{
  "markdown": "# Parlay — Prediction Market MCP Server\n\n[![MCP Badge](https://lobehub.com/badge/mcp/parlay-run-parlay-mcp)](https://lobehub.com/mcp/parlay-run-parlay-mcp)\n\nThe AI-native intelligence layer for prediction markets.\n\n![Parlay cross-venue spread comparison across Polymarket and Kalshi](./docs/hero.png)\n\nParlay is a hosted MCP server for searching, comparing, and briefing prediction markets from AI assistants. It is a PMXT-backed aggregator over Polymarket, Kalshi, and Limitless, with Manifold treated separately as a sentiment-only signal. This repository is the public bundle and connection reference for the hosted Parlay service at `https://mcp.parlay.run/mcp`; it does not contain the MCP server implementation.\n\n## What it does\n\n| Tool | What it does |\n| --- | --- |\n| `search_markets` | Cross-venue keyword search for live prediction markets and event contracts |\n| `market_brief` | Synthesized brief on a topic, combining real-money signals with community sentiment |\n| `discover_markets` | Browse trending, high-volume, fast-moving, or high-disagreement markets |\n| `compare_markets` | Compare the same event contract across venues side-by-side — probability, liquidity, settlement |\n| `scan_discrepancies` | Surface cross-venue price discrepancies as a discovery feed (informational, not trade recommendations) |\n| `inspect_platform` | Drill into a single named venue |\n\nEvery tool response carries unified metadata: data freshness, venues queried, venues failed, market type (`real_money` / `sentiment` / `mixed`), match confidence (`high` / `medium` / `low` / `not_applicable`), liquidity status, risk flags, and a standard non-trade-recommendation disclaimer.\n\n## Connect\n\nParlay supports two connection paths depending on your client.\n\n### Path A — Claude.ai (Desktop, web, mobile, Cowork)\n\nParlay connects through Claude's Custom Connectors interface. The same flow works across all Claude surfaces.\n\n1. Open Claude settings (profile icon → **Settings**).\n2. In the sidebar, select **Connectors**.\n3. Scroll to the bottom and click **Add custom connector**.\n4. Enter URL: `https://mcp.parlay.run/mcp`\n5. Click **Add**, then **Connect** to complete OAuth authorization.\n\nParlay's tools will appear in your tool list on the next message.\n\n> **Note:** Custom Connectors are available on Free, Pro, Max, Team, and Enterprise plans. Free Claude users are limited to one custom connector at a time. Do **not** configure Parlay through `claude_desktop_config.json` — that file is for local stdio MCP servers only; Parlay is a remote MCP server.\n\n### Path B — OpenClaw, Cursor, Cline, Claude Code, LobeHub, and other JSON-config clients\n\nThese clients read MCP server configuration from a JSON file and don't run an OAuth dance themselves. Use a personal access token instead.\n\n1. Generate a token at https://parlay.run/settings/tokens\n2. Export it: `export PARLAY_TOKEN=parlay_pat_xxxxxxxxxxxx`\n\n**Security**: Treat your token as a secret. Do not share, log, or commit it. Store it only in your local MCP client configuration.\n\n#### Cline\n\n**Recommended**: Use Cline's Remote Servers tab → \"Add Server\", entering `https://mcp.parlay.run/mcp` as the URL, selecting **Streamable HTTP** as the Transport Type, and adding `Authorization: Bearer <your token>` as a header.\n\nFor manual JSON editing or detailed troubleshooting, see [llms-install.md](./llms-install.md). **Do not copy `.mcp.json` verbatim into Cline** — Cline uses a slightly different schema (covered in the install guide).\n\n**OpenClaw**\n\n```bash\ngit clone https://github.com/parlay-run/parlay-mcp.git\nopenclaw plugins install ./parlay-mcp\nopenclaw gateway restart\n```\n\n**Cursor / Claude Code**\n\nDrop the `parlay` entry from `.mcp.json` (at the root of this repo) into your client's MCP server config.\n\n```json\n{\n  \"mcpServers\": {\n    \"parlay\": {\n      \"url\": \"https://mcp.parlay.run/mcp\",\n      \"transport\": \"streamable-http\",\n      \"headers\": {\n        \"Authorization\": \"Bearer ${PARLAY_TOKEN}\"\n      }\n    }\n  }\n}\n```\n\n## Coverage\n\n- Real-money: Polymarket, Kalshi, Limitless\n- Sentiment (architecturally separated): Manifold\n- Catalog-only: Smarkets, Myriad, Metaculus, Probable, Baozi\n\n## Compliance posture\n\n- **Read-only.** No order placement, no position management, no fund custody.\n- **No private credentials handled.** Users never share venue API keys with Parlay.\n- **Sentiment isolation.** Manifold is mechanically excluded from real-money tools (`compare_markets`, `scan_discrepancies`). The `sentiment_market_excluded` risk flag is emitted whenever it is filtered out.\n- **Settlement and liquidity risk flags.** Markets with weak settlement criteria, missing volume data, or stale signals carry explicit risk flags in their metadata.\n- **Standard disclaimers.** Every tool response carries a non-trade-recommendation disclaimer in its metadata block.\n\n```\n                  Claude / ChatGPT / Gemini / OpenClaw\n                              ↕  (MCP over HTTPS)\n                    ┌────────────────────┐\n                    │  mcp.parlay.run    │\n                    │   (this server)    │\n                    └────────┬───────────┘\n                             │\n                ┌────────────┴────────────┐\n                ↓                         ↓\n       Real-money data layer    Sentiment data layer\n       Polymarket, Kalshi       Manifold\n       + secondary venues       (isolated)\n```\n\n## Pricing\n\n- **Free**: 15 tool calls / month (search_markets, market_brief)\n- **Pro**: $29/mo, 150 calls / month\n- **Team**: coming soon, 1,500 calls / month\n\n## Built on\n\nParlay's real-money venue access is built on [PMXT](https://www.pmxt.dev), an open-source unified SDK for prediction market venues. Parlay adds the AI intelligence layer on top: event comparability, settlement-risk metadata, sentiment isolation, and tool orchestration for MCP. PMXT trading methods are explicitly **not** exposed by Parlay — the hosted product is read-only by design.\n\n## Resources\n\n- [parlay.run](https://parlay.run)\n- Server endpoint: https://mcp.parlay.run/mcp\n\n## License\n\nThis repository — including connection examples, metadata, and client configuration files for the hosted Parlay MCP service — is licensed under the MIT License. See [LICENSE](LICENSE). The repository/service licensing split is also described in [TERMS.md](TERMS.md).\n\nThe hosted Parlay service at `mcp.parlay.run`, Parlay brand assets, APIs, data products, pricing, accounts, and service outputs are proprietary and governed by the Parlay Terms of Service: https://www.parlay.run/terms-of-service.\n",
  "bytes": 6544,
  "sha": "c72db5f02b0d1bc18637b0d74dc58e747e552392aee4f9374c61262b9a30c8f8",
  "repo_slug": "parlay-run/parlay-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_run_parlay_parlay_2726fdcd/readme"
}