mcpField
T
Teklif

Teklif

Remote
teklif.niyazi.siteBusiness & Marketing0Updated 6d ago

About Teklif

Teklif is a remote MCP server for searching and comparing offers, currently listing Nodify-owned Aegis Scanner plans. It is intended for people comparing offers; results include source information and provider links, while purchases and bookings remain on the provider site.

Key features

  1. 01Search offers by category and filters
  2. 02Compare offers side by side
  3. 03Sort by price, rating, or relevance
  4. 04Offer-card carousel interface
  5. 05Source field for each offer

Use cases

  1. 01Find plans within a budget
  2. 02Compare one-time or monthly plans
  3. 03Sort offers by rating or relevance
  4. 04Open a provider page for an offer

MCP support

Provides `search_offers`, `compare_offers`, and `get_offer_link` through a remote MCP server using Streamable HTTP. An MCP Apps interface displays offer cards; the current catalog contains Nodify-owned Aegis Scanner plans.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://teklif.niyazi.site/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

Teklif MCP

Neutral, user-initiated offer search and comparison exposed as a remote MCP server with an interactive card widget.

Website motto (site only, not in tool outputs): Tekliflerinizi her yapay zeka sunsun

Current catalog: operator-owned Aegis Scanner security plans (source field = aegisscanner.com pricing (operator-owned)). Teklif does not take payment or book anything; links open the provider site. There is no paid ranking, sponsored placement or affiliate tracking.

Operator model: Teklif is published by Nodify (agency). Today it surfaces Nodify’s own Aegis Scanner plans. The same connector pattern is intended later as a service offered to other companies — still without paid ranking unless that is explicitly disclosed.

What it does

  • TypeScript remote MCP server (@modelcontextprotocol/sdk, Streamable HTTP)
  • Tools: search_offers, compare_offers, get_offer_link
  • MCP Apps UI: ui://teklif-mcp/offers-v11.html — offer card carousel
  • Sort options: price (default), rating, relevance — transparent, no paid placement
  • Every offer includes a source field

Live: https://teklif.niyazi.site · MCP: POST https://teklif.niyazi.site/mcp

Tools

ToolInputOutput
search_offerscategory, budget?, city?, sort_by?Matching offers + card UI
compare_offersoffer_ids?, category?, city?, sort_by?Side-by-side compare + card UI
get_offer_linkoffer_idProvider page URL on aegisscanner.com

Categories: one_time, monthly, addon, hepsi (all).

Annotations: readOnlyHint: true, destructiveHint: false, openWorldHint: false (embedded operator catalog).

Example prompts

  1. Show Aegis Scanner monthly plans under 10000 TL.
  2. Compare one-time Aegis offers.
  3. Get the link for aegis-starter.
  4. List all Aegis Scanner offers sorted by price.

Setup

npm install
npm run build
npm start
# Server:  http://127.0.0.1:8787
# MCP:     POST http://127.0.0.1:8787/mcp
# Preview: http://127.0.0.1:8787/preview

Env: PUBLIC_MCP_URL (production https://teklif.niyazi.site/mcp).

Connect in Claude / ChatGPT

  1. Add https://teklif.niyazi.site/mcp as a custom connector (no auth).
  2. Streamable HTTP · call search_offers.

Privacy & terms

Troubleshooting

SymptomWhat to try
tools/list empty / 405 on GET /mcpUse POST /mcp.
Widget blank in ClaudeConfirm PUBLIC_MCP_URL=https://teklif.niyazi.site/mcp.
Offer not foundCall search_offers first; use an id like aegis-growth.

Support

GitHub: nietzische-app/teklif-mcp

Publisher: Nodify · Support: [email protected]

License

MIT

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.