ME Human Capability is an MCP server with 37 tools an agent can call, among them me_approval, me_capabilities, me_catalog_capability_assets. It answers at https://mcp-production-ff29.up.railway.app/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 6 of 6 times since 11 September 2026; the last check, on 24 October 2026, succeeded.
Human judgment for AI agents: discover capabilities, get quotes, and track paid human tasks.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
me_approval | Create or decide a distinct APPROVE/REJECT/MODIFY authority gate. Inputs: operation, approval_id, payload |
me_capabilities | Discover agent-ready intelligence resource capabilities and execution semantics. Inputs: capability_code, include_stale |
me_catalog_capability_assets | Discover published, permissioned human-origin intelligence assets. Inputs: capability_code, limit |
me_catalog_human_capabilities | Discover active, machine-addressable human capability offers with pricing, performance, and rights. Inputs: capability_code, limit |
me_compare | Ask calibrated humans to compare two outputs. Inputs: prompt, option_a, option_b, criteria, required_responses, max_cost_cents |
me_demand_radar | Discover scored demand, shortages, and earning opportunities from the named ME Demand Radar component. Inputs: limit |
me_discover | Discover public ME capabilities and current availability. For Human Verify, call me_human_verify directly with objective, candidate and criterion; an x402-enabled MCP client handles payment. Then use me_human_verify_result with the returned Inputs: capability_code, max_price_cents, min_reliability, limit, cursor |
me_escalate | Escalate a known or unknown blocker; ME classifies and routes the required intervention. Inputs: organization_id, agent_key, operating_mandate_id, objective, blocker_description, blocker_type |
me_find_assets | Find published, permissioned human-origin intelligence assets. Alias for the asset catalog. Inputs: capability_code, limit |
me_find_capability | Find compatible verified human capability supply. Alias for the human capability catalog. Inputs: capability_code, limit |
me_find_resource | Find fresh, rights-aware intelligence resources from the generalized Resource Index. Inputs: capability_code, include_stale |
me_get_buyer_lifecycle | Inspect buyer activation, reorder, and repeat-spend metrics for the calling organization. |
me_get_demand_opportunities | Discover current capability demand and shortage opportunities observed by ME Demand Intelligence. Inputs: limit |
me_get_matches | Get the human-side economic matches selected for a funded request. Inputs: request_id |
me_get_provider_tasks | Inspect provider tasks created by ME for native spillover, generic supply, private workforces, or expert networks. Inputs: request_id |
me_get_request | Poll a durable request until terminal. Inputs: request_id |
me_get_routing_decision | Inspect the economic route decision, alternatives, and expected utility for a request. Inputs: request_id |
me_get_spending_mandate | Inspect the persistent machine spending mandate governing this organization or agent. Inputs: agent_key |
me_get_supply_forecast | Inspect forecast demand, supply, fill rate, shortage probability, and recommended compensation. Inputs: capability_code, limit |
me_get_supply_formation | Inspect the demand-triggered capability formation campaign when verified supply is short. Inputs: request_id |
me_get_supply_plan | Inspect the ME-native, private-workforce, and external-provider mix selected for a funded request. Inputs: request_id |
me_get_supply_quotes | Inspect normalized provider quotes considered by the federated liquidity router. Inputs: request_id |
me_human_verify | Purchase independent human review of a candidate against supplied criteria. Use for REVIEW/HOLD, conflicting evidence or uncertain outputs; non-sensitive evaluation only, not professional advice. Supply objective, candidate and criterion. T Inputs: objective, candidate, criterion, context, max_latency_seconds, target_reliability |
me_human_verify_result | Retrieve or briefly wait for an existing Human Verify result without another payment. Use only the private status_url returned by me_human_verify. It is a bearer credential: keep it private. Polling is bounded, at most once every five secon Inputs: status_url, wait_seconds |
me_license_capability_asset | Purchase one permitted use of a published human-origin capability asset and route the contributor share. Inputs: asset_slug, usage_type, max_cost_cents, request_id |
me_observe | Create or fulfill a fresh real-world observation capability request. Inputs: operation, observation_id, payload |
me_public_quote | Get a free signed quote bound to the complete task, capability, rights, and budget. Inputs: request_type, prompt, options, criteria, candidate_output, capability_code |
me_purchase_challenge | Advanced generic x402/MPP purchase interface for existing clients. For Human Verify, prefer the standard x402 HTTP endpoint returned by me_discover; no separate quote/challenge/execute tool sequence is required. Inputs: protocol, request, quote_token, idempotency_key |
me_purchase_execute | Execute an existing advanced generic x402/MPP purchase challenge. Human Verify normally uses a standard PAYMENT-SIGNATURE retry to its public HTTP endpoint instead. Inputs: payment_session_id, authorization, request, purchase_token, agent_id |
me_purchase_status | Poll an existing advanced generic purchase using its purchase_token. Standard Human Verify buyers instead GET the private status_url returned with 202; no purchase-token header is required. Inputs: payment_session_id, purchase_token |
me_qa_review | Create or execute a QA/adversarial preflight review. Inputs: operation, review_id, payload |
me_quote | Quote either a standard ME request or a partner-scoped Capability Exchange order before spending. Inputs: request_type, required_responses, target_reliability, max_latency_seconds, partner_id, organization_id |
me_receipt | Read a standardized Capability Receipt and provenance. Inputs: receipt_id |
me_resolve | Resolve a standard request or reserve and execute a server-driven Capability Exchange order. Inputs: prompt, capability_code, required_responses, max_cost_cents, supply_policy, order_id |
me_status | Read an asynchronous escalation or Capability Exchange order status. Inputs: kind, id |
me_submit_outcome | Submit real downstream truth for complementarity calibration. Inputs: request_id, final_answer, downstream_success, human_decision_accepted |
me_verify | Ask humans to verify an AI output against a criterion. Inputs: prompt, candidate_output, criteria, required_responses, max_cost_cents, supply_policy |
Every block below points at https://mcp-production-ff29.up.railway.app/mcp. Pick your client and copy.
claude mcp add --transport http me-human-capability https://mcp-production-ff29.up.railway.app/mcp
{
"mcpServers": {
"me-human-capability": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp-production-ff29.up.railway.app/mcp"]
}
}
}{
"mcpServers": {
"me-human-capability": {
"url": "https://mcp-production-ff29.up.railway.app/mcp"
}
}
}{
"servers": {
"me-human-capability": {
"type": "http",
"url": "https://mcp-production-ff29.up.railway.app/mcp"
}
}
}{
"context_servers": {
"me-human-capability": {
"url": "https://mcp-production-ff29.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"me-human-capability": {
"serverUrl": "https://mcp-production-ff29.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"me-human-capability": {
"url": "https://mcp-production-ff29.up.railway.app/mcp"
}
}
}name: ME Human Capability
version: 0.0.1
schema: v1
mcpServers:
- name: ME Human Capability
type: streamable-http
url: https://mcp-production-ff29.up.railway.app/mcp{
"mcpServers": {
"me-human-capability": {
"httpUrl": "https://mcp-production-ff29.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"me-human-capability": {
"type": "http",
"url": "https://mcp-production-ff29.up.railway.app/mcp"
}
}
}{
"mcpServers": {
"me-human-capability": {
"url": "https://mcp-production-ff29.up.railway.app/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp-production-ff29.up.railway.app%2Fmcp&type=streamable_http&id=me-human-capability&name=ME%20Human%20Capability
It answered our last check on 24 October 2026 in 287 ms. Over 6 checks since 11 September 2026 it answered 6. Status here comes from Neuronto's own probes, not from the publisher.
37, as returned by the server's own tools/list on 21 September 2026: me_approval, me_capabilities, me_catalog_capability_assets, me_catalog_human_capabilities, me_compare, me_demand_radar, me_discover, me_escalate, and 29 more.
It answered our last check on 24 October 2026 in 287 ms. Over 6 checks since 11 September 2026 it answered 6.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp-production-ff29.up.railway.app/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.github.somokpo. Endpoint host: mcp-production-ff29.up.railway.app. ARD identifier: urn:air:io.github.somokpo:mcp:me-human-capability.
First indexed 10 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.