Field-by-field comparison

Compare the evidence before choosing an MCP.

Each signal stays separate, missing facts remain visible, and the column order follows your selection.

MCPs in this comparison

Uncheck an MCP to remove it. Comparing two or three keeps each signal in its own row.

Open canonical comparison link

Comparable alternatives

Shown only when capability or industry context overlaps.

Side-by-side MCP evidence comparison
Evidence fieldFli - Flight Search MCP Server and LibraryMCP100 Recommendedio.github.atilaahmettaner/tradingview-mcpMCP100 Recommended
Task fit
Best for
  • Searching flight options conversationally during early travel planning
  • Generating chart-based technical indicators and summaries for symbols supported by the project's TradingView integration
Not ideal for
  • Booking, guaranteed live inventory, or final price confirmation
  • Auditable investment decisions, guaranteed real-time quotes, or order execution
Avoid when
  • The workflow would make purchase decisions without verifying itinerary, baggage rules, fare terms, and current price at the provider
  • The output would be treated as financial advice or used without independently checking data freshness and symbol coverage
Provenance
Provenance details

Community implementation

github:punitarani · Publisher source ↗

Community implementation

io.github.atilaahmettaner · Publisher source ↗

Maintenance
Maintenance details

Repo: Sep 20, 2026

Package: Not documented

Repo: Sep 1, 2026

Package: Not documented

Popularity evidence
GitHub stars

3,186

GitHub stars · checked 2026-09-24T04:14:16.266000Z

4,624

GitHub stars · checked 2026-09-24T04:14:39.529000Z

Client coverage
Client coverage details
Claude Code✓ Local stdio
Claude Desktop✓ Local stdio
Codex✓ Local stdio
VS Code✓ Local stdio
Cursor✓ Local stdio
OpenCode✓ Local stdio
Claude Code✓ Local stdio
Claude Desktop✓ Local stdio
Codex✓ Local stdio
VS Code✓ Local stdio
Cursor✓ Local stdio
OpenCode✓ Local stdio
Client coverage noteLocal stdio runs on your computer. Streamable HTTP connects to a remotely hosted MCP server.
Access and data
AuthenticationNo MCP or Google API key or OAuth requirement is documented. The guide notes that some vendor fares may require a browser-minted session token.No TradingView account or API key is required. MARKETAUX_API_TOKEN is optional; hosted-service account and authentication details are not fully documented.
CostNo project or API price is documented. Provider, booking-vendor, client, and model charges remain separate or unknown.Self-hosting is MIT-licensed. The README lists hosted plans at $9 or $29 per month with a three-day trial, and a Marketaux free key limited to 100 requests per day.
PermissionsSearches Google Flights by route, dates, passengers, filters, and locale, and returns itineraries, fares, and airline, OTA, or direct booking links. No purchase action is documented.Accesses public market data for quotes, technical analysis, screeners, backtests, news, and sentiment. The publisher says it does not execute trades or manage money.
Data handlingSearch parameters are sent to the publisher-described reverse-engineered Google Flights API. Results include itinerary, price, and booking-link data; storage, telemetry, and retention are not documented.Market-data requests and results are processed by the self-hosted or hosted server. Optional news and sentiment calls use Marketaux when MARKETAUX_API_TOKEN is configured; provider retention is not documented.
Limitations
Tradeoffs
  • Conversational search is convenient, but flight inventory changes quickly and upstream data coverage may not include every carrier or fare condition.
  • Natural-language analysis is convenient, while upstream data availability and indicator interpretation can still be incomplete or wrong.
Risk contextThe publisher describes a reverse-engineered API and vendor-fare limitations, so independently verify prices and availability before purchase. Keep configurable HTTP mode local because MCP authentication is not documented.Outputs are informational, not financial advice, and can be delayed, inaccurate, or incomplete. Do not treat signals or backtests as recommendations; verify data and third-party terms. Version 0.9.0 fixes reported wrong exchange fallback, top_losers returning gainers, fabricated volume breakouts, and other analysis/backtest issues.
Evidence date
Editorial review2026-08-112026-09-05
Candidate evidence2026-09-24T04:25:05.554391Z2026-09-24T04:25:05.554391Z

Popularity, maintenance, fit, permissions, and client support are independent evidence fields.

Read the evidence method →