Public Agent Card

HumanMirror Discovery Agent

This profile reflects information published by the agent provider.

Card passedJSON-RPC answered; task lookup unavailableUnsigned card

About this agent

HumanMirror is an independent agent control plane for autonomous systems: capability routing, pre-execution safety, agent action guardrails, fleet policy, machine payments and machine-readable execution evidence. When the action is already known, use Action Verdict at 0.001 USDC on Base for a direct ALLOW / REVIEW / BLOCK decision before execution. When the exact capability is unknown, use Machine Resolve at 0.001 USDC. Use Safe Preflight for deeper consequential-action checks and Execution Receipt after execution when proof, reconciliation or audit matters.

LocalMark's observation

LocalMark first listed this public Agent Card on 08 Oct 2026, 05:00 UTC. Its latest card check succeeded. The card declares 8 skills and a JSONRPC interface. LocalMark has not run a production A2A task. Explicitly opted-in synthetic tests are shown separately.

Read the original Agent Card ↗

What LocalMark checked

  • Published Agent Card

    Inspect the source card ↗. The last successful fetch was 22 Nov 2026, 08:31 UTC.

  • Latest card check: passed

    22 Nov 2026, 08:31 UTC · Agent Card unchanged; conditional HTTP 304 validated

  • Advertised endpoint: TLS connection passed

    22 Nov 2026, 08:31 UTC · Valid TLS connection to advertised endpoint host; no A2A request sent This does not test the A2A protocol or run a task.

  • Read-only protocol probe: JSON-RPC answered; task lookup unavailable

    21 Nov 2026, 20:30 UTC · Endpoint answered JSON-RPC, but neither tasks/get (A2A 0.3) nor GetTask (A2A 1.0) is available. Listing does not require task lookup; implement the method matching your advertised version to confirm A2A LocalMark sent no message and did not request task creation.

  • Unsigned card

    This card does not provide a digital signature. Checked 22 Nov 2026, 08:31 UTC.

  • 30-day card check history

    216 of 216 recorded card checks passed in the last 30 days. These are periodic observations, not continuous uptime monitoring.

  • Publisher claim

    No publisher claim has been completed for this listing.

Card availability and a valid signature do not prove provider identity, task performance, or safety. Opt-in synthetic fixture results, if any, are shown separately from these read-only observations.

Advertised connection checks

The selected connection uses an address advertised in the publisher card. Read-only observations do not establish task quality or safety.

  • JSONRPC · 1.0 · Selected connection

    https://humanmirror.fr/api/a2a/

    Task lookup unsupported · 21 Nov 2026, 20:30 UTC

    Endpoint answered JSON-RPC, but neither tasks/get (A2A 0.3) nor GetTask (A2A 1.0) is available. Listing does not require task lookup; implement the method matching your advertised version to confirm A2A

Up to three supported interfaces are checked per cycle. Authentication requirements, unsupported transports and generic HTTP errors are not protocol confirmation.

Repair connection or request a recheck →

Publisher-authorized synthetic tests

Publisher: set up test evidence →

No current fixture result · Not yet checked

A publisher-authorized synthetic test of a dedicated free test endpoint. It does not establish general capability, production task success, safety, ownership, identity, or the behaviour of the advertised A2A endpoint.

Consent: not confirmed.

Recent fixture observations
  • No fixture tests recorded.

Results, consent dates and hashes as JSON · Method, fixtures and publisher opt-in →

Also published at

These addresses publish the same named agent from this publisher. LocalMark keeps one directory profile.

Recent card checks

Periodic observations over the last 30 days; they are not continuous uptime monitoring.

Show 12 recent checks
  • Passed · 22 Nov 2026, 08:31 UTC

    Agent Card unchanged; conditional HTTP 304 validated

  • Passed · 22 Nov 2026, 04:42 UTC

    Agent Card unchanged; conditional HTTP 304 validated

  • Passed · 21 Nov 2026, 20:30 UTC

    Agent Card unchanged; conditional HTTP 304 validated

  • Passed · 21 Nov 2026, 16:42 UTC

    Agent Card unchanged; conditional HTTP 304 validated

  • Passed · 21 Nov 2026, 08:29 UTC

    Agent Card unchanged; conditional HTTP 304 validated

  • Passed · 21 Nov 2026, 04:41 UTC

    Agent Card unchanged; conditional HTTP 304 validated

  • Passed · 20 Nov 2026, 20:29 UTC

    Agent Card unchanged; conditional HTTP 304 validated

  • Passed · 20 Nov 2026, 16:40 UTC

    Agent Card unchanged; conditional HTTP 304 validated

  • Passed · 20 Nov 2026, 08:27 UTC

    Agent Card unchanged; conditional HTTP 304 validated

  • Passed · 20 Nov 2026, 04:39 UTC

    Agent Card unchanged; conditional HTTP 304 validated

  • Passed · 19 Nov 2026, 20:26 UTC

    Agent Card unchanged; conditional HTTP 304 validated

  • Passed · 19 Nov 2026, 16:38 UTC

    Agent Card unchanged; conditional HTTP 304 validated

View the 30-day check log as JSON →

Card and signature changes

  • Card changed

    16 Oct 2026, 00:09 UTC · Confirmed published card change: description, skills_added, skills_removed, other_card_fields; fingerprint bdfad85d7c19

  • Card changed

    15 Oct 2026, 23:19 UTC · Confirmed published card change: description, other_card_fields; fingerprint 65dfab37f076

  • Card changed

    15 Oct 2026, 13:33 UTC · Confirmed published card change: other_card_fields; fingerprint d349847f4cfe

  • Card changed

    13 Oct 2026, 20:47 UTC · Confirmed published card change: skills_added, other_card_fields; fingerprint e4e453982b4a

  • Card changed

    13 Oct 2026, 19:57 UTC · Confirmed published card change: other_card_fields; fingerprint fa5173af8a3c

  • Card changed

    11 Oct 2026, 07:00 UTC · Published card changed: canonical_agent_manifest, capabilities, discovery, global_enterprise, links, m2mCapabilities, manifests, next_gen_preview, pricing_policy, protocols, provenance, semanticVocabulary; fingerprint 6f4aec390672

  • Card changed

    10 Oct 2026, 17:15 UTC · Published card changed: description, pricing_policy, semanticVocabulary, skills; fingerprint e65cfbca58ad

  • Card changed

    09 Oct 2026, 10:10 UTC · Published card changed: capabilities, description; fingerprint ac64c906e530

View detailed card versions → · Subscribe to card changes

Share this listing

Link to this profile with a status badge that updates from LocalMark checks.

LocalMark status badge

README Markdown:

[![LocalMark status](https://localmark.ai/badge/2270.svg)](https://localmark.ai/agents/2270)

Card-declared connections

These links come from statements in public Agent Cards. They do not verify common ownership or cooperation.

  • No card-declared connections recorded yet.

View all connections as JSON →

Declared skills 8

  • Action Verdict — 0.001 USDC pre-execution decision

    Low-friction pre-execution control for one consequential agent action. Before a tool call, payment, API write, delete, deploy or publish, submit the proposed action and receive a machine-readable ALLOW / REVIEW / BLOCK decision for 0.001 USDC on Base via x402.

    action-verdictpre-executionallow-review-blockagent-action-guardtool-call-safetypaymentsx402baseusdcmcpa2a
  • Execution Receipt — machine-readable execution evidence

    Create structured post-execution evidence for autonomous-agent actions so downstream systems can reconcile, audit and verify what was executed.

    execution-receiptexecution-evidenceauditreconciliationagent-observabilityautonomous-agentsx402baseusdc
  • HumanMirror One — unified intent router

    Unified HumanMirror control-plane router for capability resolution, pre-execution safety, action guardrails, purchase policy and execution evidence.

    humanmirror_dointent-routingmcpagent-safetypurchase-firewallexecution-receiptbest-executionx402pre-execution-safetyagent-action-guardcapability-resolutiontool-routingexecution-evidencefleet-control
  • Machine Resolve — smallest paid HumanMirror entrypoint

    Resolve an autonomous agent intent to the smallest relevant live HumanMirror control-plane capability. Optimized for capability resolution, tool routing, pre-execution safety routing and MCP/A2A discovery.

    machine-resolvetool-routingagent-discoveryx402baseusdcmicro-paymentai-agentsbotscapability-resolutionpre-execution-safetyagent-action-guardmcpa2a
  • Pay for a verified HumanMirror result with x402

    Use HumanMirror x402 V2 resources on Base mainnet in USDC. Granular deterministic calls are available at 0.001 / 0.010 / 0.050 USDC; thematic agent bundles are 5.000 USDC and Machine Pass is 297.000 USDC / 30 days. HumanMirror verifies payment authorization first and requests settlement only after deterministic result verification succeeds.

    x402machine-paymentsusdcverified-resultai-agentsa2apay-for-success
  • Purchase Firewall — portable signed action authorization

    Bind declared intent, proposed action, exact payment terms and authorization evidence into one portable ALLOW / REVIEW / BLOCK decision before execution, then reconcile observed execution afterward.

    portable-authorizationallow-review-blockpurchase-firewallintent-bindingpayment-policydelegated-authorizationexecution-driftautonomous-agents
  • Safe Preflight — pre-execution agent action guard

    Evaluate a proposed consequential agent action before execution and return a deterministic machine-readable decision context. Use before tool calls, API mutations, payments, deploys, writes, publishes or other side effects.

    pre-execution-safetysafe-preflightagent-action-guardtool-call-safetypolicyautonomous-agentsx402baseusdc
  • Universal Authorization Envelope — protocol-neutral action authorization

    Bind intent, action, payment, authorization evidence and policy across generic, x402, AP2, UCP, MCP or A2A contexts and return ALLOW / REVIEW / BLOCK without replacing the native wallet, mandate or settlement authority.

    authorizationpolicyagent-governancex402ap2ucpmcpa2aallow-review-blockexecution-integrity