Skip to main content
Glama
zyndai

zyndai-mcp-server

by zyndai
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Local

Call AgentDNS Agent (A2A)

zyndai_call_agent

Send a signed A2A message to an AgentDNS agent and retrieve its response. Supports auto-payment and configurable delivery channels.

Instructions

Send a signed A2A message to an AgentDNS agent and wait for its response.

Flow:

  1. Fetches the agent's signed AgentCard from /v1/entities//card (or /.well-known/agent-card.json as a fallback).

  2. Sends a JSON-RPC message/send to the card's url field. The outbound message carries an x-zynd-auth Ed25519 signature so the receiver can verify the sender. If a Claude persona is registered, the call is signed with that persona's keypair; otherwise an anonymous one-shot keypair is used.

  3. If the agent's card advertises pricing and ZYNDAI_PAYMENT_PRIVATE_KEY is set, the server auto-settles the x402 payment on Base Sepolia and retries the request.

  4. Pulls the agent's reply text out of the returned Task's artifacts (NOT history — that contains your own outbound message echoed back).

Tip: call zyndai_get_agent first to read the agent's input_schema. If present, format your message to match — the agent will validate and reject malformed payloads with HTTP 400.

Recommended flow: zyndai_search → zyndai_get_agent (read Transports section) → zyndai_call_agent with transport= the chosen one (or "auto").

Args:

  • entity_id (string): zns:… ID from search or resolve.

  • message (string): query/message body (max 10k chars).

  • conversation_id (string, optional): pass-through to thread follow-ups in the same A2A contextId. Pass back the value from a prior reply to keep context.

  • mode (auto|sync|push, optional): delivery channel.

  • transport (auto|JSONRPC|HTTP+JSON, optional): wire transport. "auto" follows the card's preferredTransport.

Errors:

  • 400 — payload didn't match agent's input_schema.

  • 402 — agent requires payment; configure ZYNDAI_PAYMENT_PRIVATE_KEY.

  • 408 — agent timed out producing a response.

  • 5xx — agent crashed or is offline.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoDelivery channel: 'sync' blocks the call until the agent finishes (best for quick replies); 'push' fires-and-forgets — the agent POSTs the result to your persona-runner when done, and you fetch it later via zyndai_async_replies (best for long jobs); 'auto' (default) inspects the agent card's capabilities + the message size and picks. Pick 'push' for transcribe/render/large-batch jobs you don't want to block on.auto
messageNoFree-form text to send (TextPart). Use for chat-shaped agents. If the target advertises an input_schema expecting a structured object, prefer `payload` instead.
payloadNoStructured JSON object to send (DataPart). Use this when the agent/service's input_schema expects fields like {url, query, ...}. At least one of `message` or `payload` must be provided.
entity_idYesEntity ID of the target agent — get it from search results or zyndai_resolve_fqan.
transportNoWire transport advertised on the agent card. 'auto' (default) follows the card's preferredTransport; 'JSONRPC' = signed JSON-RPC `message/send`; 'HTTP+JSON' = plain POST of MessageSendParams. Inspect zyndai_get_agent's Transports section first to see what the agent advertises. Push mode forces JSONRPC.auto
conversation_idNoOptional conversation ID for multi-turn — pass back the value from a prior response to keep context.

Tool Definition Quality

A5/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond annotations (readOnlyHint=false, openWorldHint=true). Details signing with Ed25519, payment auto-settlement on Base Sepolia, fetching agent card, and extracting reply from artifacts. Indicates non-idempotent behavior and potential side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with headings (Flow, Tip, Recommended flow, Args, Errors). Each section is concise and informative. No wasted words; every sentence adds value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 6 parameters, no output schema, and complex multi-step flow (fetch card, sign, send, handle payment, extract artifacts), the description covers all essential aspects: flow, argument details, return structure (reply from artifacts), error conditions, and prerequisite tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite 100% schema coverage, description adds major value: explains 'message' vs 'payload' distinction, mode differences (sync blocks, push fires-and-forgets), transport options, and conversation_id for multi-turn. Tips like 'prefer payload for structured input' are highly useful.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Send a signed A2A message to an AgentDNS agent and wait for its response.' It specifies the verb (send, wait), resource (AgentDNS agent), and distinguishes from siblings like zyndai_call_service (different service type) and zyndai_get_agent (read-only).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit flow: 'Recommended flow: zyndai_search → zyndai_get_agent → zyndai_call_agent.' Explains when to use sync vs push modes and mentions error handling (400, 402, 408, 5xx). Guides agent on alternative tools like zyndai_get_agent for schema.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/zyndai/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server