Kagimcp vs Tinysearch

A side-by-side look at the Kagimcp and Tinysearch MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.

Kagimcp logoKagimcpSearch & Data Extraction · Local subprocess (stdio)The Official Model Context Protocol (MCP) server for Kagi Search & other tools.80ExcellentAuth: api key requiredTinysearch logoTinysearchSearch & Data Extraction · Local subprocess (stdio)Self-hosted web research for MCP agents.43FairAuth: not declared

Verdict: choose Kagimcp for search & data extraction work as a local process; choose Tinysearch for search & data extraction as a local process. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

Kagimcp logoChoose Kagimcp when

  • You need dedicated capabilities in the Search & Data Extraction domain.
  • You prefer a local stdio subprocess transport.
  • Its auth model fits you: API key required.
  • You have the keys it needs: KAGI_API_KEY.
  • You want tools like kagi_search_fetch, kagi_extract.
Explore Kagimcp

Tinysearch logoChoose Tinysearch when

  • You need dedicated capabilities in the Search & Data Extraction domain.
  • You prefer a local stdio subprocess transport.
Explore Tinysearch

Feature & specification comparison

Rows where the two servers differ are marked.

SpecKagimcp logoKagimcpTinysearch logoTinysearch
CategorySearch & Data ExtractionSearch & Data Extraction
Quality signal80/100 · Excellent43/100 · Fair
Install commandConfirmedConfirmed
TransportLocal subprocess (stdio)Local subprocess (stdio)
AuthAPI key requiredNot declared
PricingBYOK (pay the provider)Not declared
Required env varsKAGI_API_KEYNone listed
Verified owner VerifiedCommunity listing
GitHub stars546234
Directory activity 3 views 0 installs 0 upvotes 2 views 0 installs 0 upvotes
Tools2Not listed

Tools & capabilities

Kagimcp tools 2

  • kagi_search_fetchFetch web results for a query using the Kagi Search API. Use for general search and when the user explicitly tells you to 'fetch' results/information. Results are numbered so that a user may refer to a result by a specific number.
  • kagi_extractExtract the content of a web page as markdown using the Kagi Extract API. Use this to read the full content of a page when needed.

Tinysearch tools

No tool names declared yet. Check the project README from the listing page.

Ready-to-paste client configs

Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.

Kagimcp

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "kagisearch-kagimcp": {
      "command": "uvx",
      "args": [
        "kagimcp"
      ],
      "env": {
        "KAGI_API_KEY": "YOUR_KAGI_API_KEY_HERE"
      }
    }
  }
}

Tinysearch

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "tinysearch": {
      "command": "uvx",
      "args": [
        "--from",
        "tinysuite-search[server]",
        "tinysearch"
      ]
    }
  }
}

Frequently asked questions

Kagimcp is categorized under Search & Data Extraction and uses a local stdio subprocess. Tinysearch belongs to Search & Data Extraction and uses a local stdio subprocess. Pick Kagimcp for search & data extraction work and Tinysearch for search & data extraction.

Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.

Kagimcp is bring-your-own-key: usage is billed by the API provider you supply a key for. Auth: api key required. Tinysearch has no declared pricing — check the project's own site. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.

Yes. MCP clients support multiple servers: add kagisearch-kagimcp and tinysearch as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, Kagimcp has a quality signal of 80/100 (Excellent) with 3 views, 0 installs and 546 GitHub stars. Tinysearch has 43/100 (Fair) with 2 views, 0 installs and 234 GitHub stars.