Fleetstreet MCP server
online · 100% uptimeLicense your creative work to AI on your terms, and run your creator business. 46 tools, keyless.
0 stars
Reviews
Write oneNobody has reviewed Fleetstreet yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Fleetstreet tools (2, 1 write)
write = sends, deletes, buys or postsfleetstreet_get_startedFreeExplains what fleetstreet is and how to activate this MCP server (no API key on this session yet).
fleetstreet_signupwrite actionFreeCreate a new fleetstreet portfolio site. Requires the human's email and a portfolio/studio name: a welcome + activation email is sent to them (card required via Stripe to start the 7-day free trial, nothing charged during it). Returns an API key (shown once) and unlocks all fleetstreet tools in this session immediately. Ask the human for their email and portfolio name before calling.
Public scan report
scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 1637ms20/20
- Tool poisoning2 tool descriptions checked15/15
- Auth qualityAPI key sent as a header8/15
- Maintenancelast push 49 days ago12/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Fleetstreet compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 84/100
- higher than 68% of 48,255 servers
- Tools
- 2
- the typical server has 7
- Tools that change things
- 50%
- typical: 0%. Fewer write tools means less an agent can break
- Uptime
- 100%
- of our recent checks; the typical remote server answers 100%
- Response time
- 171 ms
- faster than 69% of 30,031 servers
What its tools let an agent do: 1 read · 1 change
Install Fleetstreet in Claude Code, Cursor or VS Code
claude mcp add --transport http fleetstreet https://mcp.fleetstreet.ai/sse
What the publisher says
From the Fleetstreet repository's README, as published. We do not edit it. Read it on GitHub
fst
Platform management for fleetstreet — license your creative work to AI, on your terms. Tenant admin, analytics, AI licensing, compliance evidence, support tickets - from the terminal.
Install
npm install -g fleetstreet-cliQuick Start
# Login with your SuperAdmin API key
fst login --key YOUR_SA_API_KEY
# Platform dashboard
fst stats
# Revenue metrics
fst revenue
# Signup funnel
fst funnel
# List all tenants
fst tenants
# View a tenant
fst tenant show TENANT_ID
# Support tickets
fst tickets
fst ticket show TKT-abc123
# Chat with τAI h-conductor
fst tai "show me open P0 bugs" --dept dev
# AI Licensing (A2A copyright moat)
fst licensing harbourlight # licensing overview for a creator
fst licensing harbourlight register ID # register a work (image, writing, video, or track)
fst licensing harbourlight issue ID # issue a scoped AI licence (view|derivative|train)
fst licensing harbourlight access-log # provable access log (granted + blocked)
# Video works (footage)
fst videos harbourlight # list video works
fst videos harbourlight create "Title" --set videoUrl=https://... # create (then register + license)
# Voice consent registry (voice works)
fst voice-consents harbourlight # list actor consents
fst voice-consents harbourlight create --actor "Name" --email a@x.com --scopes read,summarise
fst voice-consents harbourlight revoke ID --reason "..." # blocks fuFeatures
- Dashboard - tenant counts, user stats, post/order totals
- Revenue - MRR, ARR, platform fees, payouts
- Funnel - signup → verified ($1) → active → paying
- Tenants - list, view, suspend, activate
- Support - tickets, reply, close
- τAI Chat - talk to h-conductor (6 departments: dev, devops, bizintel, compliance, helpdesk, fixer)
- AI Licensing - register works (images, writing, music), issue/revoke per-use AI licences, provable access log (the A2A copyright moat)
- Compliance - posture score, framework assessment (EU AI Act, NIST AI RMF, SOC 2, Colorado SB24-205, GDPR), OCSF audit-event stream + export
Compliance-for-agents parity
The same AI-licensing and compliance surface is exposed to per-creator agents over the remote MCP server (mcp.fleetstreet.ai, v1.3.1, 46 tools). An agent authenticated with a creator-scoped fsk key gets read-only fleetstreetcompliance, fleetstreetcomplianceposture, fleetstreetcomplianceframeworks, fleetstreetcomplianceauditevents and fleetstreetcompliance_export tools — a per-creator mirror of the fst compliance commands here (which run platform-wide via the SuperAdmin API). Same evidence, two front doors: this CLI for platform operators, the remote MCP for a creator's own agent.
Config
fst login --local --key YOUR_KEY # saves to .fst/config.json (project-local)
fst login --key YOUR_KEY # saves to ~/.fst/config.json (global)
fst config # show which config is activeLocal config overrides global. Add .fst/ to your .gitignore.
Agent Integration
Add to your CLAUDE.md or agent instructions:
## fleetstreet Admin
Use the fst CLI for platform management.
Key is in .fst/config.json (auto-loaded).
Run fst --help for full reference.JSON Output
All commands support --json for machine-readable output:
fst stats --json
fst tenants --json
fst tickets --jsonDocumentation
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Fleetstreet: common questions
- Is Fleetstreet MCP server safe?
- Mostly: it is graded B (84/100). Read the Fleetstreet safety report
- How do I install Fleetstreet?
- It runs remotely at mcp.fleetstreet.ai. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Fleetstreet need an API key?
- Yes. The registry entry asks for
Authorization. - Is Fleetstreet maintained?
- The last commit was 89 days ago (2026-08-06). The latest release is v1.3.1.
- Is Fleetstreet up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- How does Fleetstreet compare with other MCP servers?
- safety score 84/100 (higher than 68% of 48,255 servers); tools 2 (the typical server has 7); tools that change things 50% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.