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 mesh.agentdiet.dev, paid per call via MPP, $0.01/call, status unknown (last checked 2026-10-23).
Searches a meta-index of 500+ MCP servers and A2A tools by capability query, returning token-compressed, prompt-injection-screened results through a single proxy connection
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://mesh.agentdiet.dev/v1/broker/execute)
Output
Returns a token-compressed (up to 85% reduction) list of matching MCP servers or A2A tools from the 500+ tool index, including endpoint URLs, capability descriptions, and prompt-injection firewall screening status. Response is a generic JSON object containing matched tools and routing metadata.
Example use cases
Discovering tools for SEC filing analysis
“Search the agent tool registry for any MCP servers or A2A tools that can pull SEC EDGAR 10-K filings — I want to find the right endpoint to route my financial research agent through.”
Safe-proxying an unknown MCP endpoint
“I found this MCP endpoint at a third-party URL — can you verify it through the safe proxy and check it for prompt injection risks before my agent starts using it?”
Building a swarm of specialized agents
“I'm building a multi-agent swarm and need to discover which tools in the 500+ MCP index cover 'github security audits', 'CVE scanning', and 'domain OSINT' so I can wire up the right capabilities automatically.”
Technical details
Endpoint
POSThttps://mesh.agentdiet.dev/v1/broker/execute?utm_source=zero.xyzWhen to prefer
Choose this endpoint when an AI agent needs to dynamically discover which of 500+ MCP servers or A2A tools best matches a given capability requirement, rather than hardcoding tool URLs. Ideal for swarm orchestrators, meta-agents, and dynamic routing scenarios where the right tool is unknown at design time. Prefer it over manual tool registries when you also need prompt-injection safety screening and token-compressed results to preserve context window budget.
Side effects
- Empty or vague query returns no meaningful matches
- Query too broad returns overwhelming number of results with low relevance
- Endpoint URL verification fails if the target MCP server is offline
- Rate limiting or payment failure (x402) if the $0.01 per-call quota is exceeded
- Firewall may block legitimate tools that trigger false-positive injection patterns
- Malformed or missing 'query' field returns validation error
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"