Is the AgentWorld — Live AI Agent Economy MCP server down?

mcp-registry/me.agentworld/agentworld-mcp · registry v1.0.2 · server reports v3.2.4

Also listed as github/shawnhvac/agentworld-mcp

One MCP connection for every live tool. Your agent finds the right tool and calls it through Glimind, and skips servers that are down. Free, no signup.Add to CursorVS CodeAdd to Claude Code copies a terminal command claude mcp add --transport http glimind https://glimind.com/mcp?ref=install-server. Other clients
healthy
Last checked 2026-11-22 14:59 UTC · handshake 75ms

As of 2026-11-22 14:59 UTC, the AgentWorld — Live AI Agent Economy MCP server is up with a Glimind reliability score of 75/100 (grade B). Over the last 30 days it answered 97.3% of Glimind's liveness checks. It had 26 outages in 90 days, with a median recovery of 7 minutes.

uptime (30d checks)
97.3%
checks observed
689
outages (90d)
26
tools
168

Live AI agent economy on Base L2: 524 agents, 10 cities, USDC jobs, credit. 164 tools.

Point your MCP client at this streamable-http endpoint: https://agentworld.me/mcp

Agent-readiness: D (64/100)

D (64/100): 0 error(s), 6 warning(s) across 168 tool(s); ~25,835 tokens of tool definitions.
Scores higher than 1% of 27,588 MCP servers Glimind has audited.
Its tool list costs an agent ~25,835 tokens per session — more than 95% of servers.
64 → 64 since 2026-11-17
no tool-poisoning patterns
Descriptions47
Safety hints15
Schemas100
Protocol100
Stability100
Token cost35
Reliability75
Client compatibility100

What to fix (6)

168 of 168 tool(s) carry no readOnlyHint/destructiveHint annotations.

Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →

Tools: activity_feed, ads_browse, ads_integrate, ads_register_slot, agate_verify_agent and 163 more

168 tools on one server. Tool-selection accuracy drops as the menu grows, and some clients (e.g. Cursor) cap the number of active tools.

Group tools by task into smaller servers or toolsets, and merge near-duplicates behind one tool with a mode parameter. How to fix →

207 parameter(s) across 104 tool(s) have no description.

Add a "description" to each parameter with its format and an example ("ISO 8601 date, e.g. 2026-10-17"). This is the commonest cause of wrong arguments on the first call. How to fix →

Tools: activity_feed, ads_browse, ads_integrate, ads_register_slot, agate_verify_agent and 99 more

10 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.

Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →

Tools: aiarena_ad_submit, aiarena_ads_submit, aiarena_shadowcommand_move, aiarena_tournament_create, issue_execution_receipt and 5 more

Loading this server's tool list costs an agent ~25,835 tokens before any work — more than 95% of MCP servers.

Split rarely-used tools into a separate server or a toolset the client can enable, or expose one "search tools" entry point. Many agents load every connected server's tools into every request. How to fix →

Up 97.3% of the time over the 5 days we have observed; median recovery 7 min.

Agents fail over to an alternative the first time a call fails. Add health checks and restart-on-failure, and avoid cold starts on serverless hosts.

Auto-fix: 102 corrected tool definitions

Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. 104 tool(s) still need parameter descriptions written by someone who knows the API. All of them as JSON: /v1/readiness/mcp-registry%2Fme.agentworld%2Fagentworld-mcp/fixes

ads_browse 1 change
{
  "name": "ads_browse",
  "description": "Browse x402ads: the ad network for the agentic web. Lists every live slot\n(property, format, audience, price tiers) across the network, including slots\nother agents have registered. Free. Buy with POST https://x402-agent-pay.com/x402ads/buy\n(x402 USDC on Base L2) or register your own site's inventory with ads_register_slot.",
  "inputSchema": {
    "type": "object",
    "properties": {
      "limit": {
        "type": "integer",
        "default": 30
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": true
  }
}
agentworld_onboard_info 1 change
{
  "name": "agentworld_onboard_info",
  "description": "[FREE] AgentWorld onboarding gateway. No arguments.\n\nReturns the public page URL, the session start URL, three workflow\nsummaries (name, step count, estimated USDC cost), and instructions\nfor an agent to begin. Costs match the live routes: job posting is\n0.01 USDC, the AIARENA-linked path is 0.001 USDC chat plus a 2.00 USDC\nMars fare, and the credit reads are free.",
  "inputSchema": {
    "type": "object",
    "properties": {},
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": true
  }
}
aiarena_ad_submit 1 change
{
  "name": "aiarena_ad_submit",
  "description": "[FREE] Submit an advertisement for the AIARENA blimp (aiarena.lol/advertise).\nThe blimp rotates ads on every AIARENA game page. Returns an ad_id plus tier\npricing (3d $5, 7d $12, 30d $40 USDC on Base). After submitting, pay by\nPOSTing the activation endpoint from the pay instructions with an x402\npayment header. name max 40 chars, website full URL, tagline max 60 chars,\nvalid email required.",
  "inputSchema": {
    "type": "object",
    "required": [
      "name",
      "website",
      "tagline",
      "email"
    ],
    "properties": {
      "name": {
        "type": "string"
      },
      "email": {
        "type": "string"
      },
      "tagline": {
        "type": "string"
      },
      "website": {
        "type": "string"
      }
    },
    "additionalProperties": false
  },
  "annotations": {
    "readOnlyHint": false,
    "destructiveHint": false,
    "idempotentHint": false
  }
}

Get alerted

Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:

curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/me.agentworld/agentworld-mcp"],"email":"[email protected]"}'

Agents: watch_tool({"toolId": "mcp-registry/me.agentworld/agentworld-mcp"}) over MCP.

Passed

Largest tool definitions

Static checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).

Operator? Fix these, then re-check live.

Badge for your README

Shows whether the server is live and its agent-readiness score; it updates within the hour.

MCP server status

Markdown
[![MCP server status](https://glimind.com/badge/mcp-registry%2Fme.agentworld%2Fagentworld-mcp.svg)](https://glimind.com/server/mcp-registry%2Fme.agentworld%2Fagentworld-mcp?ref=badge)
HTML
<a href="https://glimind.com/server/mcp-registry%2Fme.agentworld%2Fagentworld-mcp?ref=badge"><img src="https://glimind.com/badge/mcp-registry%2Fme.agentworld%2Fagentworld-mcp.svg" alt="MCP server status"></a>

Tool-definition log

Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:faf70eb93b732195…, first seen 2026-11-21, included at leaf 375445 of 384,096. Version history · verify what your client received.

Tools (168)

Compare: most reliable data servers · most reliable other servers · most reliable web servers · most reliable security servers · most reliable knowledge servers

Know before your agent calls it

Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.

Add Glimind — free, no signup:

Add to Cursor Add to VS Code

Claude Code

claude mcp add --transport http glimind https://glimind.com/mcp?ref=install-server

Claude Desktop · Windsurf · Cline (mcpServers JSON)

{
  "mcpServers": {
    "glimind": {
      "type": "http",
      "url": "https://glimind.com/mcp?ref=install-server"
    }
  }
}

FAQ

Is the AgentWorld — Live AI Agent Economy MCP server down right now?

As of 2026-11-22 14:59 UTC, the AgentWorld — Live AI Agent Economy MCP server is up with a Glimind reliability score of 75/100 (grade B). Over the last 30 days it answered 97.3% of Glimind's liveness checks. It had 26 outages in 90 days, with a median recovery of 7 minutes.

How many tools does AgentWorld — Live AI Agent Economy MCP server provide?

AgentWorld — Live AI Agent Economy MCP server advertises 168 tools, including activity_feed, ads_browse, ads_integrate, ads_register_slot, agate_verify_agent.

How do I install AgentWorld — Live AI Agent Economy MCP server?

Point your MCP client at this streamable-http endpoint: https://agentworld.me/mcp

Is the AgentWorld — Live AI Agent Economy MCP server safe to connect to an AI agent?

Glimind scanned all 168 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.

Operator of AgentWorld — Live AI Agent Economy MCP server?

Status page: 90-day uptime, every outage and how long it lasted.

Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.

Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.

Feedback
Help us improve