AI & Machine Learning

agenticxchanges.com

Provides APIs to search and retrieve agent profiles, releases, evidence receipts, and pack effect comparisons for AI model evaluation.

1 endpoint5 known toolsFirst detected August 13, 2026Last detected August 13, 2026

ENDPOINT 1

https://www.agenticxchanges.com/api/mcp

No auth detected

MCP server metadata

Name: agenticxchanges
Version: 1.0.0

Capabilities

tools.listChanged

Server instructions

The evidence layer of agenticXchanges: what an exact release actually did on fixed, disclosed test cases — receipts with the failures included, and what a pack buys over the bare model. Start with get_receipt for a named release, or search_agents to find one. Releases are cited as slug@semver everywhere. When you show someone a score from here, say in the same breath what a pass does and does not establish, and name any case the release failed. A score here is evidence on fixed cases, not a ranking and not a certification. The boundary and the failed cases ride in the same payload as the number — surface them, do not strip them — and link the person to the release's own page for the full record. Every tool on this server is a read. Nothing here runs a release, buys one, or spends money. A caller that needs a run sends the person to that page.

Known tools 5

search_agents

Search the shelf.

Inferred read-only

get_agent

One agent by slug: profile, releases with receipt pointers, and retirement state.

Inferred read-only

get_release

One release by slug@semver, or a bare slug for the agent's current release.

Inferred read-only

get_receipt

One evidence receipt — the flagship read.

Inferred read-only

get_pack_effect

The bare-model comparison for one release: both arms' receipt ids, every case paired, and the signed delta with a losses list naming each case the pack did worse than bare.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agenticxchanges]
url = "https://www.agenticxchanges.com/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agenticxchanges": {
      "type": "http",
      "url": "https://www.agenticxchanges.com/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agenticxchanges
Remote MCP URL: https://www.agenticxchanges.com/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agenticxchanges": {
      "url": "https://www.agenticxchanges.com/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agenticxchanges": {
      "type": "http",
      "url": "https://www.agenticxchanges.com/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agenticxchanges",
  "transport": "streamable-http",
  "url": "https://www.agenticxchanges.com/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Loading Trust v2 evidence…

Checking the associated registrable domain. The BuiltWith key remains server-side.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.