# SearchPipe

> Real-time web search for AI agents: ranked results, source URLs, and optional AI answers.

- name: tech.searchpipe/searchpipe
- version: 1.0.1
- connection class: R1 (autonomous)
- trust: 99/100
- quality: 70/100 (needs work)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/tech.searchpipe%2Fsearchpipe
- tools: https://api.protogrid.dev/v1/servers/tech.searchpipe%2Fsearchpipe/tools

**An agent can connect on its own if it already holds `SEARCHPIPE_TOKEN`.** Remote endpoint behind a static API key or header. The registry never sees the value; the agent fills the placeholder.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "searchpipe": {
      "type": "http",
      "url": "https://searchpipe.tech/mcp/",
      "headers": {
        "Authorization": "Bearer ${SEARCHPIPE_TOKEN}"
      }
    }
  }
}
```

Placeholders to fill: `${SEARCHPIPE_TOKEN}`.

## Trust

- hygiene: 100
- liveness: 97
- freshness: 100
- provenance: 100
- drivers: +repository +namespace-matches-repo +dns-namespace +website +reachable +uptime-93% +updated-20d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 70/100 (needs work)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 64 (weight 30)

- pass `tools.descriptions`: every tool has a description
- warn `tools.description_length`: 1 tools have descriptions over 1,024 characters, which crowds the context
- pass `tools.schemas`: every tool has an object input schema
- fail `tools.annotations`: no tool declares readOnlyHint or destructiveHint, so clients cannot tell safe calls from risky ones
- fail `tools.directory_hints`: no tool declares all four of readOnlyHint, destructiveHint, idempotentHint and openWorldHint; missing: searchpipe_verify (readOnlyHint, destructiveHint, idempotentHint, openWorldHint); searchpipe_search (readOnlyHint, destructiveHint, idempotentHint, openWorldHint)
- pass `tools.token_cost`: about 795 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 75 (weight 15)

- warn `stability.changes`: 6 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 2, about 795 tokens to load them all
- tool set hash: f823d3202d7e8034ad8745c7e0982158
- tools last changed: 2026-10-20T02:18:23.077Z
- badge: [![protogrid quality](https://protogrid.dev/badge/tech.searchpipe/searchpipe.svg)](https://protogrid.dev/servers/tech.searchpipe/searchpipe)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-20 `searchpipe_search` changed (outputSchema)
- 2026-10-18 `searchpipe_search` changed (outputSchema)
- 2026-10-16 `searchpipe_search` changed (outputSchema)
- 2026-10-12 `searchpipe_verify` added
  - Verify a factual claim against retrieved evidence: claim in, verdict out — a four-label judgment (supported / partial / unsupported / inconclusive), not generated text. Every result ships with verifiable evidence — span-level quotes, claim verdicts, and source authority — not just links. Verdict labels: `supported` = evidence text clearly supports the claim; `partial` = partly supported or weak evidence; `unsupported` = reachable evidence does not support the claim (misattributed citation detected); `inconclusive` = the claim could not be judged (fetch failure, paywall, or insufficient evidence) — the tool reports that honestly instead of guessing. Verification fetches source pages and judges claim-evidence consistency, so it typically takes 5-15 seconds. Uses the same commercial pipeline as the HTTP POST /verify endpoint: authentication → email verification → rate limiting → input moderation → per-request credit charge → verification → refund on failure → usage logging. Credits are charged per call; an inconclusive verdict is still a delivered result and is not refunded. mode: evidence route — "paper" / "web" / "auto" (default; a DOI or arXiv signal decides). evidence_urls: up to 5 caller-supplied citations to verify. max_evidence: maximum evidence items to return (1-10, default 5). api_key: an API key starting with `sp-`. It may also be provided through the SEARCHPIPE_API_KEY environment variable (the parameter takes precedence). Returns VerifyResponse (verdict / confidence / reason_code / evidences[] / timing). Returns a tool error on authentication failure, insufficient credits, content violation, verification failure, or when the verify endpoint is disabled ("Verify endpoint is not available").
- 2026-10-11 `searchpipe_search` changed (outputSchema)
- 2026-09-29 `searchpipe_search` changed (description)
  - before: Run an AI-powered web search for a query: SearXNG retrieval → page fetching → LLM reranking → optional AI answer. Uses the same commercial pipeline as the HTTP POST /search endpoint: authentication → rate limiting → input moderation → credit charge → search → output moderation + AI-generated marker → refund on failure → usage logging. Credits are charged per call. api_key: an API key starting with `sp-`. It may also be provided through the SEARCHPIPE_API_KEY environment variable (the parameter takes precedence). Returns Tavily-style structured results (query / answer / results[]). Returns a tool error on authentication failure, insufficient credits, content violation, or retrieval failure.
  - after: Run an AI-powered web search for a query: multi-engine retrieval → page fetching → LLM reranking → optional AI answer. Uses the same commercial pipeline as the HTTP POST /search endpoint: authentication → rate limiting → input moderation → credit charge → search → output moderation + AI-generated marker → refund on failure → usage logging. Credits are charged per call. api_key: an API key starting with `sp-`. It may also be provided through the SEARCHPIPE_API_KEY environment variable (the parameter takes precedence). Returns Tavily-style structured results (query / answer / results[]). Returns a tool error on authentication failure, insufficient credits, content violation, or retrieval failure.

Full history: https://api.protogrid.dev/v1/servers/tech.searchpipe%2Fsearchpipe/changes

## Remotes

- https://searchpipe.tech/mcp/ (streamable-http, auth api_key ${SEARCHPIPE_TOKEN}, reachable true, uptime30d 0.9292035)

## Packages

_none_

## Tools (2)

- `searchpipe_search`: Run an AI-powered web search for a query: multi-engine retrieval → page fetching → LLM reranking → optional AI answer.

Uses the same commercial pipeline as the HTTP POST /search endpoint: authentication → rate limiting →
input moderation → credit charge → search → output moderation + AI-generated marker → refund on failure
→ usage logging. Credits are charged per call.

api_key: an API key starting with `sp-`. It may also be provided through the SEARCHPIPE_API_KEY
environment variable (the parameter takes precedence).
Returns Tavily-style structured results (query / answer / results[]).
Returns a tool error on authentication failure, insufficient credits, content violation, or retrieval failure.
- `searchpipe_verify`: Verify a factual claim against retrieved evidence: claim in, verdict out — a four-label judgment (supported / partial / unsupported / inconclusive), not generated text.

Every result ships with verifiable evidence — span-level quotes, claim verdicts, and source authority — not just links.
Verdict labels: `supported` = evidence text clearly supports the claim; `partial` = partly supported or weak evidence;
`unsupported` = reachable evidence does not support the claim (misattributed citation detected); `inconclusive` = the claim
could not be judged (fetch failure, paywall, or insufficient evidence) — the tool reports that honestly instead of guessing.
Verification fetches source pages and judges claim-evidence consistency, so it typically takes 5-15 seconds.

Uses the same commercial pipeline as the HTTP POST /verify endpoint: authentication → email verification → rate limiting →
input moderation → per-request credit charge → verification → refund on failure → usage logging. Credits are charged per
call; an inconclusive verdict is still a delivered result and is not refunded.

mode: evidence route — "paper" / "web" / "auto" (default; a DOI or arXiv signal decides). evidence_urls: up to 5
caller-supplied citations to verify. max_evidence: maximum evidence items to return (1-10, default 5).
api_key: an API key starting with `sp-`. It may also be provided through the SEARCHPIPE_API_KEY environment variable
(the parameter takes precedence).
Returns VerifyResponse (verdict / confidence / reason_code / evidences[] / timing).
Returns a tool error on authentication failure, insufficient credits, content violation, verification failure, or when the
verify endpoint is disabled ("Verify endpoint is not available").