Rill MCP server

• Addresshttps://mcp.userill.com/mcp/guestnot in the official registry: answered when asked

No entry in the official MCP registry names this server. It answered on userill.com when the Atlas asked at the address servers are usually mounted on, so it is the vendor's own. Clients and catalogues that list servers from the registry do not show it.

• Stateanswerschecked 2026-10-28
• Tools11
• Server calls itselfrill
• Server version0.1.0
• Protocol version2025-06-18

On 2026-10-28 the server answered initialize and tools/list without a sign-in. First answer in 132 ms.

• Whether its tools do the product's job has not been judged yet.
• Checked on 1 of the 7 days it takes to judge reliability.

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.

• INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
• Answeredmeasuring1 of the 7 daily checks it takes to print a share
• Median first answer141 ms
• Space in an agent's context≈ 1,381 tokensthe definitions of all its tools (11), which an agent carries on every turn
• Tool definitionsC · 68 of 100
• Typed results0 of 11 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 10 of 11
• Not saying whether it only reads or can destroy: 11 of 11

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 →

• rill_search_tools

  Search available Rill MCP tools

• rill_capabilities

  Read Rill agent capabilities, seed resources, and MCP tool list

• rill_resolve_handle

  Resolve @handle, handle FQDN, or agent FQDN to pay address and agents

• rill_list_directory

  List cached MPP/x402 pay URLs. Defaults to payment_ready=true (maps to spendable / Can pay), including the bazaar catalog. Pass payment_ready=false for the full research catalog. Prefer rill_discover for the curated can-pay set. Pass…

• rill_discover

  Discover curated can-pay MPP/x402 gates (source=rill,partner, payment_ready=1, Base by default). Prefer Accept seed_gate first. Rows include pay_url, probe_method, probe_amount_cents, optional body_hint → rill_pay_url.

• rill_register_agent

  Self-register via PoW and mint a bootstrap wallet key (rill_vw_* live or rill_vw_test_*). Session adopts the key.

• rill_pay_url

  Pay any HTTPS URL that speaks MPP or x402 (open-world Spend under VW policy). Prefer urls from rill_discover; optional directory_id uses catalog probe_method/hints. Default prefer_rail=auto uses Base/x402 when the gate offers it.

• rill_pay

  Background ledger: pay a Rill resource or transfer USD to a handle / agent FQDN

• rill_balance

  Seller balance + Connect flags (seller key) or VW allowance status (vw key)

• rill_verify_receipt

  Verify a Rill receipt

• rill_fund

  Fund an account wallet. action=checkout: Stripe Checkout URL for a human. action=intent: poll until paid. action=mock: local/dev only. Bootstrap agents: no owner JWT, uses session rill_vw_* (auto-registers when missing).