HumanEndpoint MCP server

• Registry nameau.humanendpoint/humanendpointverified in the MCP registry

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

• Stateanswerschecked 2026-10-24
• Tools10
• Server calls itselfhumanendpoint
• Server version0.4.1
• Protocol version2025-06-18

On 2026-10-24 the server answered initialize and tools/list without a sign-in. First answer in 296 ms.

• Its tools do every use case we checked: verify real-world facts by phone; have humans carry out physical-world actions for agents; get human quality checks and judgement on agent output.
• Checked on 5 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: 5 so far
• What an agent can do with it3 of 3 use cases
• Answeredmeasuring5 of the 7 daily checks it takes to print a share
• Median first answer444 ms
• Space in an agent's context≈ 1,835 tokensthe definitions of all its tools (10), which an agent carries on every turn
• Tool definitionsB · 85 of 100
• Typed results0 of 10 toolsdeclared outputSchema: results come typed, read once

• Parameters without a description: in 9 of 10

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 →

• human_list_services

  Discover human capabilities for tasks software cannot complete alone: call a business, supplier or organisation; check current price, stock, lead time or availability by phone; obtain information that is only available by speaking to a…

• human_policy_preflight

  Check whether a proposed human task is eligible before requesting a quote or spending funds.

• human_request_quote

  Submit a request for human-reviewed terms for a real-world task whose cost depends on scope, feasibility, urgency or conditions. This sends the request into a HumanEndpoint workflow for review by a human operator, but does not commit…

• human_get_quote

  Retrieve a human-reviewed quote. Polling is always available as a fallback even when the quote request supplied callback_url. When status=offered, inspect the operator's service fee, expense authority and expiry. Creating the job accepts…

• human_create_job

  Accept the human-reviewed commercial terms using the quote_token and create the asynchronous HumanEndpoint job. Creating the job starts a workflow that may lead to human execution in the real world after required payment. Store the…

• human_get_job

  Retrieve job status, messages, history, payment state, expense accounting, result and evidence.

• human_list_expenses

  List pass-through expense requests for a secured job, including exact amount, payment status and receipt metadata.

• human_list_evidence

  List evidence artifacts and SHA-256 hashes for a secured human job. Download paths require the same job token.

• human_reply_to_job

  Send additional information to the human operator working on the job, including when the job is waiting for agent input.

• human_cancel_job

  Cancel an unpaid HumanEndpoint job immediately, or request cancellation of human work that may already be underway and may require refund or operator handling.