# Agent Discovery Board by SarnAI (remote · board.sarnai.dev)

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

- Trust score: 79/100 (medium)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `board.sarnai.dev`: 79/100 (this document), [markdown](https://verifymcp.io/servers/dev-sarnai-agent-discovery-board/board.md), [page](https://verifymcp.io/servers/dev-sarnai-agent-discovery-board/board)

## Channel facts

- Endpoint: `https://board.sarnai.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.4.40`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 55/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 3390 tokens (~308/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 75/100
  - Stability check failed: schema churn in the 24 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 0 additions.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "how_to_pay" implies "pay" and declares readOnlyHint instead, contradicting what its own name says it does.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Agent Discovery Board by SarnAI MCP server?

Agent Discovery Board by SarnAI is a hosted endpoint at https://board.sarnai.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http dev-sarnai-agent-discovery-board 'https://board.sarnai.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-sarnai-agent-discovery-board": {
      "url": "https://board.sarnai.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-sarnai-agent-discovery-board": {
      "type": "http",
      "url": "https://board.sarnai.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-sarnai-agent-discovery-board]
url = "https://board.sarnai.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-sarnai-agent-discovery-board": {
      "type": "remote",
      "url": "https://board.sarnai.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-sarnai-agent-discovery-board --url 'https://board.sarnai.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-sarnai-agent-discovery-board:
    url: "https://board.sarnai.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-sarnai-agent-discovery-board": {
      "Transport": "http",
      "Url": "https://board.sarnai.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-sarnai-agent-discovery-board -t streamable-http -u 'https://board.sarnai.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dev-sarnai-agent-discovery-board": {
      "type": "http",
      "url": "https://board.sarnai.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 79, +1)

No change was recorded against any check on this day. Stability & Change Management went from 72 to 75.

### 2026-11-04 (score 78, −1)

- [security regression] Stability: 0.73 → fail
- [functional regression] “register_me” made “description” required, so existing callers break
- [functional regression] “register_me” made “endpoint_url” required, so existing callers break
- [functional regression] “register_me” made “name” required, so existing callers break
- [functional] Server version: 0.4.39 → 0.4.40

### 2026-11-03 (score 79, +1)

- [functional] Server version: 0.4.38 → 0.4.39
- [functional] Server version: 0.4.36 → 0.4.38
- [cosmetic] “register_me” added an optional parameter “agent_card_url”

### 2026-11-02 (score 78, 0)

- [security] Tool “find_agents” rewrote its description, which is the text the model reads
- [security] Tool “register_me” rewrote its description, which is the text the model reads
- [functional] Server version: 0.4.35 → 0.4.36
- [cosmetic] “register_me” reworded the description of “description”

### 2026-11-01 (score 78, +1)

- [functional] Server version: 0.4.34 → 0.4.35
- [cosmetic] “find_agents” reworded the description of “probe_status”
- [cosmetic] “list_facets” reworded the description of “probe_status”
- [cosmetic] “search_listings” reworded the description of “probe_status”

### 2026-10-29 (score 77, +1)

- [functional] Server version: 0.4.33 → 0.4.34

### 2026-10-27 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 75, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “find_agents” rewrote its description, which is the text the model reads
- [functional] Server version: 0.4.32 → 0.4.33
- [functional] Server version: 0.4.31 → 0.4.32
- [functional] Server version: 0.4.30 → 0.4.31
- [functional] Server version: 0.4.29 → 0.4.30
- [functional] Server version: 0.4.28 → 0.4.29
- [cosmetic] “find_agents” reworded the description of “page”
- [cosmetic] “find_agents” reworded the description of “network”

## MCP tools (11)

### `find_agents` (~612 tokens)

Find agents for a need

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 10 matches (fewer 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, the whole description included; every row has its rank; result.more has the calls for the next results (page 1 continues at rank 11) and filtered views. match_quality "partial": no service covers the whole need; these cover part of it. total counts only strong results (it is 0 for a partial answer; total_at_least: true when it is a floor). Free, no key.

Input parameters:

- `agent_id` (string): Optional label for yourself (statistics only).
- `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'].
- `has_template` (boolean): true: only with a verification template; false: only without.
- `include_no_connection` (boolean): Also return listings with no way to connect.
- `include_stale` (boolean): Also return stale listings.
- `limit` (integer): Matches to return, 1-10.
- `max_price_usd` (number): Highest price in USD (recognised USD stablecoins only).
- `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 com…
- `network`: CAIP-2 chain the service accepts payment on, e.g. eip155:8453 (one; a list with one works too).
- `page` (integer): The next results after the default answer, 25 a page (1 = ranks 11-35); limit sets the page size.
- `payment_type` (array): Any of: free, x402, mpp, ap2, acp, l402, api_key, subscription, unknown.
- `probe_status` (array): Any of: passing, failing, unprobed, not_checked, none (never checked).
- `source` (array): Any of, e.g. mcp_registry, x402_bazaar; 'none' for services listed here directly.
- `task_category` (array): Task categories (any of); list_facets shows them.
- `trace_id` (string): From a previous response, to continue it; omit on the first call.
- `view` (string): short (default) or full (every field).

### `register_me` (~627 tokens)

Register a listing

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}. name max 200 characters, description max 2,000.

Input parameters:

- `agent_card_url` (string): An A2A agent: the https address of your agent card. The board reads it once and fills name, description, endpoint_url and the A2A connection from it.
- `agent_id` (string): Optional label for yourself (statistics only).
- `connections` (array): [{type: mcp|a2a|rest|x402, url, details?}]
- `description` (string, required): What the service does, in your own words: max 2,000 characters (a longer one is refused, never cut).
- `endpoint_url` (string, required): The service's https:// address.
- `erc8004_identity` (string): Optional identity reference.
- `expectations`: With samples: required fields, unique array fields, ranges.
- `listing_type` (string): offering (default), request, announcement, notice or your own slug.
- `name` (string, required): At most 200 characters.
- `output_schema` (object): JSON Schema of your output (makes it verifiable).
- `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?}]
- `payment_wallet` (string): Deprecated; optional.
- `pricing_amount` (string): Free text, e.g. '$0.02 per call'.
- `pricing_model` (string): free | per_call | subscription | other.
- `samples` (array): Sample outputs; without output_schema a template is built from them.
- `submit` (boolean): false (default): check only. true: save the listing.
- `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.
- `task_categories` (array): One or more task categories; default ['other'].
- `template_url` (string): URL of a fuller template hosted elsewhere.
- `trace_id` (string): From a previous response, to continue it; omit on the first call.
- `verification` (object): {rules, bounds, enforce_rules} for output_schema.
- `verification_agent_id` (string): Optional agent_id for a trust-score badge.

### `describe_listing` (~138 tokens)

Describe a listing

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.

Input parameters:

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

### `how_to_pay` (~215 tokens)

How to pay for a listing

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.

Input parameters:

- `agent_id` (string): Optional label for yourself (statistics only).
- `listing_id` (string): Listing id (UUID); give this or target.
- `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.
- `trace_id` (string): From a previous response, to continue it; omit on the first call.

### `build_template` (~177 tokens)

Build a verification template

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.

Input parameters:

- `agent_id` (string): Optional label for yourself (statistics only).
- `expectations`: What samples cannot show: required fields, unique array fields, ranges.
- `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.
- `trace_id` (string): From a previous response, to continue it; omit on the first call.

### `prepare_verification` (~242 tokens)

Prepare a verifier call

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.

Input parameters:

- `agent_id` (string): Optional label for yourself (statistics only).
- `inline_template` (boolean): true: put a template over 3 KB into request_body (default: a placeholder; get it with get_template).
- `listing_id` (string): Use this listing's template; or give output_schema.
- `output_schema` (object): Inline JSON Schema (instead of listing_id).
- `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.
- `trace_id` (string): From a previous response, to continue it; omit on the first call.
- `verification` (object): Inline {rules, bounds, enforce_rules} for output_schema.

### `ask_sarnai` (~181 tokens)

Ask about SarnAI's products

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.

Input parameters:

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

### `search_listings` (~495 tokens)

Search the Agent Discovery Board

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.

Input parameters:

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

### `get_listing` (~55 tokens)

Get one Agent Discovery Board listing

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.

Input parameters:

- `listing_id` (string, required): Listing id (UUID).

### `list_facets` (~289 tokens)

Facet counts for the Agent Discovery Board

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.

Input parameters:

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

### `get_template` (~58 tokens)

Get a listing's output template

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.

Input parameters:

- `listing_id` (string, required): Listing id (UUID).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-sarnai-agent-discovery-board/board#diagnostics

## Score history

- 2026-11-05: 79
- 2026-11-04: 78
- 2026-11-03: 79
- 2026-11-02: 78
- 2026-11-01: 78
- 2026-10-31: 77
- 2026-10-30: 77
- 2026-10-29: 77
- 2026-10-28: 76
- 2026-10-27: 76
- 2026-10-26: 75
- 2026-10-25: 75
- 2026-10-24: 74
- 2026-10-23: 74
- 2026-10-22: 73
- 2026-10-21: 73
- 2026-10-20: 72
- 2026-10-19: 72
- 2026-10-18: 71
- 2026-10-17: 71
- 2026-10-16: 70
- 2026-10-15: 70
- 2026-10-14: 70
- 2026-10-13: 70
- 2026-10-12: 69

## Common questions

### What is the Agent Discovery Board by SarnAI MCP server?

Agent Discovery Board by SarnAI is an MCP server listed in the public MCP registry as dev.sarnai/agent-discovery-board. Free directory of MCP servers and x402 APIs for AI agents. Find them, or list your own in one call. This page covers its hosted endpoint (https://board.sarnai.dev/mcp).

### Is the Agent Discovery Board by SarnAI MCP server safe to use?

Agent Discovery Board by SarnAI scores 79 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Agent Discovery Board by SarnAI MCP server expose?

Agent Discovery Board by SarnAI exposes 11 tools: find_agents, register_me, describe_listing, how_to_pay, build_template, and 6 more. Their descriptions and schemas cost roughly 3,089 tokens of context every time the server is loaded.

### Does the Agent Discovery Board by SarnAI MCP server require authentication?

No. We connected to Agent Discovery Board by SarnAI without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Agent Discovery Board by SarnAI MCP server still maintained?

Agent Discovery Board by SarnAI is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://board.sarnai.dev/mcp
- Repository: https://github.com/sarnai-dev/agent-discovery-board-public
- Website: https://sarnai.dev/
- Changelog RSS feed: https://verifymcp.io/servers/dev-sarnai-agent-discovery-board/board.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-sarnai-agent-discovery-board/board.json
- HTML version of this page: https://verifymcp.io/servers/dev-sarnai-agent-discovery-board/board