Skip to main content

fless-mcp

Fless apartment-hunting tools for any MCP-capable AI agent: a zero-dependency stdio proxy to the hosted Fless MCP server at https://mcp.fless.io/mcp.

What it does

Your agent researches apartments with live Fless data and hands you a pre-filled hunt link:

  • search_cities: live + coming-soon cities
  • get_city_overview: neighborhoods with median rents + WalkRating(TM) scores
  • get_neighborhood: full detail (rents, scores, POI counts)
  • get_hunt_requirements: every hunt field, enum, binary restriction (55+, pets, smoking), transparent pricing
  • build_hunt_link: validate a brief, get a URL that pre-fills the entire hunt form
  • check_hunt_link: created → opened → started lifecycle
  • search / fetch: ChatGPT deep-research compatibility pair
  • request_city: ask Fless to expand to a new city (write tool, rate-limited)
  • get_city_request_stats: see which cities have the most demand
  • submit_error_report: report problems with tools or data (write tool, rate-limited)

Research and hand-off tools are anonymous, no key needed. Your human creates the account, verifies email, approves the matched buildings, and pays. Agents never do.

Hunts NEVER email buildings automatically: all hunts (2.0.0 approval gate) run an instant matched-building list at creation, park at an approval gate, and Fless emails only the buildings the human explicitly approves in their dashboard. Fail-closed: untouched buildings are removed.

Licensed realtors with a Fless for Realtors account ($49.99/mo flat, 15-day free trial) get 8 authenticated realtor_* tools (client funnel: invite, hunt, curate, send to client) by sending an API key from fless.io/realtor as Authorization: Bearer fless_ak_... on every MCP call. Anonymous callers keep the public toolset.

Where we operate

Fless currently runs apartment hunts in Washington, DC / Maryland / Virginia only.

✅ Live now 🚧 Coming soon
Alexandria, VA Arlington, VA
Annapolis, MD Baltimore, MD
Frederick, MD Rockville, MD
Leesburg, VA Silver Spring, MD
Washington, DC
Richmond, VA + more

Your city not listed? We're expanding. Check back, or join the waitlist at fless.io. Agents: always call search_cities first.

Install

Claude Desktop / any stdio MCP client

{
  "mcpServers": {
    "fless": {
      "command": "uvx",
      "args": ["fless-mcp"]
    }
  }
}

Or with pip:

pip install fless-mcp
fless-mcp   # speaks JSON-RPC on stdio

Remote (no install needed)

Most clients connect to the hosted server directly:

https://mcp.fless.io/mcp

See per-assistant setup guides (Claude, ChatGPT, Perplexity, Grok, Mistral Vibe, Codex, OpenClaw, Hermes): https://fless.io/ai-agents

Environment

Variable Default Purpose
FLESS_MCP_URL https://mcp.fless.io/mcp Remote server (fallback: https://www.fless.io/mcp)
FLESS_MCP_UA fless-mcp/1.3.0 (+https://fless.io/ai-agents) User-Agent

fless-apartment-hunt: an Agent Skills-standard skill that teaches your agent the full workflow:

hermes skills install well-known:https://fless.io
# or from GitHub:
npx skills add fless-io/skills

License

MIT

Metadata

Release files for fless-mcp 1.3.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for fless-mcp 1.3.0
File Size Uploaded
fless_mcp-1.3.0.tar.gz 4.6 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for fless-mcp 1.3.0
File Interpreter ABI Platform
fless_mcp-1.3.0-py3-none-any.whl Python 3 none any Details

Total release size: 9.6 kB

Release files / fless_mcp-1.3.0.tar.gz

Download URL fless_mcp-1.3.0.tar.gz
Size 4.6 kB
Tags Source
SHA-256 checksum
How to use checksums
77d5b491c4c71d957b7898c726fc07420ae2980a76b21b4fc4e562079642080e
BLAKE2b-256 checksum
How to use checksums
a396f9c2b03588815b4b978cf07d5988dba88edfb8c5765b4f97a846c6fe1e50
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.11.16

Release files / fless_mcp-1.3.0-py3-none-any.whl

Download URL fless_mcp-1.3.0-py3-none-any.whl
Size 5.0 kB
Tags Python 3
SHA-256 checksum
How to use checksums
9e5c53a78cf575ffea4aa37f77107a99695becdff952a791c40087d92841c6b5
BLAKE2b-256 checksum
How to use checksums
c8ec29593f63223d0e57eed1979b1d492d61a39249897349b61a28b0e4d23c18
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.11.16

Release history Release notifications | RSS feed

1.4.1

2 release files

This release

1.3.0 This release

2 release files

1.2.0

2 release files

1.1.0

2 release files

1.0.1

2 release files

1.0.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page