Skip to main content

Lantern Works deals — MCP server (read-only, local stdio)

mcp-name: io.github.connormatthewdouglas/lantern-works-deals

Built on the official Python MCP SDK (mcp>=1.10,<2, FastMCP). Tools:

Tool Args Returns
search_deals query, category, offer_type, max_price, tags[], limit (1-25, default 10), cursor {total, count, results[], next_cursor} (summary fields only)
compare_deals ids (2-5) {order, deals[], note} best value first
get_deal id the deal's public record

Errors: {"error": {"code": "invalid_argument|invalid_cursor|not_found|feed_unavailable|feed_invalid", "message": ...}}.

Data: https://thelanternworks.com/api/v1/deals.json, cached 5 min (stale copy served if a refetch fails). Overrides: LANTERN_DEALS_FILE (local JSON), LANTERN_DEALS_URL. Only an allow-list of public fields is returned. Ranking (core/deals.py) uses offer type, relevance, known price and verified_at freshness, never affiliate status or commission.

Install

git clone https://github.com/connormatthewdouglas/agent-work-stack-deals.git
cd agent-work-stack-deals
python3 -m venv .venv && .venv/bin/pip install -r mcp_server/requirements.txt

Claude Desktop (claude_desktop_config.json) / Cursor (.cursor/mcp.json):

{
  "mcpServers": {
    "lantern-works-deals": {
      "command": "/ABS/PATH/agent-work-stack-deals/.venv/bin/python",
      "args": ["/ABS/PATH/agent-work-stack-deals/mcp_server/server.py"]
    }
  }
}

Test

.venv/bin/pip install pytest && .venv/bin/python -m pytest -q tests
.venv/bin/python mcp_server/smoke/smoke_client.py   # real stdio client session, live feed

Package (built and tested locally, not yet on PyPI)

pyproject.toml at the repo root builds lantern-works-deals-mcp with a lantern-works-deals-mcp console command:

python3 -m build && pip install dist/lantern_works_deals_mcp-0.1.0-py3-none-any.whl
lantern-works-deals-mcp   # stdio server

Once published, the config becomes {"command": "uvx", "args": ["lantern-works-deals-mcp"]}.

Client validation

Transcripts in smoke/: official Python SDK client (transcript.txt), MCP Inspector CLI (inspector_cli_transcript.txt), OpenAI Agents SDK MCPServerStdio (agents_sdk_transcript.txt).

server.json passes mcp-publisher validate and has not been submitted.

Metadata

Release files for lantern-works-deals-mcp 0.1.0

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

Source distribution (sdist)

Source distribution for lantern-works-deals-mcp 0.1.0
File Size Uploaded Provenance
lantern_works_deals_mcp-0.1.0.tar.gz 14.4 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for lantern-works-deals-mcp 0.1.0
File Interpreter ABI Platform
lantern_works_deals_mcp-0.1.0-py3-none-any.whl Python 3 none any Details

Total release size: 27.0 kB

Release files / lantern_works_deals_mcp-0.1.0.tar.gz

Download URL lantern_works_deals_mcp-0.1.0.tar.gz
Size 14.4 kB
Tags Source
SHA-256 checksum
How to use checksums
2aab6eb215a598b5fcf2378fa5c0c081ba6ba5781616d456965e7117b81cd0e6
BLAKE2b-256 checksum
How to use checksums
f78274c0fca4eeccc089a03609e52e187cbf8f304dedf9cf3f5036d551d11fbf
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.5

Release files / lantern_works_deals_mcp-0.1.0-py3-none-any.whl

Download URL lantern_works_deals_mcp-0.1.0-py3-none-any.whl
Size 12.6 kB
Tags Python 3
SHA-256 checksum
How to use checksums
cb7928b30fcf03cb2788678222807b6d6de4ebfdd89eecdd16efe8feb6097573
BLAKE2b-256 checksum
How to use checksums
d09f154e5f19f3eb6739b0bac158962bfbb2a656a949924e2c8472de825f4a83
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/7.0.0 CPython/3.13.5

Security for lantern-works-deals-mcp 0.1.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

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