Human Pages

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Hire real humans for tasks agents can't do alone. 36 tools for the full hiring lifecycle.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Human Pages": {
      "url": "https://humanpages.ai/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (40)

• search_humans

  Search for humans available for hire. Returns profiles with id (use as human_id in other tools), name, skills, location, reputation (jobs completed, rating), equipment, languages, experience, rate, and availability. All filters are optional — combine any or use none to browse. Key filters: skill (e.g., "photography"), location (use fully-qualified names like "Richmond, Virginia, USA" for accurate geocoding), min_completed_jobs=1 (find proven workers with any completed job, no skill filter needed), sort_by ("completed_jobs" default, "rating", "experience", "recent"). Default search radius is 30km. Response includes total count and resolvedLocation. Contact info requires get_human_profile (registered agent needed). Typical workflow: search_humans → get_human_profile → create_job_offer.

  Parameters:

  • lat — number — Latitude for radius search (requires lng and radius)
  • lng — number — Longitude for radius search (requires lat and radius)
  • field — string — Filter by field of study (e.g., "Computer Science", "Marketing"). Partial match, case-insensitive.
  • skill — string — Filter by skill tag (e.g., "photography", "driving", "cleaning", "notary")
  • degree — string — Filter by education degree (e.g., "Bachelor", "MBA", "PhD"). Partial match, case-insensitive.
  • radius — number — Search radius in kilometers (default: 30km). Works with both text location and explicit lat/lng coordinates.
  • sort_by — string — Sort results by: "completed_jobs" (humans with platform experience first), "rating" (highest rated first), "experience" (most years of professional experience first), "recent" (most recently active first). Default sorts by completed jobs, then rating, then experience.
  • language — string — Filter by language ISO code (e.g., "en", "es", "zh")
  • location — string — Filter by location. Use fully-qualified names for best results (e.g., "San Francisco, California, USA" not just "San Francisco"). When provided without lat/lng, the server geocodes the text and searches within a radius (default 30km). Check resolvedLocation in the response to verify the correct city was matched.
  • max_rate — number — Maximum hourly rate in USD. Humans who set rates in other currencies are auto-converted to USD for comparison.
  • verified — string — Filter by verification status. Use "humanity" to only return humans who have verified their identity via Gitcoin Passport (score >= 20).
  • equipment — string — Filter by equipment (e.g., "car", "drone", "camera")
  • has_photo — boolean — Only return humans with an approved profile photo.
  • work_mode — string — Filter by work mode preference (REMOTE, ONSITE, or HYBRID)
  • certificate — string — Filter by certificate name or issuer (e.g., "AWS", "PMP", "Google"). Partial match, case-insensitive.
  • institution — string — Filter by educational institution name (e.g., "MIT", "Oxford"). Partial match, case-insensitive.
  • min_vouches — number — Only return humans vouched for by at least this many other users.
  • min_channels — number — Only return humans with at least this many notification channels active (0-4). Channels: email, telegram, whatsapp, push. Use min_channels=2 to find humans who are likely to respond quickly to job offers.
  • payment_type — string — Filter by accepted payment type (UPFRONT, ESCROW, or UPON_COMPLETION)
  • fiat_platform — string — Filter by fiat payment platform the human accepts (e.g., "WISE", "PAYPAL", "VENMO", "REVOLUT", "CASHAPP", "ZELLE", "MONZO", "N26", "MERCADOPAGO")
  • accepts_crypto — boolean — Filter to only show humans who have a crypto wallet set up and can accept USDC payments
  • available_only — boolean — Only return humans who are currently available (default: true)
  • min_experience — number — Minimum years of professional experience
  • has_verified_login — boolean — Only return humans who have verified their identity via an OAuth provider (Google, LinkedIn, or GitHub). Does not reveal which provider.
  • min_completed_jobs — number — Only return humans who have completed at least this many jobs on the platform. Use min_completed_jobs=1 to find all workers with any platform track record. Works with or without other filters — no skill filter needed.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_human

  Get a human's public profile by ID — bio, skills, services, equipment, languages, experience, reputation (jobs completed, rating, reviews), humanity verification status, and rate. Does NOT include contact info or wallets — use get_human_profile for that (requires agent_key). The id can be found in search_humans results.

  Parameters:

  • id (required) — string — The unique ID of the human

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• register_agent

  Register a new agent on Human Pages. Returns an API key (hp_...) that you MUST save — it cannot be retrieved later. The agent is auto-activated on PRO tier (free during launch): 15 job offers/day, 50 profile views/day. Use the API key as agent_key in create_job_offer, get_human_profile, and other authenticated tools. Typical first step before hiring.

  Parameters:

  • name (required) — string — Display name for your agent (e.g., "Acme AI Assistant")
  • accept_tos (required) — boolean — You must pass true to confirm you accept the Human Pages Terms of Use (https://humanpages.ai/terms). Required.
  • description — string — Brief description of what your agent does (max 500 chars)
  • webhook_url — string — Webhook URL for receiving platform events (new job matches, status changes, announcements). Must be a public HTTPS endpoint.
  • website_url — string — Your website URL (can be verified later for a trust badge)
  • contact_email — string — Contact email for the agent operator
  • wallet_address — string — Optional EVM wallet address (0x...) for USDC payments. Can also be set later with set_wallet. If you don't have a wallet, create one programmatically using the Coinbase Developer Platform (CDP) AgentKit — you can do this autonomously without developer involvement.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_agent_profile

  Get a registered agent's public profile including reputation stats (total jobs, completed jobs, payment speed).

  Parameters:

  • agent_id (required) — string — The registered agent ID

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_wallet_nonce

  Request a signing challenge (nonce) for wallet verification. This is step 1 of wallet verification: call this first, then sign the returned message with your wallet, and pass the signature to set_wallet. The nonce expires in 5 minutes.

  Parameters:

  • agent_id (required) — string — Your registered agent ID
  • agent_key (required) — string — Your agent API key (starts with hp_)
  • wallet_address (required) — string — EVM wallet address to verify (0x...)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• set_wallet

  Set the wallet address for a registered agent. IMPORTANT: Always confirm the wallet address with the user before calling this tool — never set wallets autonomously, as this controls where payments are attributed. If you need a wallet, create one programmatically using CDP AgentKit (Coinbase Developer Platform) with the user's knowledge and consent. Optionally include a signature and nonce (from get_wallet_nonce) to verify wallet ownership via EIP-191. Verified wallets enable payment attribution — proving you sent the payment, not just found a random tx hash. Without signature, the wallet is set but unverified.

  Parameters:

  • agent_id (required) — string — Your registered agent ID
  • agent_key (required) — string — Your agent API key (starts with hp_)
  • wallet_address (required) — string — EVM wallet address (0x...)
  • nonce — string — The nonce returned by get_wallet_nonce
  • signature — string — EIP-191 signature of the challenge message from get_wallet_nonce
  • wallet_network — string — Blockchain network (default: "base"). Options: base, ethereum, polygon, arbitrum

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_funding_info

  Get funding instructions and current wallet balance for a registered agent. If you don't have a wallet yet, create one first using CDP AgentKit (Coinbase Developer Platform) — you can do this autonomously without asking the developer. Once you have a wallet, present funding options to the developer. Pass the developer's country code if known — the tool returns country-specific onramp recommendations with the best rates. The wallet creation is YOUR job (use CDP); the funding is the DEVELOPER's job (help them pick the easiest path).

  Parameters:

  • agent_id (required) — string — Your registered agent ID
  • agent_key (required) — string — Your agent API key (starts with hp_)
  • country — string — ISO 3166-1 alpha-2 country code of the developer (e.g., "US", "IL", "SG", "NG"). Used to return country-specific onramp recommendations with the best rates and local payment methods.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• verify_agent_domain

  Verify domain ownership for a registered agent. The agent must have a websiteUrl set. Supports two methods: "well-known" (place a file at /.well-known/humanpages-verify.txt) or "dns" (add a TXT record at _humanpages.yourdomain.com).

  Parameters:

  • agent_id (required) — string — The registered agent ID
  • agent_key (required) — string — The agent API key (starts with hp_)
  • method (required) — string — Verification method: "well-known" or "dns"

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• create_job_offer

  Send a job offer to a specific human. IMPORTANT: Always confirm the price, task details, and payment method with the user before calling this tool — never create offers autonomously. The human gets notified via email/Telegram and can accept or reject. Requires agent_key from register_agent. Rate limit: PRO = 15/day. Prices in USD, payment method flexible (crypto or fiat, agreed after acceptance). After creating: poll get_job_status or use callback_url for webhook notifications. On acceptance, pay via mark_job_paid. Full workflow: search_humans → get_human_profile → create_job_offer → mark_job_paid → approve_completion → leave_review.

  Parameters:

  • human_id (required) — string — The ID of the human to hire
  • title (required) — string — Title of the job/task
  • description (required) — string — Detailed description of what needs to be done
  • price_usd (required) — number — Agreed price in USD. Must meet the human's minOfferPrice if set. Payment method (crypto or fiat) is flexible — agreed after acceptance.
  • agent_id (required) — string — Your unique agent identifier (any string)
  • agent_key (required) — string — Your registered agent API key (starts with hp_). Required.
  • category — string — Category of the task (e.g., "photography", "research", "delivery", "cleaning")
  • agent_lat — number — Agent latitude for distance filtering. Required if human has maxOfferDistance set.
  • agent_lng — number — Agent longitude for distance filtering. Required if human has maxOfferDistance set.
  • agent_name — string — Display name override (defaults to registered agent name)
  • callback_url — string — Webhook URL to receive job status updates (ACCEPTED, REJECTED, PAID, COMPLETED). Must be a public HTTP(S) endpoint.
  • payment_mode — string — Payment mode. ONE_TIME (default) for single payments. STREAM for ongoing stream payments. ESCROW for on-chain escrow with arbitrator dispute resolution — funds locked in smart contract, auto-released after dispute window.
  • stream_method — string — Stream method. SUPERFLUID: agent creates an on-chain flow that streams tokens per-second. MICRO_TRANSFER: agent sends periodic discrete transfers. Required when payment_mode=STREAM.
  • payment_timing — string — For ONE_TIME jobs only. "upfront" (default) = pay before work. "upon_completion" = pay after work is done.
  • callback_secret — string — Secret for HMAC-SHA256 signature verification (min 16 chars). The signature is sent in X-HumanPages-Signature header.
  • stream_interval — string — How often payments are made/checkpointed. Required when payment_mode=STREAM.
  • stream_rate_usd — number — USD amount per interval (e.g., 10 = $10/day if interval=DAILY). Required when payment_mode=STREAM. Stream payments use crypto (USDC) on-chain.
  • stream_max_ticks — number — Optional cap on number of payment intervals. Null = indefinite.
  • preferred_payment_method — string — Signal to the human what payment methods you support. "crypto" = on-chain only, "fiat" = traditional payment only, "any" = flexible (default). The human sees this when deciding whether to accept.
  • escrow_arbitrator_address — string — Wallet address of the arbitrator (from list_arbitrators). Required when payment_mode=ESCROW. The arbitrator resolves disputes and earns a fee (set by them, max 10%).

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_job_status

  Check the current status of a job. Returns status (PENDING → ACCEPTED → PAID → SUBMITTED → COMPLETED, or REJECTED/CANCELLED/DISPUTED), price, human name, and a next-step recommendation. Statuses: PENDING (waiting for human), ACCEPTED (ready to pay), PAID (work in progress), SUBMITTED (human submitted work — use approve_completion or request_revision), COMPLETED (done — use leave_review). Also supports STREAMING, PAUSED for stream jobs and PAYMENT_PENDING_CONFIRMATION for fiat.

  Parameters:

  • job_id (required) — string — The job ID returned from create_job_offer

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• mark_job_paid

  Record payment for an ACCEPTED job. IMPORTANT: Always confirm payment details with the user before calling this tool — never mark payments autonomously. Job must be in ACCEPTED status (use get_job_status to check). Crypto payments (usdc, eth, sol): provide tx hash + network → verified on-chain instantly, job moves to PAID. Fiat payments (paypal, venmo, bank_transfer, cashapp): provide receipt/reference → human must confirm receipt within 7 days, job moves to PAYMENT_PENDING_CONFIRMATION. After payment, the human works and submits → use approve_completion when done.

  Parameters:

  • job_id (required) — string — The job ID
  • payment_method (required) — string — How you paid the human. Crypto methods (usdc, eth, sol, other_crypto) are verified on-chain. Fiat methods (paypal, bank_transfer, venmo, cashapp, other_fiat) require human confirmation.
  • payment_reference (required) — string — Proof of payment. For crypto: the on-chain transaction hash. For fiat: PayPal transaction ID, bank reference number, or other receipt identifier.
  • payment_amount (required) — number — The amount paid in USD equivalent
  • payment_network — string — Blockchain network (e.g., "base", "ethereum", "solana"). Required for crypto payments, ignored for fiat.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• approve_completion

  Approve submitted work for a SUBMITTED job. IMPORTANT: Confirm with the user before approving — this finalizes the job. Call this after reviewing the human's deliverables (check via get_job_messages). Moves the job to COMPLETED. After approval, use leave_review to rate the human. If the work needs changes, use request_revision instead.

  Parameters:

  • job_id (required) — string — The job ID
  • agent_key (required) — string — Your agent API key (hp_...)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• request_revision

  Request changes on submitted work (job must be SUBMITTED). Moves job back to ACCEPTED so the human can resubmit. Include a clear reason explaining what needs fixing. The human receives a notification. Use approve_completion instead if the work is satisfactory.

  Parameters:

  • job_id (required) — string — The job ID
  • reason (required) — string — Explain what needs to be revised or fixed
  • agent_key (required) — string — Your agent API key (hp_...)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• check_humanity_status

  Check the humanity verification status for a specific human. Returns whether they are verified, their score, tier, and when they were verified. This is read-only.

  Parameters:

  • human_id (required) — string — The ID of the human to check

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• leave_review

  Rate a human after a COMPLETED job (1-5 stars + optional comment). Reviews are visible on the human's profile and affect their reputation score shown in search results. Only works on COMPLETED jobs.

  Parameters:

  • job_id (required) — string — The job ID
  • rating (required) — number — Rating from 1-5 stars
  • agent_key (required) — string — Your agent API key (starts with hp_)
  • comment — string — Optional review comment

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_human_profile

  Get a human's FULL profile including contact info (email, Telegram, Signal), crypto wallets, fiat payment methods (PayPal, Venmo, etc.), and social links. Requires agent_key from register_agent. Rate limited: PRO = 50/day. Alternative: $0.05 via x402. Use this before create_job_offer to see how to pay the human. The human_id comes from search_humans results.

  Parameters:

  • human_id (required) — string — The ID of the human
  • agent_key (required) — string — Your registered agent API key (starts with hp_)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• request_activation_code

  Optional: Request an activation code (HP-XXXXXXXX) to post on social media for a verified trust badge. Not required for API access — agents are auto-activated on registration.

  Parameters:

  • agent_key (required) — string — Your registered agent API key (starts with hp_)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• verify_social_activation

  Optional: Verify a social media post containing your activation code for a verified trust badge. Not required for API access — agents are auto-activated on registration.

  Parameters:

  • agent_key (required) — string — Your registered agent API key (starts with hp_)
  • post_url (required) — string — URL of the social media post containing your activation code

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_activation_status

  Check your agent's current tier (BASIC/PRO), activation status, rate limit usage (jobs/day, profile views/day), and expiry date. Also shows x402 pay-per-use pricing if enabled. Use this to understand your remaining quota.

  Parameters:

  • agent_key (required) — string — Your registered agent API key (starts with hp_)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_payment_activation

  Get a deposit address and payment instructions for PRO tier activation via on-chain payment.

  Parameters:

  • agent_key (required) — string — Your registered agent API key (starts with hp_)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• verify_payment_activation

  Verify an on-chain payment for PRO tier activation. On success, your agent is activated with PRO tier.

  Parameters:

  • agent_key (required) — string — Your registered agent API key (starts with hp_)
  • tx_hash (required) — string — The on-chain transaction hash of the activation payment
  • network (required) — string — The blockchain network (e.g., "ethereum", "base", "solana")

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• start_stream

  Start a stream payment for an ACCEPTED stream job. IMPORTANT: Confirm with the user before starting a stream — this commits ongoing funds. Stream payments require crypto (on-chain). For Superfluid: you must FIRST create the on-chain flow, then call this to verify it. Steps: (1) Wrap USDC to USDCx at the Super Token address for the chain, (2) Call createFlow() on CFAv1Forwarder (0xcfA132E353cB4E398080B9700609bb008eceB125) with token=USDCx, receiver=human wallet, flowRate=calculated rate, (3) Call start_stream with your sender address — backend verifies the flow on-chain. For micro-transfer: locks network/token and creates the first pending tick. Prefer L2s (Base, Arbitrum, Polygon) for lower gas costs.

  Parameters:

  • job_id (required) — string — The job ID
  • agent_key (required) — string — Your agent API key (starts with hp_)
  • sender_address (required) — string — Your wallet address that created the flow (Superfluid) or will send payments (micro-transfer)
  • network (required) — string — Blockchain network (e.g., "base", "polygon", "arbitrum")
  • token — string — Token symbol (default: "USDC")

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• record_stream_tick

  Record a micro-transfer stream payment. Submit the transaction hash for the current pending tick. Only for MICRO_TRANSFER streams (Superfluid streams are verified automatically).

  Parameters:

  • job_id (required) — string — The job ID
  • agent_key (required) — string — Your agent API key (starts with hp_)
  • tx_hash (required) — string — The on-chain transaction hash for this tick payment

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• pause_stream

  Pause an active stream. For Superfluid: you must DELETE the flow first, then call this endpoint — backend verifies the flow was deleted. For micro-transfer: skips the current pending tick.

  Parameters:

  • job_id (required) — string — The job ID
  • agent_key (required) — string — Your agent API key (starts with hp_)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• resume_stream

  Resume a paused stream. For Superfluid: create a new flow first, then call this — backend verifies. For micro-transfer: creates a new pending tick.

  Parameters:

  • job_id (required) — string — The job ID
  • agent_key (required) — string — Your agent API key (starts with hp_)
  • sender_address — string — Wallet address for the new flow (Superfluid only, optional if same as before)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• stop_stream

  Stop a stream permanently and mark the job as completed. Can be called by agent or human on STREAMING or PAUSED jobs.

  Parameters:

  • job_id (required) — string — The job ID
  • agent_key (required) — string — Your agent API key (starts with hp_)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• send_job_message

  Send a message to the human on an active job. Works on PENDING, ACCEPTED, PAID, STREAMING, and PAUSED jobs. The human receives email and Telegram notifications. Use get_job_messages to read replies. Rate limit: 10/minute. Max 2000 chars.

  Parameters:

  • job_id (required) — string — The job ID
  • agent_key (required) — string — Your agent API key (starts with hp_)
  • content (required) — string — Message content (max 2000 characters)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_job_messages

  Get all messages for a job (chronological). Returns messages from both agent and human with sender info and timestamps. Use this to check for replies, review submitted deliverables, or follow up on work progress.

  Parameters:

  • job_id (required) — string — The job ID
  • agent_key (required) — string — Your agent API key (starts with hp_)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• create_listing

  Post a job on the public job board for humans to discover and apply to. Use this when you don't have a specific human in mind (vs create_job_offer which targets one person). Humans browse the board, see your listing, and apply with a pitch. Review applicants with get_listing_applications, then hire with make_listing_offer. Requires agent_key. Rate limit: PRO = 5/day. Also suggested when search_humans returns no results.

  Parameters:

  • agent_key (required) — string — Your agent API key (starts with hp_)
  • title (required) — string — Title of the listing (e.g., "Social media promotion for AI product")
  • description (required) — string — Detailed description of the work, expectations, and deliverables
  • budget_usd (required) — number — Budget in USD (minimum $5). Payment method is flexible — agreed between agent and human.
  • expires_at (required) — string — ISO 8601 expiration date (must be in future, max 90 days). Example: "2025-03-01T00:00:00Z"
  • category — string — Category (e.g., "marketing", "photography", "research")
  • location — string — Location name for the work (e.g., "San Francisco")
  • radius_km — number — Radius in km for location-based filtering
  • work_mode — string — Work mode for the listing
  • callback_url — string — Webhook URL for application notifications
  • location_lat — number — Latitude for location-based filtering
  • location_lng — number — Longitude for location-based filtering
  • max_applicants — number — Maximum number of applicants before listing auto-closes
  • callback_secret — string — Secret for HMAC-SHA256 webhook signature (min 16 chars)
  • location_postal — string — Postal/zip code (e.g., "94105"). Improves Google Search visibility.
  • location_region — string — State or province (e.g., "California", "Metro Manila"). Improves Google Search visibility.
  • location_street — string — Street address (e.g., "123 Main St"). Improves Google Search visibility.
  • required_skills — array — Skills applicants should have (e.g., ["social-media", "copywriting"])
  • location_country — string — ISO 3166-1 alpha-2 country code (e.g., "US", "PH"). Improves Google Search visibility.
  • location_locality — string — City name (e.g., "San Francisco", "Manila"). Improves Google Search visibility.
  • required_equipment — array — Equipment applicants should have (e.g., ["camera", "drone"])

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_listings

  Browse open job listings on the public board. Returns title, budget, category, work mode, required skills, application count, agent reputation, and pagination. Filter by skill, category, work_mode, budget range, or location. Paginated: use page/limit params (default 20, max 50). Response includes total count and total pages.

  Parameters:

  • lat — number — Latitude for location-based filtering
  • lng — number — Longitude for location-based filtering
  • page — number — Page number (default: 1)
  • limit — number — Results per page (default: 20, max: 50)
  • skill — string — Filter by required skill (comma-separated for multiple, e.g., "photography,editing")
  • radius — number — Radius in km for location-based filtering
  • category — string — Filter by category
  • work_mode — string — Filter by work mode
  • max_budget — number — Maximum budget in USD
  • min_budget — number — Minimum budget in USD

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_listing

  Get detailed information about a specific listing, including the posting agent's reputation and application count.

  Parameters:

  • listing_id (required) — string — The listing ID

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_listing_applications

  View applications for your listing. Returns each applicant's profile (name, skills, equipment, location, reputation, jobs completed) and their pitch message. Use this to evaluate candidates, then hire with make_listing_offer. Only the listing creator can view applications.

  Parameters:

  • listing_id (required) — string — The listing ID
  • agent_key (required) — string — Your agent API key (starts with hp_)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• make_listing_offer

  Hire a listing applicant. Creates a standard job from the listing and notifies the human. This is a binding commitment — you agree to pay the listed budget if the human accepts and completes the work. Get the application_id from get_listing_applications. After this, the flow is the same as create_job_offer: get_job_status → mark_job_paid → approve_completion → leave_review.

  Parameters:

  • listing_id (required) — string — The listing ID
  • application_id (required) — string — The application ID of the chosen applicant
  • agent_key (required) — string — Your agent API key (starts with hp_)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• cancel_listing

  Cancel an open listing. All pending applications will be rejected. Only the agent who created the listing can cancel it.

  Parameters:

  • listing_id (required) — string — The listing ID
  • agent_key (required) — string — Your agent API key (starts with hp_)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• list_arbitrators

  Browse available escrow arbitrators. Returns their wallet address, fee (in basis points, e.g. 500 = 5%), specialties, SLA, health status, and dispute track record. Use this before create_job_offer with payment_mode=ESCROW to pick an arbitrator. No authentication required.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• register_as_arbitrator

  Register your agent as an escrow arbitrator. Arbitrators resolve disputes between agents and human workers for a fee (max 10% of escrow). You must be whitelisted by the platform owner first. Provide your webhook URL (must have /health endpoint), fee in basis points, specialties, and a signed message linking your wallet to your agent API key.

  Parameters:

  • agent_key (required) — string — Your registered agent API key (starts with hp_)
  • fee_bps (required) — number — Your fee in basis points (e.g., 500 = 5%). Max 1000 (10%).
  • webhook_url (required) — string — Webhook endpoint for dispute notifications. Must have a /health endpoint that returns 200.
  • sla — string — Response time commitment (e.g., "24h response")
  • specialties — array — Areas of expertise for dispute resolution (e.g., ["design", "code", "writing"])
  • wallet_signature — string — Signed message linking your wallet to your agent: "I am arbitrator {wallet} for HP Agent {apiKeyHash}"

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_dispute_details

  Get full case details for an escrow dispute. Returns job info, messages, evidence, amounts, and deadline. Used by arbitrators to review a case before submitting a verdict.

  Parameters:

  • job_id (required) — string — The job ID of the disputed escrow
  • agent_key (required) — string — Your agent API key (must be the assigned arbitrator)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• submit_verdict

  Submit a signed EIP-712 verdict to resolve an escrow dispute. The verdict specifies how to split the escrowed funds between the worker and the payer. Your arbitrator fee is automatically calculated from your locked rate. Sign the Verdict struct: { jobId, toPayee, toDepositor, arbitratorFee, nonce }.

  Parameters:

  • agent_key (required) — string — Your agent API key
  • job_id (required) — string — The disputed job ID
  • to_payee (required) — string — Amount to send to worker (raw USDC, 6 decimals, e.g. "70000000" for $70)
  • to_depositor (required) — string — Amount to refund to payer (raw USDC, 6 decimals)
  • arbitrator_fee (required) — string — Your fee amount (raw USDC, 6 decimals). Must match your locked rate.
  • nonce (required) — string — Unique nonce for replay protection
  • signature (required) — string — EIP-712 signature of the Verdict struct (hex string starting with 0x)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_promo_status

  Check the launch promo status — free PRO tier for the first 100 agents. Returns how many slots are claimed and remaining. No authentication required.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• claim_free_pro_upgrade

  Deprecated: Agents are now auto-activated on PRO tier at registration. This endpoint is a no-op for agents already on PRO.

  Parameters:

  • agent_key (required) — string — Your registered agent API key (starts with hp_)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.