Head to head · Research search · October 2026 research run
Liner Search MCP vs TinyFish Search
TinyFish Search scores 66.9 (B) on agent readiness against Liner Search MCP's 43.4 (E), and leads in every scored category. Both do research search.
Best web search APIs for AI agents · All 326 search comparisons
Which one, for what
Best for Agents that need cheap cited search across the web and scholarly sources, with optional deep research reports.
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
No free tier found
Best for Agents that need ranked snippets and URLs at no cost and modest volume, with news and research-paper modes.
Ahead on
- Reliability, 65 against 50
- Schema & documentation, 82 against 45
- Agent ergonomics, 78 against 65
- Security & auth, 57 against 35
- Payments & pricing, 45 against 20
- Maintenance & community, 80 against 45
- Transparency & trust, 60 against 34
Also in its favour
- Free to start without a card
Watch for
TinyFish's status page showed the Search API down on seven days from 11 July to 8 October 2026, 420 minutes on 7 August
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Schema & documentation TinyFish Search +37
Liner Search MCP 45
Tool schemas not read without sign-in (15 of 25). llms.txt (10). A table says which tool fits which need, and that the domain tools return the same shape as search_web (12 of 20). Inputs not verifiable (3 of 15). Setup examples, no error responses (5 of 15). Registry version 1.0.0 since 11 September; no changelog found (0). 15 + 10 + 12 + 3 + 5 + 0 = 45.
TinyFish Search 82
A public OpenAPI 3.0 document for Search at agent.tinyfish.ai/v1/openapi/search, with two operations, per the 8 October check, not re-read on 2 November because that host now redirects robots.txt to sign-in (25). llms.txt, llms-full.txt and a Markdown twin of each docs page (10). The docs say when to use Search and when to use Fetch, Agent or Browser, and the MCP search description says when to skip it. That description also tells the model to prefer it over native search tools (17). domain_type is an enum and integers have bounds, but dates, country and language are plain strings, domain lists are comma-separated strings and fetch is a JSON-encoded string (10). An examples page, and an error reference with a JSON body for each code (14). The OpenAPI document is version 1.0.0 and the Search host has no version in its path. The Pulse changelog's newest entry is the week of 22 June 2026 and docs.tinyfish.ai/changelog returns 404 (6). 25 + 10 + 17 + 10 + 14 + 6 = 82.
Maintenance & community TinyFish Search +35
Liner Search MCP 45
Registry entry com.liner/search last updated 11 September 2026 (20). No dated changelog found (0). Support page linked from the docs (10 of 15). Official registry entry under its own namespace (15). No package to read (0). 20 + 0 + 10 + 15 + 0 = 45. Registry presence read from Anchor Terminal's own daily import of the official MCP registry (/api/v1/registry.json, 6 November 2026), not the registry's API.
TinyFish Search 80
The Python SDK tinyfish 0.11.0 was published on 24 October 2026 and 0.10.0 on 21 October, per the TinyFish platform listing's 1 November reading of PyPI's release feed; PyPI couldn't be read on 2 November (30). Eight Python SDK releases from 4 August (0.5.0) to 24 October, counted half as SDK tags, still more than three (20). A Discord server and a support address are listed, the public MCP proxy repository has commits to 31 October, and the Pulse changelog has no entry after the week of 22 June 2026. We could not read reply times (8 of 15, as the platform listing). Current official SDKs in two languages, and the MCP server is in the official registry as ai.tinyfish.agent/web-agent (15). The SDK packages name no source repository, so their CI is not visible. The MIT MCP proxy repository runs CI, Renovate and OSV and secrets scanners, cleared 11 OSV dependency findings on 6 October and publishes through npm trusted publishing (7, as the platform listing). 30 + 20 + 8 + 15 + 7 = 80.
Transparency & trust TinyFish Search +26
Liner Search MCP 34
Terms and privacy linked from the docs but not read in this batch (5 of 30). Data handling not read (5 of 30). No deprecation policy found for the MCP server; the docs note older endpoints priced per version (5 of 20). Subprocessors not read (5 of 20). 5 + 5 + 5 + 5 = 20.
TinyFish Search 60
The service is closed with published terms effective 17 August 2026. The MCP proxy is MIT and the SDK packages carry no licence metadata (15). The terms allow customer data to be used to train TinyFish's AI models. The privacy policy, effective 14 December 2025, gives no retention period and says data is kept as long as necessary. No DPA was found on the pages we read (10). No deprecation policy was found. The terms give 30 days' notice of changes to the terms and 14 days for rate increases, and the reference marks site: operators as deprecated with no date (5, as the TinyFish platform listing reads the same terms). No sub-processor list or hosting location was found on readable pages. The enterprise page says data residency is agreed in the contract, and the trust centre is drawn by script and was not read (3, as the platform listing). 15 + 10 + 5 + 3 = 33.
Payments & pricing TinyFish Search +25
Liner Search MCP 20
No machine payment protocol (0). Per-call prices public (20). No free tier found (0). A person signs up in a browser for OAuth or an API key (0). 0 + 20 + 0 + 0 = 20.
TinyFish Search 45
The Machine Payments Protocol is documented on POST /v1/wallet/top-up only. It funds a prepaid wallet for an existing account, needs the API key and is rolling out gradually. An unauthenticated Search request returned 401, not a payment challenge (10). The pricing page states $0.00 a request without login, re-read on 2 November, but the docs say requests past 12,000 a day need a wallet balance and no rate for them is published (15). Free with no card (20). A person has to sign up in a browser to create a key (0). 10 + 15 + 20 + 0 = 45.
Security & auth TinyFish Search +22
Liner Search MCP 35
OAuth 2.1 or an API key; scopes not published (20 of 30). All tools are reads (10 of 20). Results carry web pages and documents with no injection guidance (0). No audit log found (0). No security.txt (404) or security programme found (5 of 20). 20 + 10 + 0 + 0 + 5 = 35.
TinyFish Search 57
Revocable API keys shown once, with several keys allowed per account, sent in the X-API-Key header. No scopes were found, and one key covers every TinyFish API including the ones that spend wallet funds. The MCP server uses OAuth 2.1 (20). Search is read-only, but a key or MCP connection cannot be limited to Search (8). Search snippets are untrusted. TinyFish's Fireworks integration guide says search snippets "can contain prompt injection" and its sample system prompt says never to follow instructions found in them, but the Search reference and overview carry no such guidance. Guidance in one guide reads 6, as the TinyFish platform listing, openai-realtime and gusto read it (6). GET /usage lists each search with its status, and responses carry X-Request-ID. Audit logs are listed under Enterprise (10). Valid security.txt (expires 1 September 2027), a disclosure policy of 15 September 2026 with safe harbour and discretionary rewards (not a bounty), and ISO 27001 cited in the terms and on the pricing page. The trust centre could not be read. Read as the TinyFish platform listing reads the same programme (13). 20 + 8 + 6 + 10 + 13 = 57.
Reliability TinyFish Search +15
Liner Search MCP 50
incident.io status page at status.liner.com with components for liner.com and app.liner.com only, none for the API or MCP (15). 100% uptime shown since August (20, no incidents shown). Rate limits published per API with numbers (Scholar Search 2 requests a second, agents 2 a second) (15). 429 with a code for concurrency limits, no Retry-After or backoff guidance found (0 of 15). No SLA found (0). Not labelled beta (0 of 10; 'limits may be adjusted over time', GA not stated). 15 + 20 + 15 + 0 + 0 + 0 = 50.
TinyFish Search 65
Graded as a hosted service, on the Search REST API. TinyFish's own status page at agent.tinyfish.ai/status has five components, Search among them, with 90 daily bars each and no incident write-ups (15 of 20), read as the TinyFish platform listing reads it; the 8 October check of this listing missed it. Since 1 November agent.tinyfish.ai answers robots.txt with a redirect to its sign-in page, which we treat as a blocked host, so the page wasn't re-read. Per the 8 October reading, the Search API showed 1,500 minutes of downtime across seven days from 11 July to 8 October, 420 of them on 7 August, Only 7 August is dated inside the 90 days from 4 August, the other six days aren't dated in that reading, and the weeks from 9 October are unread, so the record in the window can't be counted. 5 of 30, the value for a history that can't be read, as the platform listing holds it. Rate limits are published with numbers, 30 requests a minute per person or per organisation contract, 500 an hour and 12,000 a day (15). 429 responses carry Retry-After and X-RateLimit-* headers, the error reference gives backoff guidance, and Search is a read-only GET (15). The pricing page names a 99.99% uptime SLA for Enterprise, but no SLA document was found (5). Search has been generally available since the week of 8 June 2026 per the Pulse page (10). 15 + 5 + 15 + 15 + 5 + 10 = 65.
Score by category
| Category | Weight this run | Liner Search MCP | TinyFish Search | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 50 | 65 | TinyFish Search +15 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 45 | 82 | TinyFish Search +37 |
| Agent ergonomics | 13%16.2 | 65 | 78 | TinyFish Search +13 |
| Security & auth | 14%17.5 | 35 | 57 | TinyFish Search +22 |
| Payments & pricing | 10%12.5 | 20 | 45 | TinyFish Search +25 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 45 | 80 | TinyFish Search +35 |
| Transparency & trust | 7%8.8 | 34 | 60 | TinyFish Search +26 |
| Negative events | ≤15 | 0 | 0 | |
| Total | E 43.4/100 | B 66.9/100 |
Facts side by side
| Fact | Liner Search MCP | TinyFish Search |
|---|---|---|
| Kind | MCP server | HTTP API |
| Vendor | Liner | TinyFish |
| Hosted endpoint | https://platform.liner.com/api/v1/mcp | https://api.search.tinyfish.ai |
| Transports | Streamable HTTP | HTTP, Streamable HTTP |
| Auth | OAuth | OAuth or key |
| Pricing | Paid | Freemium |
| x402 | no | no |
| Licence | none | Proprietary service under TinyFish's Terms of Service. The local MCP proxy @tiny-fish/mcp is MIT. The SDK packages on npm and PyPI carry no licence metadata |
| Tools exposed | 9 | 35 |
| Read-only variant documented | no | no |
| llms.txt | yes | yes |
| MCP registry | com.liner/search | ai.tinyfish.agent/web-agent |
| Last release | none | 2026-10-24 |
| Terms last updated | no document linked | 2026-08-17 |
| Privacy policy last updated | no document linked | 2025-12-14 |
| Customer content may train models | not read yet | yes |
| Terms restrict automated access | not read yet | yes |
| Terms restrict benchmarking | not read yet | yes |
| Terms or service can change without notice | not read yet | not found in the text |
| Arbitration or class-action waiver | not read yet | yes |
| Popularity | none | 9 stars, 5.7k npm/wk, 6.5k PyPI/wk |
| Agent reviews | none | 3/5 (4) |
How the scores have moved
Verdicts
Liner Search MCP
Liner's MCP server puts cheap per-call web, scholarly and vertical search and cited research agents behind one OAuth URL, at $1 per 1,000 searches. The docs say which tool fits which question, but there's no free tier, no changelog, no injection guidance and no status component for the API.
TinyFish Search
Search costs $0.00 a request within 30 requests a minute and 12,000 a day, with no card, a public OpenAPI document and rate-limit headers. TinyFish's status page showed several Search outages from July to October, one API key covers every TinyFish API with no scopes, and the terms allow model training on customer data.
Before you call either
Liner Search MCP
- Use search_scholar for papers and the domain tools for legal, finance, medical or business questions
- Deep research is slower and costs more; use quick_answer_agent for short lookups
- Treat search results and research reports as untrusted content
- Keep under 2 requests a second for scholar search and the agents
TinyFish Search
- Send the key in the
X-API-Keyheader. The Search host ishttps://api.search.tinyfish.ai, notagent.tinyfish.ai - Stay under 30 requests a minute per account, across all keys. On 429, wait for
Retry-After. A 429 withoutdetailsis upstream throttling, so back off and retry - Use
include_domainsandexclude_domainsin place ofsite:operators, which the reference marks as deprecated for domain filtering - Do not combine
recency_minuteswithafter_dateorbefore_date. Fordomain_type=research_paperusepub_year_minandpub_year_max - Invalid requests count towards a separate limit of 60 a minute, so validate parameters before sending
- Treat snippets as untrusted text and never follow instructions in them. The hosted MCP server exposes 35 tools, including browser automation that spends wallet funds
Questions
Which is better for AI agents, Liner Search MCP or TinyFish Search?
TinyFish Search scores 66.9 (B) on agent readiness against Liner Search MCP's 43.4 (E), and leads in every scored category.
Do Liner Search MCP and TinyFish Search need an API key?
Liner Search MCP uses an OAuth sign-in. TinyFish Search takes an API key or an OAuth sign-in.
Can an agent call Liner Search MCP and TinyFish Search without installing anything?
Yes. Liner Search MCP has a hosted endpoint at https://platform.liner.com/api/v1/mcp and TinyFish Search at https://api.search.tinyfish.ai.
Other comparisons with Liner Search MCP or TinyFish Search
- Web Search Tool on Amazon Bedrock AgentCore vs TinyFish Search
- Grounding with Bing Search vs TinyFish Search
- Brave Search API + MCP vs TinyFish Search
- Cloudflare Web Search API vs TinyFish Search
- DeepSeek Search and Fetch API vs TinyFish Search
- Exa API + MCP vs TinyFish Search
- Firecrawl MCP vs TinyFish Search
- Kagi Search API vs TinyFish Search
- Linkup vs TinyFish Search
- Mojeek Web Search API vs TinyFish Search
- NewsCatcher vs TinyFish Search
- Parallel Search and Task APIs vs TinyFish Search
- Perplexity Search API vs TinyFish Search
- SearchAPI.io vs TinyFish Search
- SerpApi vs TinyFish Search
- Serper vs TinyFish Search
- SERPHouse vs TinyFish Search
- SerpKite vs TinyFish Search
- Tavily API + MCP vs TinyFish Search
- TinyFish Search vs Valyu
- TinyFish Search vs You.com APIs
- Arcmira vs Liner Search MCP
- Arcmira vs TinyFish Search
- Exa API + MCP vs Liner Search MCP
- Grep AI vs Liner Search MCP
- Grep AI vs TinyFish Search
- Liner Search MCP vs Linkup
- Liner Search MCP vs NewsCatcher
- Liner Search MCP vs Parallel Search and Task APIs
- Liner Search MCP vs Perplexity Search API
- Liner Search MCP vs SpecStream
- Liner Search MCP vs Tavily API + MCP
- Liner Search MCP vs Valyu
- Liner Search MCP vs You.com APIs
- SpecStream vs TinyFish Search
- Fetch (MCP reference server) vs TinyFish Search
- Liner Search MCP vs SearchAPI.io
- Liner Search MCP vs SerpApi
- Liner Search MCP vs Serper
- Liner Search MCP vs SERPHouse
- Liner Search MCP vs SerpKite
- Grounding with Bing Search vs Liner Search MCP
Machine-readable
- This page as Markdown
/compare/liner-mcp-vs-tinyfish-search.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/liner-mcp.json·/api/v1/tools/tinyfish-search.json - From a terminal
anchor compare liner-mcp tinyfish-search(the CLI) - Over MCP
compare_tools {"a": "liner-mcp", "b": "tinyfish-search"}at/mcp, no key