key in _meta[satledger/api-key].

  • anchor_agent

    Ask a public RFC 3161 Time-Stamp Authority to sign the agent's current state. The one fact here the operator cannot manufacture: a timestamp cannot be issued for a time that has passed. An unchanged state returns the anchor it already…

  • export_agent

    Build the export bundle, run the customer-side verifier over it and return the summary plus the URL of the archive (HTTP, X-API-Key, free). Pass expect_action_head / expect_action_count from state YOU kept to check completeness. Free…

  • list_agents

    Every agent in your workspace. Free. Authenticate with the workspace key in _meta[satledger/api-key].

  • describe_agent

    Current state: root id, state hash, event count, balance. Free. Authenticate with the workspace key in _meta[satledger/api-key].

  • list_actions

    The agent's action log, with its head hash. Free. Authenticate with the workspace key in _meta[satledger/api-key].

  • list_anchors

    Every anchor commitment recorded for the agent. Free. Authenticate with the workspace key in _meta[satledger/api-key].

  • workspace_balance

    Units remaining and what each operation costs. Free, so you can plan before you are refused. Authenticate with the workspace key in _meta[satledger/api-key].

How to connect

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

{
  "mcpServers": {
    "timestamp-receipt": {
      "type": "http",
      "url": "https://api.satledger.org/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http satledger https://api.satledger.org/mcp

Add to CursorAdd to VS Code

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

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.