FAQ

13 frequently asked questions about integration, billing, rate limits and result usage. Can't find your answer? Submit feedback from the console.

What is SearchPipe?

SearchPipe is an AI search API and remote MCP server for AI agents: a single call runs multi-engine retrieval, full-text fetching, LLM reranking and optional summarization, returning structured results with relevance scores that agents can consume directly.

How is SearchPipe different from calling a search engine directly?

SearchPipe returns cleaned page content, relevance scores and optional answers — not raw search-result HTML that you have to parse. Agents can consume the response directly, and failed requests are automatically refunded.

Which AI clients are supported?

Any MCP-compatible client with streamable-http support can connect — Claude Code and Cursor are tested. Self-built agents can call the REST API directly via POST /search.

Can SearchPipe search the Chinese web?

Yes. SearchPipe aggregates multiple search engines and can retrieve and clean Chinese-language pages, making it a practical choice when your agents need coverage of both English and Chinese web content.

How does pricing work?

Credits: $0.005 = 1 credit (limited-time 50% OFF; standard rate $0.01). A basic search costs 1 credit and an advanced search costs 2 credits. New accounts get 1,000 free credits per month. Recharged credits never expire; subscription credits are valid for 30 days.

How long does integration take?

Copy the MCP link from the dashboard into your client config — typically 1–3 minutes. Agents can also read /agent-setup/SKILL.md to configure themselves automatically.

Is the API key embedded in the MCP URL safe?

The key lives in the client config file, so treat that file like a credential. Create a separate key for each agent client, and revoke it immediately in the dashboard if it leaks — a revoked key stops working at once.

Why is a search sometimes slow?

A cold query runs the full pipeline — multi-engine retrieval, full-text fetching, LLM reranking — which usually takes a few seconds. Identical queries with identical parameters hit the cache (default TTL 300 seconds) and return in milliseconds.

How many results does one request return?

Five by default; adjust with max_results (1–20). Results carry 0–1 relevance scores and are sorted from most to least relevant.

How is the answer summary generated?

With include_answer enabled, the service generates a summary with citation markers based on the fetched page content, flagged with ai_generated=true.

Do failed searches cost credits?

No. When upstream retrieval fails (502) or output moderation rejects the content (400), the charge is automatically refunded (idempotently). Only successful requests are billed.

Is there a rate limit?

Yes: a sliding-window limiter (default 100 requests per minute, burst 20). Over-limit requests get a 429 with a Retry-After header. Contact us to raise the quota for high-volume use.

Do credits expire?

Credits from recharges never expire. Credits from monthly subscriptions (including renewals and upgrades) are valid for 30 days from the moment they land and expire automatically if unused.

Further reading

Still have questions?

Sign in to submit a support ticket from the console, or let your agent read the setup guide and configure itself.

Start for free Read the docs