DealX

MCP (Model Context Protocol) server enabling LLMs to search classified ads on the DealX platform (Ukrainian marketplace). Provides standardized tool interface with query, sorting, and pagination support for ad discovery.

Evaluated Apr 04, 2026 (20d ago)
Repo ↗ Automation mcp-server dealx marketplace classifieds integration typescript ukrainian agent-tools
⚙ Agent Friendliness
54
/ 100
Can an agent use this?
🔒 Security
46
/ 100
Is it safe for agents?
⚡ Reliability
28
/ 100
Does it work consistently?

Score Breakdown

⚙ Agent Friendliness

MCP Quality
60
Documentation
72
Error Messages
--
Auth Simplicity
95
Rate Limits
10

🔒 Security

TLS Enforcement
80
Auth Strength
25
Scope Granularity
0
Dep. Hygiene
65
Secret Handling
70

TLS likely enforced via axios to DealX backend (assumed HTTPS). Environment variable handling is safe (no hardcoded secrets). Minimal dependency set (axios, @modelcontextprotocol/sdk, dotenv) limits attack surface. No CVE tracking visible. Zero scopes (auth-less model). No published security policy or disclosure process. Early-stage (v0.1.9) suggests light security review.

⚡ Reliability

Uptime/SLA
0
Version Stability
35
Breaking Changes
55
Error Recovery
20
AF Security Reliability

Best When

You need simple LLM-friendly DealX search in conversational contexts without custom API wrapper development and can tolerate early-stage software maturity.

Avoid When

You need production reliability, full ad management (CRUD), documented error recovery, or explicit rate limit guarantees. Version 0.1.9 unsuitable for SLA-dependent deployments.

Use Cases

  • LLM agents searching DealX classifieds without direct API integration
  • Claude Desktop and Cline integration for ad discovery tasks
  • Building conversational interfaces for Ukrainian marketplace listings
  • Price comparison and market research assistants

Not For

  • Creating, editing, or deleting ads (search-only implementation)
  • Production environments without reliability guarantees
  • High-volume commercial operations requiring full ad lifecycle management
  • Mission-critical systems (early-stage 0.1.9 version)

Interface

REST API
No
GraphQL
No
gRPC
No
MCP Server
Yes
SDK
No
Webhooks
No

Authentication

Methods: Environment variable (DEALX_API_URL)
OAuth: No Scopes: No

Zero explicit auth. Server forwards DEALX_API_URL env var to DealX backend; authentication model delegated to underlying DealX platform (undocumented).

Pricing

Model: Free (MIT open source)
Free tier: Yes
Requires CC: No

Open source NPM package. DealX platform pricing/limits not documented. No documented rate limits at server or platform level.

Agent Metadata

Pagination
offset-limit (1-indexed offset, max limit 100)
Idempotent
True
Retry Guidance
Not documented

Known Gotchas

  • DEALX_API_URL must be set or server fails silently; no informative startup error
  • Only search_ads tool implemented; roadmap lists create/edit/delete/threads but unimplemented
  • Error handling collapses all failures to generic InternalError; agents cannot distinguish timeout from 404 from auth failure
  • No documented timeout behavior; slow DealX API may hang agent indefinitely
  • Rate limits (if any) are undocumented; agents may exceed limits without warning
  • Pagination offset is 1-indexed not 0-indexed; common agent mistake
  • Max 100 results per page; large result sets require multiple API calls
  • Created 2025-04-01 (recent); 0 stars, 2 forks suggest minimal adoption/testing
  • No TypeScript types exported for tool parameters; agents must infer from description

Alternatives

Full Evaluation Report

Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for DealX.

AI-powered analysis · PDF + markdown · Delivered within 30 minutes

$99

Package Brief

Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.

Delivered within 10 minutes

$3

Score Monitoring

Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.

Continuous monitoring

$3/mo

Scores are editorial opinions as of 2026-04-04.

8642
Packages Evaluated
17761
Need Evaluation
586
Need Re-evaluation
Community Powered