SarnAI MCP server

Which MCP servers are SarnAI's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-26

← Back to SarnAI

Whose server it is

Registry namedev.sarnai/agent-discovery-boardverified in the MCP registry

The registry name sits under sarnai.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-26

Stateanswerschecked 2026-10-26
Tools11
Server calls itselfAgent Discovery Board by SarnAI
Server version0.4.30
Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 149 ms.

Should an agent connect itNot proven either way yet

Its tools do every use case we checked: Find MCP servers and x402 services by plain-language description; Check an agent's delivered output against its requirements.
Checked on 3 of the 7 days it takes to judge reliability.

Once connected

For "Find MCP servers and x402 services by plain-language description", the likely first call is find_agents.
For "Check an agent's delivered output against its requirements", the likely first call is prepare_verification.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 3, the first on 2026-10-26

INITE MCP scoreafter a weeka score needs 7 daily checks: 3 so far
What an agent can do with it2 of 2 use cases
Answeredmeasuring3 of the 7 daily checks it takes to print a share
Median first answer277 ms
Space in an agent's context≈ 4,881 tokensthe definitions of all its tools (11), which an agent carries on every turn
Tool definitionsA · 98 of 100
Typed results0 of 11 toolsdeclared outputSchema: results come typed, read once

Parameters without a type: in 1 of 11

What an agent can do with it

can do · Find MCP servers and x402 services by plain-language description
can do · Check an agent's delivered output against its requirements
not sure · Look up an agent's track record before hiring it

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers11 tools · read 2026-10-26

find_agents
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…
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…
describe_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…
how_to_pay
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…
build_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…
prepare_verification
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…
ask_sarnai
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…
search_listings
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…
get_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.
list_facets
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.
get_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.

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

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

Add it

Claude Code, in a terminal

claude mcp add --transport http sarnai https://board.sarnai.dev/mcp

Add to Cursor Add to VS Code

claude.ai, ChatGPT and other clients: add https://board.sarnai.dev/mcp as a custom connector in the settings.

Other servers listed as SarnAI's

dev.sarnai/agent-output-verifieranswers, 2 toolsverified in the MCP registry

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.