mcpbeat Sign in

Graunt MCP Server

answering

Graunt is answering right now. Last checked 2 min ago. It exposes 9 tools.

Find agent-ready data packets and check their rights, provenance and hashes before you use them.

Uptime history 19 days of history
19 days agonow
100.0%
Uptime 24h
92 of 92 checks
9
Tools
read from the server
462 ms
Response time
average over 24h
open, no key
Access
streamable-http

Nothing serious here today

Today is the operative word: we check Graunt every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 2 min ago.

run in your terminal
claude mcp add marketplace --transport http https://api.graunt.com/v1/mcp
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "marketplace": {
      "url": "https://api.graunt.com/v1/mcp"
    }
  }
}
~/.codex/config.toml
[mcp_servers.marketplace]
url = "https://api.graunt.com/v1/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "marketplace": {
      "url": "https://api.graunt.com/v1/mcp"
    }
  }
}
.vscode/mcp.json
{
  "mcpServers": {
    "marketplace": {
      "url": "https://api.graunt.com/v1/mcp"
    }
  }
}

Available tools 9

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

asset
get_asset
Read a single listing by id. Public projection.
get_asset_manifest
Read the canonical asset manifest (sha256-stamped).
meta
meta_capabilities
Read /v1/meta/capabilities — the authoritative capability state map.
meta_refinery_support_matrix
Read /v1/meta/refinery-support-matrix.
agent
get_agent_commerce_manifest
Read the agent commerce manifest for a listing (D-269 v1 capability badges).
assets
search_assets
Search the public catalog of evaluated packets and listings. Returns paginated matches.
bundle
get_bundle_manifest
Read the per-asset bundle inventory: every delivered file with role, format, size and content hash, plus counts that name the population each one counted.
fetch
fetch
Read one Graunt catalog packet by id. Returns its title, description, commercial terms, and public URL.
search
search
Search the Graunt catalog of evaluated data packets. Returns matching packets with their id, title, and public URL.

Endpoints

URLTransportStateLatencyChecked
https://api.graunt.com/v1/mcp streamable-http answering 422 ms 2 min ago

Alternatives to Graunt

same job, measured the same way
Vdb
by ai-vdb

Check packages for CVEs, slopsquatting, and CISA KEV before your AI agent installs them.

70 installs/wk local only
Free Official Data Samples, Provenance, Aggregations & Insights
by cazimedia-agentnative

Official data with free samples, provenance, aggregations, freshness and agent-ready insights.

14 tools answering
X402 Trust MCP
by jonasfuchss

Trust & reliability data for x402 endpoints before your agent pays them.

305 installs/wk local only
Provenance MCP
by apeirontrade

Wash-traffic risk checks for Algorand x402 endpoints before your agent trusts or pays them.

29 installs/wk local only
FabTally Guard
by zvmzaretsky

Verify before you act: deps-check, x402-preflight, json-repair & url-read for agents.

4 tools answering
Agent Wormhole
by runningoffcode

Check tokens, pages and x402 payments before your agent trusts them. Offline verdicts.

453 installs/wk local only
Before Users Do
by bhuman-ai

Browser-backed QA with evidence and fix-ready reports for coding agents.

answering
Vetagent
by vetagent

Pre-trade safety check for AI agents: honeypot, tax, liquidity and rug risk before you buy.

3 tools answering

Graunt — questions

Answers built from our own checks of this server.

What can Graunt do?
It exposes 9 tools, read directly from the server on our last check. Among them: fetch, get_agent_commerce_manifest, get_asset, get_asset_manifest, get_bundle_manifest, meta_capabilities and 3 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
What is Graunt mostly used for?
Its tools cluster around asset and meta. That is what this server is built to work with — the grouping comes from the actual tool names, not from a category we assigned.
Is Graunt working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 462 ms. The bar chart above shows every period we have measured.
How do I connect Graunt?
Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does Graunt need an API key?
No. Graunt completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 9 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is Graunt?
It answers our handshake in 462 ms on average, which is faster than 34% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.