MCP server for AgentCanary that provides market intelligence data such as regime classifications, risk scores, narratives, scenario probabilities, predictions, news, macro indicators, and positioning signals. It also exposes a public track-record endpoint and a diagnose tool for tier, scope, and credit issues.
From the registry: Market context for AI agents: fresh regime, risk, narrative and scenario state via REST + MCP.
$ curl -X POST https://api.agentcanary.ai/api/keys/create -H "Content-Type: application/json" -d '{"walletAddress": "<your-wallet-address>"}'Please install the `agentcanary` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js and npx** — Install Node.js so the MCP server can be launched with npx.
- **AgentCanary API key** — Create an AgentCanary API key. Most tools require AC_API_KEY. The README shows creating a key by POSTing your wallet address, and notes you may need to deposit funds to access higher tiers or credits. Run: `curl -X POST https://api.agentcanary.ai/api/keys/create -H "Content-Type: application/json" -d '{"walletAddress": "<your-wallet-address>"}'` (https://api.agentcanary.ai/api/docs)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","agentcanary-mcp"]
- required environment variables:
- `AC_API_KEY`: AgentCanary API key used to authenticate requests. Required for the default configuration and for most tools; only the public track record data is noted as not requiring a key. (example: `<your-agentcanary-api-key>`)
Note: Quick start shows `npx agentcanary-mcp`; client config examples use `npx -y agentcanary-mcp`, which is the most portable canonical stdio shape.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.AC_API_KEYrequiredAPI key used to authenticate with AgentCanaryMeta Ads MCP (Facebook + Instagram) - analyze performance, manage budgets, pause campaigns.