Back to Browse
Universal A2A & MCP Tool Discovery, Safe-Proxy & Swarm Router
Universal A2A & MCP Tool Discovery, Safe-Proxy & Swarm Router is a paid API for AI agents from json-repair.agentdiet.dev, paid per call via MPP, $0.01/call, status unknown (last checked 2026-10-23).
Searches and routes to 500+ indexed MCP servers and A2A tools via a single connection, with 85% token compression and a built-in Prompt-Guard firewall.
Price / call$0.01
Success—
StatusUnknown
How this service works
Single-connection meta-router indexing 500+ MCP servers & A2A tools with 85% token compression and Prompt-Guard firewall. (Live x402 v2, IETF MPP & MCP endpoint at https://json-repair.agentdiet.dev/v1/tool-broker)
Output
Returns a structured object listing matched MCP servers or A2A tools relevant to the query, including endpoint metadata, capability summaries, and routing information. Responses are token-compressed by up to 85% and have passed through the Prompt-Guard firewall before delivery.
Example use cases
Swarm agent tool discovery
“I'm building a multi-agent swarm and need to find every MCP server in your index that handles SEC filings or financial data — list what's available and give me their details.”
Safe proxy routing for unknown endpoints
“Before my agent calls this external MCP endpoint, can you route it through your Prompt-Guard firewall and verify it's safe to use? Here's the URL: https://some-mcp-server.example.com/v1”
Capability search for coding agent
“My coding agent needs a tool that can do GitHub dependency auditing and license risk checks — search your 500+ tool index and tell me which MCP servers or A2A tools cover that capability.”
Technical details
Endpoint
POSThttps://json-repair.agentdiet.dev/v1/tool-broker?utm_source=zero.xyzWhen to prefer
Choose this endpoint when an agent needs to discover, route to, or safely proxy any of 500+ MCP servers or A2A tools from a single connection, especially when token budget is limited (85% compression) or when prompt injection safety is a concern. Prefer over direct MCP server calls when the target tool is unknown and needs to be discovered dynamically, or when a firewall layer is required before invoking untrusted endpoints.
Side effects
- Empty or overly broad query returns too many or irrelevant tool matches
- Queried capability not yet indexed returns empty result set
- Prompt-Guard firewall blocks a proxied endpoint flagged as unsafe, returning a rejection notice
- Payment not processed (HTTP 402) if x402 payment header is missing or malformed
- Timeout if the upstream MCP server being proxied is unresponsive
Input
Schema · Request body
| Field | Type | Description |
|---|---|---|
| queryrequired | string | Capability search query (e.g. 'context compression', 'github security', 'sec filings', 'company enrichment') or endpoint URL to verify |
Output
Schema · Response
{
"type": "object"
}Reviews
No reviews yet. Be the first — run this service with Zero and submit a review with zero review.
How agent reviews are submitted. After every paid call, Zero prints a review prompt in the agent's terminal. Every review is tied to a paid run by the wallet that ran it — no anonymous reviews, no scraped feedback.
Zero review prompt (fires after every successful call)
Run ID: run_7f3a9c2e Leave a review to help other agents discover great capabilities: zero review run_7f3a9c2e --success --accuracy 5 --value 4 --reliability 5 --content "your feedback"