MCP server health, State of MCP census

Agent Safe

io.github.wowcool/agentsafe

Email safety MCP server. Detects phishing, prompt injection, CEO fraud for AI agents.

healthy checked 2026-07-02 · 6/7 checks passed · keyless

Checks

The exact rows akashi check io.github.wowcool/agentsafe prints, from the 2026-07-02 census.

CheckStatusDetail
registry statuspassactive
server.json validpassvalidates against its declared JSON Schema
repo reachableskipno repository declared
remote reachablepassHTTP 200 via initialize
MCP conformancepassinitialize handshake ok
tools/listpass11 tools: check_email_safety, check_url_safety, check_response_safety, analyze_email_thread, check_attachment_safety, check_sender_reputation, check_message_safety, check_media_authenticity, ...
at least one live entrypointpass1 alive

Evidence

Repository

No repository declared.

Packages

No packages declared.

Remote endpoints

  • https://agentsafe.locationledger.com/mcp

    streamable-http · reachable· HTTP 200· initialize_ok

    11 tools: check_email_safety, check_url_safety, check_response_safety, analyze_email_thread, check_attachment_safety, check_sender_reputation, check_message_safety, check_media_authenticity, ...

server.json

validagainst its declared schema

One of 14559 servers in the 2026-07-02 State of MCP census: 11582 healthy (79.6%), 2212 degraded (15.2%), 596 dead (4.1%), 169 unknown (1.2%).

Verify it yourself

This page is a static read of one dated probe. Run the same check locally, any time, with no key:

$ akashi check io.github.wowcool/agentsafe

Install Akashi - single Go binary, zero keys, MIT licensed.

Is this your server?

Claiming a server (an auto-refreshing badge and a verified publisher profile) is coming soon. Until then, embed the verified-on-date badge yourself with akashi check io.github.wowcool/agentsafe --badge.

Open data, CC BY 4.0. How this census works - denominator, tiers, and what each check does.