mcpField
A
AgentCanary

AgentCanary

Local
agentcanary.aiFinance0Updated 16w ago
RepositoryVisit website

About AgentCanary

AgentCanary MCP is a retired compatibility stub for existing MCP clients. Its legacy tools return a retirement notice and links to the ongoing daily briefs on X and Telegram; they no longer contact product endpoints.

Key features

  1. 01Keeps legacy tool names registered
  2. 02Returns retirement status
  3. 03Provides current X and Telegram links
  4. 04Requires no configuration

Use cases

  1. 01Let existing clients start without endpoint errors
  2. 02Show clients where daily briefs continue

MCP support

This MCP server preserves AgentCanary's legacy tools for compatibility. Calls return retirement information and social links rather than contacting the retired product API.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "mrcerq-agentcanary": {
      "command": "npx",
      "args": [
        "-y",
        "agentcanary-mcp"
      ]
    }
  }
}
Run commandnpx -y agentcanary-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmagentcanary-mcp1.4.8

Tools

19

Saved tool list · updated 3w ago

This tool takes no parameters.

Details

From the project README

AgentCanary MCP Server

AgentCanary's public API and MCP product were retired on 2026-07-09.

The npm package remains as a compatibility stub so existing MCP clients start cleanly and receive a clear retirement notice instead of failing on API keys or retired endpoints.

Daily AgentCanary briefs continue here:

Usage

npx agentcanary-mcp

No configuration is required. All legacy tools return the same retired-status payload with the current X and Telegram locations.

Tools

The server keeps the legacy tool names registered for compatibility:

  • get_briefs
  • get_indicators
  • get_regime
  • get_predictions
  • get_narratives
  • get_news
  • get_scores
  • get_scenario_analysis
  • get_signals
  • get_defi
  • get_btc_options
  • get_market_structure
  • get_central_banks
  • get_expectations
  • get_macro
  • get_open_interest
  • get_liquidations
  • diagnose
  • get_track_record

These tools do not contact retired AgentCanary product endpoints.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.