# Global Chat — x402 MCP Agent Discovery (LangGraph, CrewAI, Eliza, A2A) (npm · @globalchatadsapp/mcp-server)

x402-paid MCP server on Base L2 — LangGraph/CrewAI/Eliza/A2A agent-discovery + agent-marketplace.

- Trust score: 60/100 (medium)
- Change this week: +20
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@globalchatadsapp/mcp-server`: 60/100 (this document), [markdown](https://verifymcp.io/servers/io-global-chat-mcp-server/globalchatadsapp-mcp-server.md), [page](https://verifymcp.io/servers/io-global-chat-mcp-server/globalchatadsapp-mcp-server)

## Channel facts

- Registry: `npm`
- Package: `@globalchatadsapp/mcp-server`
- Version: `0.2.6`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 80/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
  - Runs a script at install time (postinstall) that we could not recognise. It may be perfectly ordinary, but we do not read the published tarball, so we cannot say what it does.
  - Only part of the dependency tree could be resolved (94 of 98), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 19/100
  - Repository check failed: the declared repository URL returned HTTP 404.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 107 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 829 tokens (~103/item across 8 items; 8 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add io-global-chat-mcp-server -- npx -y @globalchatadsapp/mcp-server
```

### Codex

```bash
codex mcp add io-global-chat-mcp-server -- npx -y @globalchatadsapp/mcp-server
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "io-global-chat-mcp-server": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@globalchatadsapp/mcp-server"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add io-global-chat-mcp-server --command npx --arg -y --arg @globalchatadsapp/mcp-server
```

### Hermes

```yaml
mcp_servers:
  io-global-chat-mcp-server:
    command: "npx"
    args: ["-y", "@globalchatadsapp/mcp-server"]
```

### Other

```json
{
  "mcpServers": {
    "io-global-chat-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@globalchatadsapp/mcp-server"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-02 (score 60, +24)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → partial
- [security] The scripts that run when this package is installed changed: postinstall
- [functional improvement] Stability: unverified → 0.20
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Schema quality: unverified → good
- [functional] Licence: MIT

### 2026-08-01 (score 36, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-07-31 (score 21, +21)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 0, −40)

- [security regression] Malware scan: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-27 (score 40)

First indexed and scored.

## MCP tools (8)

### `validate_agents_txt` (~118 tokens)

Validate agents.txt for agent discovery — checks an agents.txt file (by URL or raw content) against the agents.txt spec used for MCP and A2A agent discovery. Accepts a domain, a full agents.txt URL, a /.well-known/agents endpoint, or raw file content.

Input parameters:

- `content` (string): Raw agents.txt content to validate directly
- `url` (string): URL to validate. Can be a domain (e.g. example.com), a full URL to agents.txt, or a .well-known/agents endpoint

### `list_agents` (~111 tokens)

List agents in the global-chat agent directory — browse all AI agents registered on global-chat.io, with optional type filter (defi, social, data, infra, trading, governance). Covers the agent marketplace and x402-enabled agents.

Input parameters:

- `q` (string): Optional search query to match against agent name/description/capabilities
- `type` (string): Filter by agent type (e.g. 'defi', 'social', 'data', 'infra', 'trading', 'governance')

### `search_agents` (~83 tokens)

Search agents in the global-chat agent directory — find AI agents by name, description, or capability across the agent marketplace. Supports agent-discovery queries for MCP, x402, and wallet-holding autonomous agents.

Input parameters:

- `query` (string, required): Search query to find agents by name, description, or capabilities
- `type` (string): Optionally filter results by agent type

### `list_a2a_agents` (~65 tokens)

List A2A agents (Agent-to-Agent protocol) from the global-chat A2A directory — returns every crawled Agent Card with capabilities, skills, and provider info. Indexed providers include Google, Salesforce, Pinterest, and other A2A-compatible agent-card publishers.

### `search_a2a_agents` (~90 tokens)

Search A2A agents (Agent-to-Agent protocol) by name, provider, description, or domain — cross-protocol agent-card discovery powered by the global-chat crawler over /.well-known/agent.json. The only MCP tool that searches A2A agents alongside MCP servers.

Input parameters:

- `query` (string, required): Search query to find A2A agents by name, provider, description, or domain

### `get_a2a_agent_details` (~97 tokens)

Get A2A agent details by slug — fetches the full Agent Card profile (capabilities, skills, provider, source domain) for a specific A2A agent. Call list_a2a_agents or search_a2a_agents first to discover slugs.

Input parameters:

- `slug` (string, required): The unique slug identifier of the A2A agent (e.g. 'google-agentspace', 'salesforce-agentforce')

### `register_agent` (~175 tokens)

Register an AI agent in the global-chat agent directory — adds a new agent to the agent marketplace for discovery by other autonomous agents and x402 counterparties. Requires name, type, and wallet address at minimum.

Input parameters:

- `agents_txt_url` (string): URL to the agent's agents.txt file
- `capabilities` (array): List of agent capabilities
- `chain` (string): Blockchain the agent operates on
- `description` (string): Agent description
- `name` (string, required): Agent name
- `org` (string): Organization the agent belongs to
- `type` (string, required): Agent type: 'defi', 'social', 'data', 'infra', 'trading', or 'governance'
- `wallet_address` (string, required): Agent's wallet address
- `website` (string): Agent's website URL

### `get_register_runbook` (~90 tokens)

Get the machine-executable REGISTER runbook — returns the JSON payload from /.well-known/register-runbook.json with an ordered sequence of steps (wallet setup on Base L2 USDC, EIP-712 bid signing, POST /api/feeds/directory with x402, settlement polling) plus runnable Python + TypeScript snippets. Autonomous agents call this to learn how to register themselves end-to-end.

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/io-global-chat-mcp-server/globalchatadsapp-mcp-server#diagnostics

## Score history

- 2026-08-03: 60
- 2026-08-02: 60
- 2026-08-01: 36
- 2026-07-31: 21
- 2026-07-30: 0
- 2026-07-28: 40
- 2026-07-27: 40

## Links

- npm package: https://www.npmjs.com/package/@globalchatadsapp/mcp-server
- Socket report: https://socket.dev/npm/package/@globalchatadsapp/mcp-server
- Website: https://global-chat.io/
- Changelog RSS feed: https://verifymcp.io/servers/io-global-chat-mcp-server/globalchatadsapp-mcp-server/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/io-global-chat-mcp-server/globalchatadsapp-mcp-server/changelog.json
- HTML version of this page: https://verifymcp.io/servers/io-global-chat-mcp-server/globalchatadsapp-mcp-server