---
title: "Kagi MCP Server: review, setup & limitations · Undominated.ai"
canonical: https://undominated.ai/mcp-servers/kagi/
description: "Search with Kagi and extract selected pages through a hosted or local MCP server."
---

# Kagi MCP Server: review, setup & limitations · Undominated.ai

> Search with Kagi and extract selected pages through a hosted or local MCP server.

[← Explore all mcp servers](/mcp-servers/)

WEB SEARCH / Kagi Search

# Kagi MCP Server

Search with Kagi and extract selected pages through a hosted or local MCP server.

 [See setup guidance ↓](#setup)[Original source ↗](https://github.com/kagisearch/kagimcp)

SOURCE REVIEW

 Reviewed 2026-10-14
 Evidence 3 linked sources
 Publisher Kagi Search
 Licence [MIT ↗](https://github.com/kagisearch/kagimcp/blob/55b38d20c67f1406f2c284af776de395297a75cc/LICENSE)
 Revision 55b38d20c67f
 [Read what was—and wasn’t—checked ↓](#review)

“It exposes search and extraction tools to MCP-compatible clients.”

 [Kagi Search · upstream description ↗](https://github.com/kagisearch/kagimcp/blob/55b38d20c67f1406f2c284af776de395297a75cc/README.md) Our analysis follows below.

01 / THE REASONING

## Why this made the selection.

 - Publisher-maintained integration with a documented hosted or local setup and explicit data/cost boundaries.
- Provides both hosted bearer access and a documented per-request identity model for self-hosting.
- The pinned README is Kagi search and page extraction, as a hosted MCP URL or a local uvx process.
- OAuth is not implemented on this pin, and the older FastGPT and summarizer tools are gone.

### A good fit for

 - Search web/news or a configured lens, then extract only the relevant source pages.
- Apply date/domain constraints for a focused research comparison and keep evidence URLs.
- Kagi web search or full-page extraction from an HTTP MCP client that can send a bearer API key

### Weigh up before choosing

 - Hosted OAuth is not supported in the reviewed documentation; supply an API key as a bearer header. A consumer login alone is insufficient.
- The local package requires Python 3.12.x. Its search and extraction timeouts are distinct, and slow requests can need explicit adjustment.
- KAGI_HIDDEN_PARAMS hides fields from the model-facing schema; it should not be described as an account-level authorization or domain firewall.
- Search and extraction results require verification for freshness, source access and completeness; API charges and quotas remain separate.
- FastGPT and the summarizer are not in this revision.
- Hosted and HTTP modes need a Kagi API key on each request or in the environment.
- The README does not provide an anonymous endpoint.
- A pin does not verify transitive dependencies.
- This review did not execute the resource.
- Schema hiding is not a credential permission boundary; the hosted server currently requires bearer API-key authentication rather than OAuth.

02 / THE REVIEW RECORD

## What we actually inspected.

Source review has boundaries. A clear record is more useful than a “safe” badge.

### Material inspected

 - README.md
- LICENSE
- pyproject.toml
- Round 2 reread of acquired publisher setup and permission evidence; see immutable wave review.

### Our findings

 - README and pyproject.toml distinguish hosted bearer authentication, local runtime and separate search/extract timeouts.
- The supplied setup uses the hosted endpoint and does not execute or install the Python package.
- The server exposes kagi_search_fetch and kagi_extract. The README says kagi_fastgpt and kagi_summarizer have been removed.
- The hosted URL is https://mcp.kagi.com/mcp. OAuth2 is not supported yet, so the client sends a Kagi API key as a bearer token.
- Self-hosted HTTP mode is multi-tenant: each request supplies its own key instead of one server-wide environment variable. A local uvx run still needs KAGI_API_KEY.
- KAGI_HIDDEN_PARAMS can remove selected search arguments from the model-facing schema, and retry/timeout settings are separately configurable.

### Not established by this review

 - Server startup, authentication, live tool execution and security isolation were not tested.
- Published package/container parity with a source revision and hosted implementation internals were not tested.
- The server was not started and its tools were not called.
- A pin does not verify transitive dependencies.

The review applies to the material and revision named here. A newer upstream release can change its behavior.

03 / PUT IT TO WORK

## Connect a server deliberately.

[Upstream setup instructions ↗](https://github.com/kagisearch/kagimcp/blob/55b38d20c67f1406f2c284af776de395297a75cc/README.md)

DOCUMENTED COMMAND

 claude mcp add kagi -e KAGI_API_KEY="YOUR_API_KEY_HERE" -- uvx kagimcp Copy command ↗

Copying does not execute this command. It may retrieve a newer version than the reviewed source.

 - The command above is the README's Claude Code registration; replace the placeholder with your key. It was not run.
- Other clients use the README's uvx kagimcp block, or the hosted https://mcp.kagi.com/mcp with an Authorization bearer header. Do not commit the key.

### Before you start

 - uv
- Python 3.12
- A Kagi API key

### Documented configuration example

Use the client and authentication context described in the setup guidance. Configuration formats vary between hosts.

 {
 "mcpServers": {
 "kagi": {
 "command": "uvx",
 "args": [
 "kagimcp"
 ],
 "env": {
 "KAGI_API_KEY": "YOUR_API_KEY_HERE"
 }
 }
 }
} Copy configuration ↗

### Compatibility

Codex CLI · Claude Desktop · Claude Code · Kiro · OpenCode

### Implementation

Python

### Transports

stdio · Streamable HTTP

### Web research

 - Submits queries and URL extraction requests to Kagi using the caller API key.
- The self-hosted HTTP documentation selects each request identity from its bearer header.

### Cost model

Publisher API usage, account plans and selected paid operations apply separately from the source licence.

04 / FOLLOW THE EVIDENCE

## The source trail.

Our notes are separate from the original resource. Check upstream before adopting a new version.

 - [Publisher setup, capabilities and operating boundaries ↗](https://github.com/kagisearch/kagimcp/blob/55b38d20c67f1406f2c284af776de395297a75cc/README.md) Checked 2026-10-14 https://github.com/kagisearch/kagimcp/blob/55b38d20c67f1406f2c284af776de395297a75cc/README.md Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports
- [Inspected implementation or package metadata ↗](https://github.com/kagisearch/kagimcp/blob/55b38d20c67f1406f2c284af776de395297a75cc/pyproject.toml) Checked 2026-10-14 https://github.com/kagisearch/kagimcp/blob/55b38d20c67f1406f2c284af776de395297a75cc/pyproject.toml Supports: summary, install, configExample, access, limitations, bestFor, review, compatibility, transports
- [Source licence; hosted service terms are separate ↗](https://github.com/kagisearch/kagimcp/blob/55b38d20c67f1406f2c284af776de395297a75cc/LICENSE) Checked 2026-10-14 https://github.com/kagisearch/kagimcp/blob/55b38d20c67f1406f2c284af776de395297a75cc/LICENSE Supports: license

KEEP COMPARING

## Other approaches to consider.

Related by category or shared topics. These are alternatives to inspect, not a measured quality order.

 [### Brave Search MCP ↗ Provides web, news, image, video and place search using the Brave Search API.](/mcp-servers/brave/)[### Algolia MCP Server ↗ Algolia's managed MCP offerings: Public MCP exposes application-scoped search and recommendations on selected indices for customer-facing agents; Productivity MCP gives user-scoped, read-only exploration and analytics; DevEx MCP serves version-matched API client snippets to coding agents without touching data.](/mcp-servers/algolia/)[### Bright Data MCP Server ↗ Search-engine results, page scraping, pre-built structured-data scrapers and a remote browser through Bright Data's proxy infrastructure, from a hosted URL or a local npx package.](/mcp-servers/brightdata/)

 [AI Tools ↗](/tools/)[Skills ↗](/skills/)[Agents ↗](/agents/)[MCP Servers ↗](/mcp-servers/)[Workflows ↗](/workflows/)

## Continue your investigation

 - [Inspect resource evidence](/tools/)
- [Choose a host](/agents/)
- [Inspect reusable workflows](/skills/)
- [Use Undominated data](/api/)
