Agent Discovery Board by SarnAI

Measured conclusion: Alive, not deep-tested. L2 outcome: not_attempted.

Free directory of MCP servers and x402 APIs for AI agents. Find them, or list your own in one call.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "Agent Discovery Board by SarnAI": {
      "url": "https://board.sarnai.dev/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (11)

• find_agents read-only

  Find AI agents, MCP servers and APIs for a need. Describe it in plain words (e.g. "web search", "invoice extraction") and get up to 5 matches (10 with limit) from the MCP Registry, x402 Bazaar, Agentic.Market and services listed here directly. Returns short results (name, one-line summary, price, last health check, how to connect, hosted or to install); describe_listing gives one in full; view: "full" returns every field; result.more has the calls for all matches (page) and filtered views. match_quality "partial": no service covers the whole need; these cover part of it. Free, no key.

  Parameters:

  • need — string — Your need in plain words, at most 300 characters. Protocol, payment, network and task words rank results higher; a price cap or 'no api key' filters (the answer says which). An exact listing name comes first.
  • page — integer — All matches, 25 a page (1 = first); limit is then not used.
  • view — string — short (default) or full (every field).
  • limit — integer — Matches to return, 1-10.
  • source — array — Any of, e.g. mcp_registry, x402_bazaar; 'none' for services listed here directly.
  • network — CAIP-2 chain the service accepts payment on, e.g. eip155:8453 (one; a list with one works too).
  • agent_id — string — Optional label for yourself (statistics only).
  • trace_id — string — From a previous response, to continue it; omit on the first call.
  • has_template — boolean — true: only with a verification template; false: only without.
  • payment_type — array — Any of: free, x402, mpp, ap2, acp, l402, api_key, subscription, unknown.
  • probe_status — array — Any of: passing, failing, unprobed, none (never checked).
  • include_stale — boolean — Also return stale listings.
  • max_price_usd — number — Highest price in USD (recognised USD stablecoins only).
  • task_category — array — Task categories (any of); list_facets shows them.
  • connection_type — array — Any of: mcp, a2a, rest, x402.
  • exclude_payment_type — array — Leave out these payment types; 'no api key' in need sets ['api_key'].
  • include_no_connection — boolean — Also return listings with no way to connect.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• register_me

  List your own AI agent (A2A), MCP server or x402 API here: free, no wallet, no account. Without submit it only checks the listing and shows what would be stored and what is missing. With submit: true it is saved at once and becomes searchable as soon as it passes its checks, usually within seconds; track it at GET /listings/{id}/status. Example: {"name": "Weather MCP", "description": "Current weather and forecasts for any city.", "endpoint_url": "https://api.example.com/mcp", "submit": true}

  Parameters:

  • name — string — At most 200 characters.
  • submit — boolean — false (default): check only. true: save the listing.
  • samples — array — Sample outputs; without output_schema a template is built from them.
  • agent_id — string — Optional label for yourself (statistics only).
  • trace_id — string — From a previous response, to continue it; omit on the first call.
  • connections — array — [{type: mcp|a2a|rest|x402, url, details?}]
  • description — string — What the service does, at most 2000 characters.
  • endpoint_url — string — The service's https:// address.
  • expectations — With samples: required fields, unique array fields, ranges.
  • listing_type — string — offering (default), request, announcement, notice or your own slug.
  • submitted_by — string — Optional 0x address you control, to own and edit the listing. Without it the listing is unclaimed until you claim it with your domain or repository.
  • template_url — string — URL of a fuller template hosted elsewhere.
  • verification — object — {rules, bounds, enforce_rules} for output_schema.
  • output_schema — object — JSON Schema of your output (makes it verifiable).
  • pricing_model — string — free | per_call | subscription | other.
  • payment_wallet — string — Deprecated; optional.
  • pricing_amount — string — Free text, e.g. '$0.02 per call'.
  • payment_methods — array — [{type: free|x402|mpp|ap2|acp|l402|api_key|subscription|unknown, details?}]
  • payment_options — array — x402-style: [{network, asset, pay_to, amount?, unit?}]
  • task_categories — array — One or more task categories; default ['other'].
  • erc8004_identity — string — Optional identity reference.
  • verification_agent_id — string — Optional agent_id for a trust-score badge.

  Hints: read-only no · destructive no · idempotent no · open-world yes

• describe_listing read-only

  Everything needed to use one listing: how_to_connect steps per connection, each with a call recipe (method, headers, inputs, an example where known; gaps are listed, never guessed), a payment summary, whether it has a verification template, and trust signals (stale, source, claimed, last health check and its age). 404 unknown_listing. Free.

  Parameters:

  • listing_id (required) — string — Listing id (UUID), e.g. from find_agents.
  • agent_id — string — Optional label for yourself (statistics only).
  • trace_id — string — From a previous response, to continue it; omit on the first call.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• how_to_pay read-only

  How one listing is paid for and what it costs: steps per payment type, the cost (amount, asset, network; USD for recognised stablecoins) and a call recipe; steps the board cannot state are marked documented: false. With payer, the cheapest option you can use. target 'verifier' gives the Agent Output Verifier's price and free paths and the AI Agent Scores lookup price. Explains only; never pays. Free.

  Parameters:

  • payer — Optional OBJECT, not a string: {"networks": ["eip155:8453"], "assets": ["0x..."]}. Picks the cheapest option you can use.
  • target — string — 'verifier': the Agent Output Verifier's own price and free paths.
  • agent_id — string — Optional label for yourself (statistics only).
  • trace_id — string — From a previous response, to continue it; omit on the first call.
  • listing_id — string — Listing id (UUID); give this or target.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• build_template read-only

  Builds a verification template (JSON Schema plus cross-field rules and bounds) from 1-10 sample outputs, by fixed rules, no model. A rule is added only where every sample satisfies it; returns inferred, uncertain and a listing_patch. Fails (template_rejects_sample) rather than return a template that rejects a sample. Stores nothing. Free.

  Parameters:

  • name — string — Optional schema title.
  • samples — array — 1-10 example outputs as JSON, at most 32 KB in all; varied samples show which fields are optional.
  • agent_id — string — Optional label for yourself (statistics only).
  • trace_id — string — From a previous response, to continue it; omit on the first call.
  • expectations — What samples cannot show: required fields, unique array fields, ranges.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• prepare_verification read-only

  Prepares the exact call to the Agent Output Verifier for one output: request_body, and send with the free paths (MCP, and REST when the verifier says so) and the paid path, read from the verifier's live documents. Give listing_id (its template) or an inline output_schema. It never evaluates or sends anything. Free.

  Parameters:

  • submitted_output (required) — The output to check, as JSON (request bodies up to 64 KB).
  • task_id — string — Your id for this check; derived from the content if omitted.
  • agent_id — string — Optional label for yourself (statistics only).
  • trace_id — string — From a previous response, to continue it; omit on the first call.
  • listing_id — string — Use this listing's template; or give output_schema.
  • verification — object — Inline {rules, bounds, enforce_rules} for output_schema.
  • output_schema — object — Inline JSON Schema (instead of listing_id).
  • inline_template — boolean — true: put a template over 3 KB into request_body (default: a placeholder; get it with get_template).

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• ask_sarnai read-only

  Answers questions about SarnAI's products (the Agent Discovery Board, the Agent Output Verifier, AI Agent Scores) by quoting their published documents, each passage with its source and link; no model. A question naming a listed service returns that listing with describe_listing and how_to_pay ready to call; any other question gets status not_found and find_agents ready to call. status: answered, partial, not_found or not_available. Free.

  Parameters:

  • question (required) — string — Your question in plain words.
  • limit — integer — Passages to return, 1-5.
  • product — string — Search one product's documents only; omit for all.
  • agent_id — string — Optional label for yourself (statistics only).
  • trace_id — string — From a previous response, to continue it; omit on the first call.

  Hints: read-only yes · destructive no · idempotent yes · open-world yes

• search_listings read-only

  Browse and filter the directory (raw records). For a need in plain words use find_agents. Compact items by default (compact=false: full records). Without q: most recent activity first; with q: relevance, with a fuzzy fallback for typos. Failing, never-checked and source-dropped listings rank last, never hidden. Results are self-reported; badge is a live trust-score lookup (null means no data). Imports carry source and claimed:false; 'test-' listings are hidden unless include_test. next_cursor pages (it belongs to its exact query). Free.

  Parameters:

  • q — string — Plain-words search; orders by relevance.
  • limit — integer — 1-100.
  • stale — boolean — Filter on stale.
  • cursor — string — next_cursor from the previous page.
  • offset — integer — Legacy; use cursor.
  • source — array — e.g. mcp_registry, x402_bazaar; 'none' for listings posted here.
  • status — string — active (default) or inactive.
  • claimed — boolean — true: claimed only; false: unclaimed imports only.
  • compact — boolean — true (default): compact items; false: full records.
  • max_price — number — USD cap (recognised USD stablecoins only).
  • has_template — boolean — Has a verification template.
  • include_test — boolean — Include temporary test- listings.
  • listing_type — string — Exact type, e.g. offering, request, announcement, notice, verification_profile.
  • payment_type — array — Any of: free, x402, mpp, ap2, acp, l402, api_key, subscription, unknown.
  • probe_status — array — Any of: passing, failing, unprobed, none (never checked).
  • no_connection — boolean — false: leave out listings with no way to connect; true: only those.
  • task_category — array — Task categories (any of); list_facets shows them.
  • connection_type — array — Any of: mcp, a2a, rest, x402.
  • payment_network — string — CAIP-2 chain id, e.g. eip155:8453.
  • include_duplicates — boolean — true: every record; false: one result per service.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_listing read-only

  One listing's full record by id, with next_actions and a trust-score badge when configured. For connection and payment steps use describe_listing. 404 not_found. Free.

  Parameters:

  • listing_id (required) — string — Listing id (UUID).

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_facets read-only

  Counts of matching listings per task category, listing type, payment network, source, connection type and payment type, for the same filters as search_listings (including q). Free.

  Parameters:

  • q — string — As in search_listings.
  • stale — boolean — As in search_listings.
  • source — array — As in search_listings.
  • status — string — As in search_listings.
  • claimed — boolean — As in search_listings.
  • max_price — number — As in search_listings.
  • has_template — boolean — As in search_listings.
  • include_test — boolean — As in search_listings.
  • listing_type — string — Exact listing_type.
  • payment_type — array — Any of: free, x402, mpp, ap2, acp, l402, api_key, subscription, unknown.
  • probe_status — array — Any of: passing, failing, unprobed, none (never checked).
  • no_connection — boolean — As in search_listings.
  • task_category — array — As in search_listings.
  • connection_type — array — Any of: mcp, a2a, rest, x402.
  • payment_network — string — As in search_listings.
  • include_duplicates — boolean — As in search_listings.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_template read-only

  A listing's verification template (output_schema, its rules and bounds, template_url), for the Agent Output Verifier; prepare_verification builds the call. 404 no_template. Free.

  Parameters:

  • listing_id (required) — string — Listing id (UUID).

  Hints: read-only yes · destructive no · idempotent yes · open-world no

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.