fleetstreet
Remote MCP server for the fleetstreet creator platform, enabling AI agents to register creative works, issue/revoke AI licences, access compliance evidence, and manage a creator business (catalog, merch, events) via 46 tools.
README
fleetstreet — Remote MCP
License your creative work to AI — on your terms. The first creator platform with built-in AI licensing, exposed to your agent as a remote MCP server.
Your copyright, enforced. And the whole creator business comes with it.
AI companies are training on the world's creative work. fleetstreet is the platform that lets a creator register every work — image, writing, or track — to an agent-to-agent copyright registry, issue per-use licences to the AI agents that want to read or reproduce it, revoke them, and pull a provable audit trail of exactly who accessed the work — and who was blocked. This remote MCP server puts that copyright moat, and the entire creator business behind it, directly inside any MCP-capable agent.
Works with: Claude Code · Claude Web · Claude Desktop · Cursor · ChatGPT · Cline · Windsurf · Raycast · any MCP client
- Endpoint:
https://mcp.fleetstreet.ai/sse - Health:
https://mcp.fleetstreet.ai/health - Server card:
https://mcp.fleetstreet.ai/.well-known/mcp/server-card.json - Auth: none required — keyless onboarding built in.
The copyright moat (A2A AI-licensing)
Five tools turn your agent into the control plane for who may train on your work:
fleetstreet_register_work— register a work (image, writing, or track) to the agent-to-agent copyright registry.fleetstreet_issue_licence— grant a scoped licence (read / summarise / reproduce) to another AI agent.fleetstreet_revoke_licence— pull a licence back.fleetstreet_licensing_access_log— a provable, tamper-evident log of every access — granted and blocked.fleetstreet_licensing— the licensing overview.
It's how an AI agent can legally read or reproduce a work — while the creator stays in control and gets paid. Every upload is screened for originality and registered with A2A Infrastructure; AI companies need a licence key to access the work.
…and the compliance evidence to prove it
Five more read-only tools turn that audit trail into regulator-ready evidence — the paperwork an AI company (or its lawyers) needs to show its training data was licensed:
fleetstreet_compliance— a point-in-time compliance snapshot.fleetstreet_compliance_posture— an at-a-glance posture check across the copyright controls.fleetstreet_compliance_frameworks— assessment mapped to the EU AI Act, NIST AI RMF, SOC 2, Colorado SB24-205 and GDPR.fleetstreet_compliance_audit_events— the OCSF audit event stream (filter by allowed / blocked).fleetstreet_compliance_export— export the evidence as a portable file.
…and the whole creator business comes with it
fleetstreet is a multi-tenant platform where creators build a site and sell works, merch, tickets, fan subscriptions and crowdfunding — keeping ~95% of revenue via Stripe Connect. This server exposes that whole surface as 46 tools — exact parity with the fst CLI's per-creator agent surface, plus the AI-licensing and compliance suite — led by fleetstreet_tai, a built-in AI manager with full context of the creator's catalog, merch, events, fans and settings. Ask it "which work should I release next?" or "draft an announcement" and it advises and takes safe actions on the creator's behalf.
Keyless onboarding
No signup friction. A fresh agent starts with two tools — fleetstreet_get_started and fleetstreet_signup. After self-signup the full 46-tool set unlocks in place (via notifications/tools/list_changed). Signup returns a scoped fsk_ key that works immediately for reads; writes stay gated until the human owner completes the 7-day-free-trial card check ($0 today), so the abuse surface is zero. The agent never handles a tenant ID — it's derived from the key.
Connect
Remote — no install:
{
"mcpServers": {
"fleetstreet": { "url": "https://mcp.fleetstreet.ai/sse" }
}
}
With a key (for an existing creator), pass the fsk_ key as a bearer token if your client supports headers:
{
"mcpServers": {
"fleetstreet": {
"url": "https://mcp.fleetstreet.ai/sse",
"headers": { "Authorization": "Bearer fsk_yourslug_..." }
}
}
}
Try it (no key, no install): connect to https://mcp.fleetstreet.ai/sse, call fleetstreet_get_started, then fleetstreet_signup with a creator name + email.
Structured output
Every JSON-returning tool declares an outputSchema and returns structuredContent on tools/call, so directory scanners and typed clients get machine-readable results, not just text. (46 / 46 tools carry an outputSchema.)
Docs
LISTING-KIT.md— canonical copy/metadata for every MCP-directory listing + the full 46-tool inventory.server.json— MCP registry manifest.
License
Proprietary — Tyga.Cloud Ltd. See LICENSE.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.