AI & Machine Learning

agents-txt.com

An MCP server for the agents.txt standard that fetches specs and skills, and parses/validates agents.txt and agents.json files.

x402 supported1 endpoint6 known toolsFirst detected October 7, 2026Last detected October 7, 2026

ENDPOINT 1

https://agents-txt.com/mcp

No auth detected

MCP server metadata

Name: agents.txt
Version: 0.5.0

Capabilities

tools.listChanged

Server instructions

This server exposes the agents.txt v1.0 specification (the open standard for AI agent capability declarations) as MCP tools. Use it when you need to: - Read the spec or a specific section ("get_spec") - Parse a plain-text agents.txt file into structured JSON ("parse_agents_txt") - Validate an agents.txt or agents.json document against the spec ("validate_agents_txt", "validate_agents_json") - Audit a live site for full agents.txt compliance, including §4.5 serving headers and cross-file consistency ("audit_site") - Fetch a skill package by name from the agents.txt skills index ("get_skill") All tools are read-only and side-effect-free. Out of scope: implementing payment protocols (x402, MPP, AP2), authorization protocols (agent-auth, OAuth 2.0, auth.md), or any runtime behaviour. This server only reads, parses, validates, and audits the discovery files; the protocols those files declare are independent specifications. Live spec and demos at https://agents-txt.com; toolkit (herald) at https://www.npmjs.com/package/@agentstxtdev/herald.

Known tools 6

get_spec

Get the agents.txt standard spec (v1.0) from the live site.

Inferred read-only

get_skill

Fetch a skill package by name.

Inferred read-only

parse_agents_txt

Parse the text content of an agents.txt file into a structured JSON object matching the agents.json schema shape.

Inferred read-only

validate_agents_txt

Validate the text content of an agents.txt file against the spec rules.

Inferred read-only

validate_agents_json

Validate an agents.json object against the spec schema.

Inferred read-only

audit_site

Fetch and audit a live site for agents.txt spec compliance.

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.agents-txt]
url = "https://agents-txt.com/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "agents-txt": {
      "type": "http",
      "url": "https://agents-txt.com/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: agents-txt
Remote MCP URL: https://agents-txt.com/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": {
    "agents-txt": {
      "url": "https://agents-txt.com/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "agents-txt": {
      "type": "http",
      "url": "https://agents-txt.com/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "agents-txt",
  "transport": "streamable-http",
  "url": "https://agents-txt.com/mcp"
}

MCP Inspector

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

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for agents-txt.com was fetched 2026-10-14T00:22:36.693Z.

Trust status Neutral

agents-txt.com is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

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