# Liner Search MCP vs Parallel Search and Task APIs (slim)

> Parallel Search and Task scores 75 (BB) to Liner Search MCP's 43.4 (E) for research search. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/liner-mcp-vs-parallel-search-api.md (~5,250 tokens) · this version ~2,830 tokens · JSON https://www.anchorterminal.com/compare/liner-mcp-vs-parallel-search-api.json · canonical https://www.anchorterminal.com/compare/liner-mcp-vs-parallel-search-api
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-07
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Parallel Search and Task APIs scores 75 (BB) on agent readiness against Liner Search MCP's 43.4 (E), and leads in every scored category. Both do research search.

- Liner Search MCP: E 43.4, rank #1252 of 1510 · https://www.anchorterminal.com/tools/liner-mcp.min.md
- Parallel Search and Task APIs: BB 75, rank #73 of 1510 · https://www.anchorterminal.com/tools/parallel-search-api.min.md
- Liner Search MCP, good for Agents that need cheap cited search across the web and scholarly sources, with optional deep research reports.
- Parallel Search and Task APIs, good for Agents that mix quick search with long research or enrichment jobs and want one vendor and one bill. Ahead on Reliability, 75 against 50; Schema & documentation, 94 against 45; Agent ergonomics, 87 against 65; Security & auth, 45 against 35; Payments & pricing, 75 against 20; Maintenance & community, 87 against 45; Transparency & trust, 65 against 34. Also Agent-ready, a grade of BB or better.

| Category | Liner Search MCP | Parallel Search and Task APIs |
| --- | --- | --- |
| Reliability (16%) | 50 | 75 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 45 | 94 |
| Agent ergonomics (13%) | 65 | 87 |
| Security & auth (14%) | 35 | 45 |
| Payments & pricing (10%) | 20 | 75 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 45 | 87 |
| Transparency & trust (7%) | 34 | 65 |

| Fact (where they differ) | Liner Search MCP | Parallel Search and Task APIs |
| --- | --- | --- |
| Kind | MCP server | HTTP API |
| Vendor | Liner | Parallel Web Systems |
| Hosted endpoint | `https://platform.liner.com/api/v1/mcp` | `https://api.parallel.ai/v1/search` |
| Transports | Streamable HTTP | HTTP, Streamable HTTP |
| Auth | OAuth | OAuth or key |
| Pricing | Paid | Freemium |
| x402 | no | payer tooling only |
| Tools exposed | 9 | 6 |
| Read-only variant documented | no | yes |
| MCP registry | `com.liner/search` | `ai.parallel/search-mcp` |
| Last release | none | 2026-10-28 |
| Terms last updated | no document linked | 2026-10-17 |
| Privacy policy last updated | no document linked | 2026-08-11 |
| Customer content may train models | not read yet | yes |
| Terms restrict automated access | not read yet | not found in the text |
| Terms restrict benchmarking | not read yet | not found in the text |
| Terms or service can change without notice | not read yet | not found in the text |
| Arbitration or class-action waiver | not read yet | not found in the text |
| Popularity | none | 28 stars, 250k npm/wk, 994k PyPI/wk |
| Agent reviews | none | 3.6/5 (8) |

Why the edge:
- Payments & pricing, Parallel Search and Task APIs +55: 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.); Parallel Search and Task APIs 75 (Parallel runs a separate gateway at parallelmpp.dev that takes x402 (USDC on Base) and MPP (Stripe or Tempo) for search and extract at $0.01 and an ultra task at $0.30. Our unpaid POST to /api/search on 6 October returned 402 with an x402 v2 challenge for 10000 base units on eip155:8453 and a Tempo MPP challenge. Nothing on api.parallel.ai, and the gateway sells one price per endpoint with no mode choice, so partial (25). Per-unit prices published without login (20). Up to 5,000 free requests a month, $5 monthly credit and up to $80 at signup on the pricing page, which still doesn't say whether a card is needed (10). The hosted Search MCP works with no key, and the gateway needs only a wallet (20).)
- Schema & documentation, Parallel Search and Task APIs +49: 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.); Parallel Search and Task APIs 94 (Public OpenAPI at docs.parallel.ai/public-openapi.json, linked from llms.txt (25). llms.txt and Markdown pages (10). A live `tools/list` on search.parallel.ai/mcp on 17 October and again on 1 November returned the two definitions, and the newer Parallel MCP server at mcp.parallel.ai adds `web_decisions`, whose description says when to use web_search instead. `web_search` states its purpose and ideal uses, and `web_fetch` says to use it "only when web_search excerpts are insufficient". The docs add that domain filters are hard filters that can cut quality. `web_search` has no when-not-to line of its own (17). Typed JSON Schema inputs with required fields and an output schema on both tools, `mode` is an enum in the API, and Task output schemas are JSON Schema. The MCP inputs carry no enums (12). The errors page lists each code with whether to retry and what to do, and 422s carry a structured `detail` (15). A dated changelog, newest entry 26 October 2026 (Decisions API) after 19 October (EU data residency), and beta headers retire on dated entries (15).)
- Maintenance & community, Parallel Search and Task APIs +42: 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.); Parallel Search and Task APIs 87 (parallel-web 1.3.7 for Python on 2026-10-23 and for TypeScript on 2026-10-28, and changelog entries on 19 and 26 October, the second launching the Decisions API (30). Counted from the tags and the changelog, the 90 days from 3 August hold Python SDK releases 1.3.1 to 1.3.7, TypeScript 1.3.1 to 1.3.7 and ten changelog entries from 19 August to 26 October (20). The SDK releases since 1.3.5 are dependency bumps. Closed service with a changelog and support@parallel.ai. We didn't test whether support answers (12). Current Python and TypeScript SDKs, and ai.parallel/search-mcp and ai.parallel/task-mcp in the official registry (15). The Python SDK runs lint and build in CI on push, plus a workflow that detects breaking changes (10).)
- Transparency & trust, Parallel Search and Task APIs +31: 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.); Parallel Search and Task APIs 65 (The API is closed with published terms, and the SDKs are MIT (20). Privacy policy effective 11 August 2026 and Customer Terms effective 17 October 2026, both re-read on 1 November. EU-endpoint search requests keep no request or response content, but the default endpoint gets only "as long as necessary". The Customer Terms still let Parallel use Customer IP (inputs and outputs) to train and improve its models, not linked to an individual, and ask for a separate DPA before personal data is processed. No retention period is stated, and the DPA wasn't found as a public page (12). No deprecation notices or policy found in the changelog, which points older integrations from /v1beta to /v1 without an end date, and the docs now call the standalone Search and Task MCP servers legacy while saying both keep running, also without a date (5). EU data residency for basic-mode Search and Extract is documented, on enterprise agreements since 19 October. Subprocessors sit behind the trust centre and the privacy policy says to ask your Parallel contact (8).)
- Reliability, Parallel Search and Task APIs +25: 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.); Parallel Search and Task APIs 75 (incident.io page at status.parallel.ai with Search, Task, Chat, Monitor, FindAll and Entity Search components and history (20). The feed, re-read on 1 November, has nothing after 13 October, so the 90 days from 3 August hold the same four incidents, all partial or degraded. Elevated 503s on 6 August, about an hour of Task API latency on 2 September, intermittent 4xx errors on 7 September, and transient 502s from the network gateway on 13 October, degraded performance from 01:23 to 01:43 UTC. Most have no duration listed (20). Published limits, 600 a minute for Search, Image Search, Extract, Decisions and Entity Search, 2,000 for Tasks, 300 for Chat and Monitor (15). The errors page marks 429 as retryable with exponential backoff, but there's no `Retry-After` and no idempotency guidance for creating Task runs, which the SDKs retry twice by default (10). No SLA found (0). Search, Extract and Task are GA (10).)
- Agent ergonomics, Parallel Search and Task APIs +22: Liner Search MCP 65 (Nine tools (25). No paging or size controls documented (5 of 20). 429 codes documented for the API (8 of 20). All tools read; annotations not read (12 of 20). One URL with OAuth, few required inputs and an OpenAI-compatible API (15). 25 + 5 + 8 + 12 + 15 = 65.); Parallel Search and Task APIs 87 (The Search MCP has two tools, about 5,700 characters of names, descriptions and input schemas on 1 November, and the Parallel MCP server lists three without a key (about 9,700 characters) and a fourth, `web_research`, after sign-in. `web_fetch` returns excerpts unless `full_content` is set, and the docs cap excerpts at roughly 25,000 characters a call and warn full pages can run to tens of thousands of tokens (25). Result counts, excerpt settings and source policies for domains and paths (18). The errors table gives each code a retry column and a resolution, with troubleshooting for 402 and 429 and a structured `detail` on 422 (20). Both Search MCP tools carry readOnlyHint true, destructiveHint false and idempotentHint true in the live `tools/list`, and searches are safe to repeat. There's still no idempotency key for Task creation, the SDKs retry creates on 429 and 5xx, and the Task MCP needs a key, so its annotations weren't read (14). Python and TypeScript SDKs, but `mode` defaults to advanced, the $5 per 1,000 tier, when you leave it out (10).)