What this kind of tool is for
- Hand your agent a structured way to call a model or an inference API.
- Compare outputs from two different providers on the same prompt.
- Wire retrieval, embeddings, or generation into an existing agent workflow.
How to compare servers like this
- Provider coverage:
- Match the tool's supported providers and models to the ones your project uses.
- Cost exposure:
- Model-backed tools spend real API budget; check how usage and limits are configured.
- Maintenance signal:
- The provider landscape shifts weekly; prefer tools updated within the last few months.
- Config surface:
- Prefer tools whose environment-variable or config keys are documented plainly.
This page carries your copy-paste config: pick your MCP client in the install section on this page and use the copy button.
What is the Sprawl MCP server?
Build and supervise fleets of agents from Claude Code, Codex or Cursor. Connects over OAuth.
How to install Sprawl
Copy-paste configuration for popular MCP clients.
AuthorizationsecretOPTIONAL. This server supports OAuth 2.1 with PKCE, discovered automatically at /.well-known/oauth-protected-resource — browser-based clients (claude.ai connectors and similar) should use that and need no header at all. Supply this header only for headless, CLI, or CI callers that have no browser to complete consent with: a Sprawl API key as a bearer token, from https://sprawl.to/docs/mcp.
{
"mcpServers": {
"sprawl": {
"url": "https://sprawl.to/api/mcp"
}
}
}Related MCP servers

naia GEO Autopilot
Autopilot MCP server for GEO analyses, reports, content, audits, memories and agents.
AI-only game publishing, autonomous play, live observation, replay and independent certification.
Play Werewolf against other AI agents. join once, then loop observe/act. Public ELO leaderboard.
View repository →Stock market trading signals: regime, ranked buy list, stock + sector reads. Free tier + x402 live.
Unified.to MCP server — one API for 500+ B2B SaaS integrations across 28+ categories

Living Memory
An MCP memory server. One memory your agents share — across models, devices and apps.
