MCPModel Context Protocol

AI agents

Set up with AI

Open your project in a coding agent that can read URLs, edit files, and run commands. Copy this prompt and paste it into your agent — the skill it points at carries the setup steps:

Set up Predictefy in this project using this skill: https://docs.predictefy.com/.well-known/agent-skills/predictefy/skill.md

For a chat connection, add the client name to your prompt. The agent sets up the SDK or MCP connection and verifies a small authenticated market query. You may need to sign in and create a key, enter it locally, or reload your chat client before verification can finish. The verification request uses API credits.

You can use the prompt without installing the skill first. For manual setup or a reusable skill, choose a route below.

Using an LLM (Claude, Cursor, ChatGPT)? Predictefy ships an MCP server exposing 59 tools — 49 default tools, being 40 read, intelligence, and platform tools for normalized markets, order books, history, cross-venue intelligence, and trader analytics across 16 served prediction-market venues plus 9 paper tools for simulated orders, and 10 guardrailed execution tools for a non-custodial trade surface that stay off until you opt in. One-line install: npx -y @predictefy/mcp (get a free API key at portal.predictefy.com/keys). No install? Paste https://docs.predictefy.com/llms.txt into your LLM — it is a self-contained integration brief. Building an autonomous agent? Start with the TypeScript SDK or Python SDK and the published agent skill. Pick your route below.

Which piece is which

Layer	Asset	Reach for it when
Context	`llms.txt`	You want a curated, self-contained integration brief to paste into an LLM.
Context	`llms-full.txt`	All 56 authored pages plus the generated API operation catalogue.
Context	Per-page `.md` twins	Clean Markdown for any of the 56 authored pages; API pages have no twin.
Tools	`@predictefy/mcp`	A chat client or agent needs callable Predictefy tools at runtime.
Tools	REST API	You need the normalized HTTP contract directly.
Tools	`@predictefy/sdk`	You are building a typed TypeScript agent.
Tools	`predictefy` on PyPI	You are building a Python research, automation, or backtesting agent.
Tools	`@predictefy/cli`	An agent or operator needs the same API from a shell.
Discovery	`/.well-known/agent-card.json`	An A2A platform needs Predictefy’s identity and capability card.
Discovery	`/.well-known/agent-skills/`	A platform needs the published skill URL and integrity digest.
Discovery	`/.well-known/mcp/server-card.json`	An MCP directory or platform builder needs the local stdio install contract.
Discovery	The `llms.txt` convention	A crawler checks the docs origin for an LLM-readable starting point.
Discovery	`sitemap-index.xml`	A crawler needs the complete index of docs URLs.

Route A — use Predictefy from your chat client

Start read-first. Use the MCP server for research, market screening, cross-venue comparison, and Trader Intelligence. Treat price gaps as indicative price discrepancies unless every live executability gate passes.

Create a free key at portal.predictefy.com/keys, then choose your client.

Claude Code

claude mcp add predictefy -e PREDICTEFY_API_KEY=pk_live_your_key_here -- npx -y @predictefy/mcp

Claude Desktop

Add this server to claude_desktop_config.json:

{
  "mcpServers": {
    "predictefy": {
      "command": "npx",
      "args": ["-y", "@predictefy/mcp"],
      "env": {
        "PREDICTEFY_API_KEY": "pk_live_your_key_here"
      }
    }
  }
}

Cursor

Create .cursor/mcp.json in your project:

{
  "mcpServers": {
    "predictefy": {
      "command": "npx",
      "args": ["-y", "@predictefy/mcp"],
      "env": {
        "PREDICTEFY_API_KEY": "pk_live_your_key_here"
      }
    }
  }
}

VS Code

Create .vscode/mcp.json in your workspace:

{
  "servers": {
    "predictefy": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@predictefy/mcp"],
      "env": {
        "PREDICTEFY_API_KEY": "pk_live_your_key_here"
      }
    }
  }
}

Advanced: trading from chat

The 10 execution tools are off by default. Set MCP_ENABLE_TRADE=true or 1 to enable them and opt into trade per key in the console. Unset or MCP_ENABLE_TRADE=false disables the tools.

No tool both builds and signs an order: build operations return unsigned artifacts, and signing stays client-side. Server-side spend caps still apply — by default, 100 USD per order and 1,000 USD per API key over a rolling 24 hours. Read Trading & execution before acting; it records the current per-venue reality and guardrails.

Route B — build an agent on the API

Choose context at the granularity your agent needs:

Paste llms.txt when the model needs a compact integration brief in-context.
Load llms-full.txt when you need all 56 authored pages plus the complete generated API operation catalogue.
For one authored page, use /index.md, /quickstart.md, or replace the trailing slash in a /guides/**/ or /reference/**/ URL with .md.
Do not append .md to /api/ or /api/operations/**/: the generated API reference has no per-page markdown twins. Use llms-full.txt for its operation catalogue.

Install the published agent skill

The canonical skill is served at https://docs.predictefy.com/.well-known/agent-skills/predictefy/skill.md.

For Claude Code, install it at ~/.claude/skills/predictefy/SKILL.md:

mkdir -p ~/.claude/skills/predictefy
curl -fsSL https://docs.predictefy.com/.well-known/agent-skills/predictefy/skill.md \
  -o ~/.claude/skills/predictefy/SKILL.md

For runtimes using the Agent Skills ecosystem, install the same file in the shared user directory:

mkdir -p ~/.agents/skills/predictefy
curl -fsSL https://docs.predictefy.com/.well-known/agent-skills/predictefy/skill.md \
  -o ~/.agents/skills/predictefy/SKILL.md

Other runtimes can fetch the raw .well-known URL directly. The skill discovery index publishes its URL and digest.

Discovery cards for platform builders

agent-card.json advertises the A2A identity and capabilities.
agent-skills/index.json lists the published skill and its integrity digest.
mcp/server-card.json describes the local stdio MCP package and install contract; it does not advertise a hosted MCP endpoint.

Build with the API, SDKs, or CLI

Use the REST API when your agent owns its HTTP client.
Use @predictefy/sdk for TypeScript or predictefy on PyPI for Python.
Use @predictefy/cli, the terminal and AI-agent client, when shell commands are the right integration boundary.

npm install @predictefy/sdk
pip install predictefy
npm install --global @predictefy/cli