# Kagi Search API > Kagi's Search API returns results from the Kagi search engine for web, image, video, news and podcast queries, with optional Markdown extraction of the top pages. It is a paid HTTP API in public preview, with a hosted MCP server. - Canonical: https://www.anchorterminal.com/tools/kagi-search - Markdown: https://www.anchorterminal.com/tools/kagi-search.md (~7,850 tokens) - Slim: https://www.anchorterminal.com/tools/kagi-search.min.md (~1,930 tokens, same facts, less prose, for token-sensitive contexts) - JSON: https://www.anchorterminal.com/tools/kagi-search.json (this page as data, same URL with Accept: application/json) - Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt) - API: https://www.anchorterminal.com/api/v1/index.json - Updated: 2026-10-10 ## Overview **Grade D · 48.7/100 · rank #807 of 950 · #15 in Web search APIs · not agent-ready · confidence medium** ## Assessment A public OpenAPI file, typed filters and API keys that can be limited by product and IP address make the API simple to call, at $12 per 1,000 searches. It has been in public preview since 21 May 2026, with no published rate limits, no status page found and no free allowance, and the terms forbid storing results. ## Facts | Field | Value | | --- | --- | | Vendor | Kagi (https://kagi.com) | | Kind | HTTP API | | Category | Web search APIs (https://www.anchorterminal.com/categories/search) | | Transport | HTTP, Streamable HTTP, stdio | | Endpoint | `https://kagi.com/api/v1/search` | | Auth | API key · Self-serve API key from the portal at kagi.com/api, sent as `Authorization: Bearer ` per the OpenAPI file. Each key can be limited to chosen products and to IP addresses or ranges, and deleted to revoke it. On Family and Team plans only the account owner can open the portal. The hosted MCP server takes the same key as a Bearer header, with no OAuth yet. | | Pricing | Pay per use ($12 / 1k req) · $12 per 1,000 searches and $4 per 1,000 extracted pages, pay as you go, invoiced every 30 days or when usage reaches $100. Prepaid credit and a spending cap are available. No free tier or sandbox. The quick start asks for a Kagi account and a payment method first. Enterprise volume prices are by quote (https://kagi.com/api/pricing, checked 2026-10-09). | | x402 | No · No x402, MPP or L402 in the OpenAPI file, the API docs or the pricing page (checked 2026-10-09). | | Licence | Proprietary service under the Kagi API Terms of Service. The MCP server is MIT and the OpenAPI file states Apache-2.0 | | Packages | pypi: `kagimcp` | | Source | https://github.com/kagisearch/kagimcp | | Docs | https://help.kagi.com/kagi/api/overview.html | | llms.txt | not found | | Last release | 2026-08-21 | | GitHub stars | 535 (as of 2026-10-09) | | Surface graded | The v1 HTTP API at `https://kagi.com/api/v1`, read from the OpenAPI file the docs link. The hosted MCP server and the open-source `kagimcp` package wrap the same two operations | | Index | Kagi says results come from its own web index (Teclis) and news index (TinyGem), calls to other search providers, and sources such as Wolfram Alpha and Wikipedia. No index size is published | | Result types | `workflow` is one of search, images, videos, news or podcasts. Responses group results under keys such as `search`, `image`, `video`, `news`, `podcast`, `adjacent_question`, `direct_answer` and `infobox` | | Results per query | `limit` 1 to 1,024 and `page` 1 to 10. Without `limit` the API returns everything gathered in one pass | | Full text or snippets | Snippets by default. `extract.count` (1 to 10) replaces the snippet of the top results with page Markdown. `POST /extract` takes 1 to 10 HTTPS URLs | | Filters | Lens by ID or inline (sites and keywords included or excluded, file type, dates, region), `filters` for region and dates, `safe_search` (on by default), and up to 1,000 domain rules and 1,000 regex rewrite rules | | Response format | JSON, or Markdown through `format`, which the reference marks experimental | | Answer endpoint | None in v1. FastGPT and the Universal Summarizer are separate APIs, and the docs say the summariser is not yet available in v1 | | Credentials | API keys created in the portal, each with a name, allowed products, an optional IP allow-list and a delete button. The portal shows use count and last-used time per key | | Rate limits | Not published. The terms say limits and quotas apply per plan. 429 covers rate limiting and an exhausted usage limit. Custom rate limits are an enterprise item | | Errors | An envelope with `meta.trace` and an `error` array of `code`, `url`, `message` and `location`. The reference says the error documentation URLs currently return 404 | | Clients | Generated Python, TypeScript, Go and Rust clients on GitHub, last synced 26 May 2026. Python installs from git. `@kagi/api` was not on npm on 9 October 2026 | | Data retention | Queries are not stored against the account. Load balancer and VM logs are kept 7 days and sampled Sentry errors 90 days. A Data Processing Addendum is not yet published | | Contracting entity | Kagi Inc., a Delaware public benefit corporation, per the docs and privacy page. The API terms are under Delaware law and do not name the entity | | Capabilities | web.search, web.fetch, web.extract, search.news, search.images | | Tags | official, hosted, api-key, closed-source, usage-based, openapi, preview, mcp, ip-allowlist, python, typescript, go, rust | | JSON | https://www.anchorterminal.com/api/v1/tools/kagi-search.json | ## Score breakdown (methodology v0.4, October 2026 research run) Assessed 2026-10-09 from public evidence against the published checklist (https://www.anchorterminal.com/benchmark/#checklist). Confidence: medium. Performance and Task success pending (no score, not in the total); the total is Σ(score × weight) ÷ 80 over the 7 assessed categories. "This run" is each category's share of the 100 points. | Category | Weight | This run | Score (0–100) | Points | | --- | --- | --- | --- | --- | | Reliability | 16% | 20 | 8 | 1.6 | | Performance | 10% | pending | pending | n/a | | Schema & documentation | 13% | 16.2 | 71 | 11.5 | | Agent ergonomics | 13% | 16.2 | 75 | 12.2 | | Security & auth | 14% | 17.5 | 64 | 11.2 | | Payments & pricing | 10% | 12.5 | 20 | 2.5 | | Task success | 10% | pending | pending | n/a | | Maintenance & community | 7% | 8.8 | 41 | 3.6 | | Transparency & trust (editorial 54, provenance 83) | 7% | 8.8 | 69 | 6.0 | | Negative events | up to −15 | up to −15 | none recorded | 0 | | **Total** | | | | **48.7 → D** | ### Why each score - Reliability 8: No status page is linked from the API docs, the pricing page, the API terms or the changelog, and we did not type an address for one (0). With no readable incident history the record takes the floor (5). No rate limit numbers are published. The terms say only that limits and quotas apply per plan (0). The OpenAPI file documents 429 as 'Rate limited or usage limit exhausted' with no `Retry-After` header or backoff guidance. The calls are read-only, and Kagi's own MCP server retries 429 and 5xx twice by default (3). The pricing page lists SLAs under Enterprise by quote, and the API terms say there is no uptime or service-level commitment unless agreed in writing (0). The API has been a public preview since 21 May 2026 (0). 8. - Performance: Pending. Latency is measured per call by our probes, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until the first probe window closes. - Schema & documentation 71: Public OpenAPI 3.0 file at kagi.com/api/docs/_spec/openapi.yaml, linked from the docs (25). No llms.txt on kagi.com or help.kagi.com, both 404. The docs' Markdown source is in a public GitHub repository, which is not the same as serving it to agents (0). Parameter descriptions say what each does and which option wins when lens, filters and query operators overlap, and the MCP tool says when to pick each workflow (14). Enums for `workflow`, `format`, `time_relative` and rule kinds, ranges on `page`, `limit`, `timeout` and `extract.count`, and one required field. Result `props` and `meta` are open objects (13). Three request examples with full responses and one 401 example. The error envelope is typed, but there is no list of error codes, and the file says its error documentation URLs return 404 for now (9). The path carries `/v1` and v0 is documented as legacy. The changelog is product-wide, with API items on 21 May, 16 June and 21 August 2026 (10). 71. - Agent ergonomics 75: `limit` caps results, extraction of page text is opt-in, snippet length follows an account setting, and an experimental Markdown response format exists. The MCP server has two tools (22). `page` 1 to 10, `limit` 1 to 1,024, lens and `filters` for domains, keywords, file type, dates and region (20). Errors return a namespaced `code`, a message, the field `location` and a trace ID, but no code catalogue is published and the linked error pages are not live (12). Both operations are read-only, so a retry is safe, though the docs do not say so and failed-call billing is stated only for extraction. The MCP tools set no read-only annotations (10). Only `query` is required and defaults are stated. Generated clients exist for Python, TypeScript, Go and Rust, installable from GitHub. `@kagi/api` returned 404 on npm (11). 75. - Security & auth 64: Several named keys an account, each limited to chosen products and optionally to IP addresses or ranges, revoked by deleting. The v1 key travels only in the `Authorization` header. No expiry or OAuth (27). The API only reads. Per-key product limits and a spending cap in USD narrow what a leaked key can do (16). Search and Extract return third-party page text, and we found no prompt-injection guidance in the reference, the docs or the MCP README (2). The portal shows use count and last-used time per key and requests and cost per day per API, and every response carries a trace ID. No per-call log (7). security.txt with a contact, a bug bounty with a safe harbour policy, and an independent audit by Illumant cited on the security page, whose date we did not read. No SOC 2 or ISO 27001 statement found (12). 64. - Payments & pricing 20: No x402, MPP or L402 (0). $12 per 1,000 searches and $4 per 1,000 extracted pages, published without a login (20). No free tier or trial for the API. The quick start asks for a payment method, and the $5 credit of 21 May 2026 was a one-off for subscribers (0). A person signs up in a browser and creates the key in the portal (0). 20. - Task success: Pending. Task success needs the category task suites run through each tool, which haven't run yet, so this run doesn't score it. Its weight is shared across the assessed categories until then. A data provider's data-quality score is published on its listing now and becomes half of this category when it's scored. - Maintenance & community 41: The last dated API change is the Extract API fix in the changelog of 21 August 2026, 49 days before the check (20). That is the only dated API entry in the last 90 days. The MCP server's last commit is 7 July 2026 (0). A public changelog that credits user reports, developers@kagi.com, a Discord `#api` forum and GitHub discussions. We could not read the issue list, since the GitHub API answered 403 (9). Four generated clients last synced on 26 May 2026, Python tagged only as 1.0.0rc3, TypeScript not on npm, and `kagimcp` at 1.0.2 untagged. We did not look the server up in the MCP registry (8). The Python client has a generated CI workflow and the MCP server has a lock file but no CI workflow (4). 41. - Transparency & trust 69: Closed service with clear API terms dated 22 September 2026. The MCP server is MIT and the OpenAPI file states Apache-2.0 (18). The privacy policy's API section agrees with the API terms. Queries are not stored against the account, load balancer and VM logs are kept 7 days and sampled Sentry errors 90 days. The Data Processing Addendum both documents cite is not yet published (23). v0 is marked deprecated with no end date, and the terms promise reasonable notice of breaking changes only where practicable (5). The privacy page names the payment processors and Sentry, the FAQ names GCP as the hosting provider and the docs name search sources, but there is no subprocessor list and no data locations (8). 54. Fix list for a coding agent, everything this grade says the listing lacks, the biggest gain first (19 items): https://www.anchorterminal.com/fixes/kagi-search.md (JSON https://www.anchorterminal.com/fixes/kagi-search.json) ### What we couldn't check - The lead gave `Authorization: Bot` and a GET request, as the help page example still shows. The OpenAPI file defines `POST /search` with a Bearer key. Whether v1 accepts both was not tested, since we send nothing to the API - unchecked: whether Kagi has a status page. None is linked from the pages we read, so it is scored as absent. A linked status page with a clean record would raise Reliability by up to 45 - unchecked: the rendered API reference at kagi.com/api/docs, which is script-drawn. The OpenAPI file it is built from was read instead - unchecked: issues and discussions on kagisearch/kagi-docs and kagisearch/kagimcp. The GitHub API answered 403 to the issue list and we did not retry - unchecked: the MCP registry, PyPI download counts for `kagimcp`, and the tools the hosted server at mcp.kagi.com lists. The tool definitions were read from the source - unchecked: the date and scope of the Illumant security audit, which is on blog.kagi.com and was not read - The API terms forbid probing, scanning or testing Kagi's systems and reaching the API other than through the documented interface. This matters before any probe is run - The Data Processing Addendum cited by the API terms and the privacy policy is not yet published - The TypeScript client's README says `npm install @kagi/api@1.0.0`, and the registry returned 404 for that package on 9 October 2026 ### Sources - OpenAPI description (read as the file, not the rendered reference at kagi.com/api/docs, which is script-drawn): (seen 2026-10-09) - API pricing: (seen 2026-10-09) - Kagi API Terms of Service: (seen 2026-10-09) - privacy policy and general terms: (seen 2026-10-09) - changelog: (seen 2026-10-09) - security.txt: (seen 2026-10-09) - Search API help page: (seen 2026-10-09) - API portal, quick start, legacy API, security, bug bounty, company and search sources pages, read from the docs repository: (seen 2026-10-09) - MCP server source, README and branches: (seen 2026-10-09) - Python client source, tags and CI workflow: (seen 2026-10-09) - TypeScript client README and package.json: (seen 2026-10-09) - npm registry lookup for @kagi/api (404): (seen 2026-10-09) - RDAP record for kagi.com: (seen 2026-10-09) ## Who's behind it (provenance 83/100, checked 2026-10-09) | Check | Finding | Points | | --- | --- | --- | | Legal entity named | Kagi Inc. | 20/20 | | Domain age | kagi.com, registered 1993-11-18 (32 years) | 15/15 | | Endpoint on the vendor's domain | kagi.com | 15/15 | | Terms of service | read, states 7 of the 7 things a reader expects, and has 2 clauses that cost points | 6/10 | | Privacy policy | read, states 4 of the 8 things a reader expects | 7/10 | | Status page | not found | 0/10 | | Changelog | published | 10/10 | | security.txt | valid | 10/10 | kagi.com was registered in 1993, long before Kagi Inc. was founded in 2018. The Kagi API Terms of Service (effective and last updated 22 September 2026) govern the Search API and incorporate the privacy policy and a Data Processing Addendum that is not yet published. The privacy policy at kagi.com/privacy has a Kagi API section added on 22 September 2026. The same page also holds the general Terms of Service. The API terms do not name a legal entity. The docs' company page gives Kagi Inc., and the privacy page describes Kagi as a Delaware public benefit corporation. kagi.com/.well-known/security.txt gives security@kagi.com and a bug bounty with a safe harbour policy, and has no Expires field. It is recorded as valid, although RFC 9116 asks for that field. No status page is linked from the API docs, the pricing page, the API terms, the privacy page or the changelog. We did not type an address for one. The changelog covers every Kagi product. API entries are a few lines inside those posts. RDAP for kagi.com gives a registration date of 1993-11-18. kagi.com/robots.txt allows every path for every agent and carries no Content-Signal line. help.kagi.com/robots.txt answered 404. ### Terms and privacy, as read A reading by a fixed set of rules, each answered with the vendor's own sentence. Not legal advice. **Terms of service** (https://kagi.com/privacy/api), read 2026-10-09, dated 2026-09-22, states 7 of the 7 things a reader expects. - To know. Restricts automated access (costs points). "You may not create a persistent copy of, or a derivative index from, the Kagi search index or other Results, and you may not bulk download, scrape, or archive Results." - To know. Restricts benchmarking or competitive use (costs points). "Use Results to train or fine-tune a search index, ranking system, translation or summarization model, or other service that competes with Kagi, or systematically harvest Results to assemble a training or evaluation dataset." - Gives the date it was last updated. Last updated 2026-09-22. - Names the governing law or courts. The law of the State of Delaware. - States a limit on its liability. Capped at the greater of US $500 and the fees paid in the 12 months before the claim. - Says how changes to the terms are announced. Says it gives notice of a change. - Also in the text (2026-10-08). Storing, caching or building a database of Results is banned beyond the transient caching needed to run the customer's application. "Store, cache, or build a database of Results beyond the transient caching needed to operate your application." - Also in the text (2026-10-08). Customers must not send sensitive personal data through the API, including health, payment, government ID, biometric, children's and precise location data. "Don't send us data you have no right to send, and don't send sensitive personal data (health, payment, government ID, biometrics, children's data, precise location)." - Also in the text (2026-10-08). On termination the customer must stop using the API and delete any cached Results, except limited records the law requires it to keep. "On termination, your license ends and you must stop using the API and delete any cached Results (except limited records you are legally required to keep)." **Privacy policy** (https://kagi.com/privacy), read 2026-10-09, gives no date, states 4 of the 8 things a reader expects. - Not found in the text. Gives the date it was last updated. - Not found in the text. Says what personal data is collected. - Says how long data is kept. Names a period of 30 days. - Not found in the text. Says whether personal data is sold or shared for advertising. - Not found in the text. Gives a privacy contact. - Says where data is transferred or stored. Relies on standard contractual clauses. - Also in the text (2026-10-08). The general Terms of Service on this page cap Kagi's collective liability at 500 US dollars. "THE COLLECTIVE LIABILITY OF KAGI AND THE INDEMNIFIED PARTIES UNDER THIS AGREEMENT WILL NOT EXCEED $500 (FIVE HUNDRED DOLLARS)." - Also in the text (2026-10-08). Frontend products such as Universal Summarizer may be used only for non-commercial purposes, while API products are licensed for commercial use. "Frontend products, such as (but not limited to) Universal Summarizer (found here) may only be used for non commercial purposes." - Also in the text (2026-10-08). Kagi says the third-party AI model providers it uses do not save data or use it for training whenever possible. "When using third party AI model providers, we are using privacy-respecting services that do not save the data or use it for training, whenever possible." ## Live (updated 2026-10-10 01:37 UTC) - Right now: up, HTTP 404, 144 ms, checked 2026-10-10 01:37 UTC (get on `https://kagi.com/api/v1/search`) - Uptime 24h 100.0% (102 probes) · 30 days 100.0% (102 probes) · p50 148 ms · p95 399 ms - pypi `kagimcp` 1.0.2, released 2026-07-07 - Watching changelog - Watching pricing - Watching privacy - Watching terms - Always current: https://www.anchorterminal.com/api/v1/live/kagi-search.json ## Probe metrics Not measured yet. Our benchmark probes haven't run, so there's no availability, latency or error rate from a run and Performance is pending. Live uptime, where we poll the endpoint, is under Live and doesn't change the score. ## Prices | Item | Price | Unit | Note | | --- | --- | --- | --- | | Search | $12 | per 1,000 requests | page extraction inside a search is billed at the Extract rate on top | | Extract | $4 | per 1,000 pages | up to 10 URLs a request | Across all listings: https://www.anchorterminal.com/prices/index.md ## Strengths - Public OpenAPI 3.0 file for `POST /search` and `POST /extract`, with enums, ranges and request and response examples - Each API key can be limited to chosen products and to IP addresses or ranges, and the billing page sets a spending cap in USD - Per-unit prices are public, $12 per 1,000 searches and $4 per 1,000 extracted pages, with pay-as-you-go billing - Searches can carry an inline lens, domain block, lower, raise and pin rules, date and region filters, and extraction of up to 10 result pages - The privacy policy has an API section with retention periods, and says queries are not stored against the account ## Weaknesses - Public preview since 21 May 2026. The API terms say it is under active development with no uptime or service-level commitment - No rate limit numbers are published, and no status page is linked from the docs, pricing, terms or changelog pages we read - No free allowance. The quick start asks for a Kagi account and a payment method before the first call - The API terms forbid storing or caching results beyond transient caching, building datasets from them, and probing or testing Kagi's systems - The help page example uses `GET` with `Authorization: Bot`, while the OpenAPI file defines `POST` with a Bearer key. The TypeScript client's README names an npm package that returned 404 ## Before you call it (notes for agents) 1. Send `POST https://kagi.com/api/v1/search` with a JSON body and `Authorization: Bearer `, as the OpenAPI file defines. Only `query` is required 2. Set `limit` to cap results returned. In the mixed `search` workflow the MCP tool applies the cap to each result category separately 3. Use `extract.count` (1 to 10) only when page text is needed. Extraction is billed at the Extract rate on top of the search 4. Do not store results. The API terms allow only the transient caching an application needs, and require deletion on termination 5. On 429 back off before retrying. The response covers both rate limiting and an exhausted usage limit, and no `Retry-After` header is documented ## Connect Install: ```bash uvx kagimcp ``` First request: ```bash curl -X POST https://kagi.com/api/v1/search \ -H "Authorization: Bearer $KAGI_API_KEY" -H "Content-Type: application/json" \ -d '{"query":"steve jobs","workflow":"search"}' ``` Claude Code: ```bash claude mcp add kagi https://mcp.kagi.com/mcp --transport http --header "Authorization: Bearer $(read -sp 'API key: ' k; echo $k)" --scope user ``` MCP client configuration: ```json { "mcpServers": { "kagi": { "args": [ "kagimcp" ], "command": "uvx", "env": { "KAGI_API_KEY": "YOUR_API_KEY_HERE" } } } } ``` Through letme (picks today, calling later): https://letme.dev/kagi-search. letme answers with the pick and how to call it direct; calling through letme (one key, the vendor's own price) comes later. How it works: https://www.anchorterminal.com/letme/index.md ## Similar tools Ranked by shared capabilities, then score. Same-category tools with no shared capability key are listed last. | Tool | Grade | Score | Rank | Shared capabilities | x402 | Markdown | | --- | --- | --- | --- | --- | --- | --- | | Tavily API + MCP | BB | 76.8 | 26 | web.search, web.extract, web.fetch, search.news, search.images | no | https://www.anchorterminal.com/tools/tavily-mcp.md | | SerpKite | B | 64.8 | 337 | web.search, search.news, search.images, web.fetch, web.extract | no | https://www.anchorterminal.com/tools/serpkite.md | | You.com APIs | BB | 76.5 | 31 | web.search, web.fetch, web.extract, search.news | no | https://www.anchorterminal.com/tools/you-com-api.md | | Linkup | B | 68.9 | 201 | web.search, web.fetch, web.extract, search.images | yes | https://www.anchorterminal.com/tools/linkup.md | | Brave Search API + MCP | B | 68 | 231 | web.search, web.extract, search.news, search.images | no | https://www.anchorterminal.com/tools/brave-search-mcp.md | | Exa API + MCP | B | 66 | 302 | web.search, web.fetch, web.extract, search.news | yes | https://www.anchorterminal.com/tools/exa-mcp.md | ## Panel reviews (0) Reviewed by the Anchor panel (https://www.anchorterminal.com/reviewers/index.md): . Desk reviews, written from public documentation, pricing, terms, source and status history on 1 October 2026. No calls made. For a desk review, the outcome says whether the reviewer's questions could be answered from public material: success, partial or failure. How reviews work: https://www.anchorterminal.com/reviews/how-it-works.md ## Notable - The v1 API has two operations, `POST /search` and `POST /extract`, on `https://kagi.com/api/v1`, with HTTP Bearer authentication (source: ) - The Search API opened as a public preview on 21 May 2026, after an invited preview announced on 30 April 2026 (source: ) - Search costs $12 per 1,000 requests and Extract $4 per 1,000 pages. Kagi invoices every 30 days or when usage reaches $100 (source: ) - The API Terms of Service, effective 22 September 2026, forbid storing results beyond transient caching, building datasets, reselling raw results and probing or testing Kagi's systems (source: ) - Requests can inherit the account's settings, including blocked and promoted sites, when the key has `Inherit account settings in API requests` ticked (source: ) - A hosted MCP server at `https://mcp.kagi.com/mcp` takes the API key as a Bearer header. OAuth is not supported yet. The open-source server has two tools, `kagi_search_fetch` and `kagi_extract` (source: ) - The legacy v0 Search API (`GET /api/v0/search`, `Authorization: Bot`, $25 per 1,000 queries) is marked deprecated with no end date given (source: ) - #15 of 16 in Best web search APIs for AI agents: https://www.anchorterminal.com/best/search/index.md - All 129 search comparisons: https://www.anchorterminal.com/compare/search/index.md ## Compare - [Brave Search API + MCP vs Kagi Search API](https://www.anchorterminal.com/compare/brave-search-mcp-vs-kagi-search.md): B 68 vs D 48.7 - [Cloudflare Web Search API vs Kagi Search API](https://www.anchorterminal.com/compare/cloudflare-web-search-vs-kagi-search.md): C 61.9 vs D 48.7 - [Exa API + MCP vs Kagi Search API](https://www.anchorterminal.com/compare/exa-mcp-vs-kagi-search.md): B 66 vs D 48.7 - [Firecrawl MCP vs Kagi Search API](https://www.anchorterminal.com/compare/firecrawl-mcp-vs-kagi-search.md): BB 75.3 vs D 48.7 - [Grep AI vs Kagi Search API](https://www.anchorterminal.com/compare/grep-ai-vs-kagi-search.md): B 64.4 vs D 48.7 - [Kagi Search API vs Linkup](https://www.anchorterminal.com/compare/kagi-search-vs-linkup.md): D 48.7 vs B 68.9 - [Kagi Search API vs Parallel Search and Task APIs](https://www.anchorterminal.com/compare/kagi-search-vs-parallel-search-api.md): D 48.7 vs BB 74 - [Kagi Search API vs SearchAPI.io](https://www.anchorterminal.com/compare/kagi-search-vs-searchapi-io.md): D 48.7 vs D 51.2 - [Kagi Search API vs SerpApi](https://www.anchorterminal.com/compare/kagi-search-vs-serpapi.md): D 48.7 vs B 62.5 - [Kagi Search API vs Serper](https://www.anchorterminal.com/compare/kagi-search-vs-serper.md): D 48.7 vs F 24.1 - [Kagi Search API vs SerpKite](https://www.anchorterminal.com/compare/kagi-search-vs-serpkite.md): D 48.7 vs B 64.8 - [Kagi Search API vs Tavily API + MCP](https://www.anchorterminal.com/compare/kagi-search-vs-tavily-mcp.md): D 48.7 vs BB 76.8 - [Kagi Search API vs TinyFish Search](https://www.anchorterminal.com/compare/kagi-search-vs-tinyfish-search.md): D 48.7 vs B 63.2 - [Kagi Search API vs Valyu](https://www.anchorterminal.com/compare/kagi-search-vs-valyu.md): D 48.7 vs B 64.6 - [Kagi Search API vs You.com APIs](https://www.anchorterminal.com/compare/kagi-search-vs-you-com-api.md): D 48.7 vs BB 76.5 - [Fetch (MCP reference server) vs Kagi Search API](https://www.anchorterminal.com/compare/fetch-reference-server-vs-kagi-search.md): C 57.5 vs D 48.7 ## Verify this listing For the vendor. The badge or a plain link to this page verifies the listing, from a page on kagi.com or one of its subdomains, or the README of github.com/kagisearch/kagimcp. It shows the listing is the vendor's and that the vendor knows it's here, and it never changes a grade, rank or review. The vendor sends the page's address to `POST https://www.anchorterminal.com/api/v1/verify` as `{"slug": "kagi-search", "url": "…"}`, or calls the `verify_listing` tool at https://www.anchorterminal.com/mcp. We fetch the page once, then again every week; two failed checks in a row and the verification lapses, and a later pass restores it. What we check: https://www.anchorterminal.com/builders/index.md#verify HTML badge: ```html Kagi Search API on Anchor Terminal ``` Markdown badge, for a README: ```markdown [![Kagi Search API on Anchor Terminal](https://www.anchorterminal.com/badges/kagi-search.svg)](https://www.anchorterminal.com/tools/kagi-search) ``` Plain link: ```html Kagi Search API on Anchor Terminal ``` ## Share this listing For the vendor. Sharing assets for social media, two PNGs of 1200 × 630 that say Kagi Search API is listed on Anchor Terminal, with the vendor's logo and this page's address and no grade or score. - Dark: https://www.anchorterminal.com/assets/share/kagi-search-dark.png - Light: https://www.anchorterminal.com/assets/share/kagi-search-light.png