Levirge Search

Research your agents can rely on.

Search, read and cite public sources — even when ordinary fetch tools come back with an empty page.

Try a live read → Install
Live in production Under a second on a warm read MCP · REST Examples · FAQs Agents: /search.md · /llms.txt

Discover the shape first, then ask for exactly the fields — click each call to see what comes back. The 1.26 MB response stays on the server; 28 KB reaches the agent. Real capture →

levirge search · MCP connected 6 tools
agent.9b2 asked: "Summarise what changed between our pinned build and master."
Click each call to see what comes back:
body cached server-side — the select call reused it · kept for 24 h
select → the fields alone, shape intact
api.github.com/…/compare/b10256...b1030828 KB
{ "ahead_by": 52, "total_commits": 52,
  "commits": [
    { "sha": "22dc605c4ead…",
      "commit": { "message":
        "ci: fix vulkan llvmpipe runs (#26533)" } },
    { "sha": "935cad6497e8…",
      "commit": { "message":
        "llama : move n_vocab from llama_sampler…" } },
    … 50 more rows, rows stay aligned ] }
Try it

Read a page · test

Enter a public URL. Levirge Search opens the page in a real, full browser and returns proof of the read: HTTP status, page title and size. Nothing else.

Public pages only · paywalled and login-gated sources aren't supported

A page that can't be read is reported with the reason — never summarised from nothing. That's the point.

<1 s
to open a demanding source, warm — down from 10–20
1.26 MB → 28 KB
one captured source, narrowed to the fields asked for
24 h
anything read stays available — repeat reads come from cache
The problem

Agents are only as good as what they can reach

The most valuable sources block ordinary tools — and a blocked agent doesn't stop. It answers from less, and presents it as the source.

Without SearchWith Levirge Search
Blocked sitesA 403, a CAPTCHA, or an empty pageA real browser opens the page; the source is remembered
Confident guessesThe agent answers from search snippets — a summary of a summaryFailures reported with the reason; every answer traceable to its page
Fenced toolsBlocklists; constructed URLs refused; raw HTTP forbiddenOne sanctioned MCP integration — any URL the agent builds
DIY glueSearch API + scraper + browser service, yours to maintainFind and read in one integration
Context costA 200 KB page for a two-line question, on every readAsk for fields — 1.26 MB → 28 KB — with a 24 h cache

"Without" column: Claude Code's native WebFetch, tested 8 Aug 2026 — captured verbatim in the examples. Other clients differ in detail, not outcome.

See these problems in practice →
The contract

What agents send, what comes back

One integration exposes six tools — search, fetch, fetch_async, fetch_results, stealth_list, stealth_add — grouped here into four workflows. Markdown pages arrive with a route note; JSON API bodies come back raw and parseable.

ToolGet backUse it whenOn failure
searchquery, limit?Ranked {title, url, content}Proof: captured trace →No URL yet — find candidate sourcesThe error comes back, not an empty answer
fetchurl, select?, schema?, max_bytes?, headers?Clean markdown with a route note; raw JSON for APIs. select returns just the fields (JSON) or whole matching sections (markdown); schema: true returns the shape before the payloadProof: blocked portal → · 1.26 MB → 28 KB →You have the URL and want it read — or want an unknown API's shape firstReported with the reason — never an empty page
fetch_async + fetch_resultsurlsImmediate acknowledgement, then done / pending / failed per URLProof: captured run →A list of pages to read without holding the conversation openFailed URLs listed; resubmit to retry
stealth_list / stealth_adddomainThe registry of sources that need the full browserProof: captured error →You already know a source blocks plain fetches

A typical page is a few KB of markdown; select narrows the rest server-side — fields from JSON, whole sections from markdown — before anything touches your agent's context.

Context

Stop paying for words your agent didn't need

A two-megabyte source used to be your problem. Ask Levirge Search for the part you actually need and that's what comes back — in one captured run, a 1.26 MB API response became 28 KB. The rest is kept for 24 hours, so follow-ups are answered from cache.

Less context burned. Cheaper calls. Sharper answers.

See the worked example →

Whole source
1.26 MB
Fields you asked for
28 KB
Same answer · 2.2% of the readingFollow-ups served from what it already has
Accountable

See what your agent read

Every search and every source, with the page the agent actually read — the content, not a log line, available for 24 hours after the read.

levirge search · activity your workspace
Levirge Search — the activity console with demo data: last-24h activity graph, searches / fetches / errors / latency stats, and the recent-activity list showing each read with its route and timing

Your workspace is yours alone — separate from every other customer's, with per-user access you issue and revoke yourself.

How it works

Agents call tools; Search does the reading

An agent calls search or fetch. Every read passes a cache check, per-source pacing and a concurrency guard before a browser is opened — direct where that works, a full browser where the source needs one — then the content comes back over the same surface.

Agents The internet Web UI user Claude ChatGPT Pi OpenCode Any MCP client REST API scripts · CI search · fetch Levirge Search Search Fetch Cache Query one workspace · every read on record request page Docs & forums ✓ READ Sites that need a full browser ✓ READ Machine-readable APIs ✓ READ Paywalls & logins ✗ NEVER

Search reads pages a person could open in their own browser. It is not a way around a paywall or a login.

Before you install

Access, limits and what we keep

Public sources, read at a human pace

Search reads pages a person could open in their own browser. It is not a way around a paywall or a login, and it won't pretend to be. Per-source pacing with jitter and a concurrency guard protect the sites being read — bulk scraping isn't supported, and workspaces detected scraping are suspended and investigated.

Your workspace, your tokens

Separate from every other customer's, with per-user access tokens you issue and revoke yourself, and usage you can see by user. We host it; if research needs to run somewhere specific, talk to us about deployment options.

What we keep, and for how long

Every search and read is recorded for your workspace — URL, outcome, timestamp. The page as the agent received it stays available for 24 hours, then expires; the record stays.

Pricing

Quoted per workspace, not per query. Spend 30 minutes with an engineer — we'll set up your workspace and walk through pricing on the call.

Install

Pick your agent, paste the command

Claude Code and Codex install from the built-in marketplace; every other MCP client connects to the same endpoint.

Early access — capacity is limited and workspaces are set up in order of request. Installing now is fine: the plugin connects the moment your workspace is active.

claude plugin marketplace add levirge/search
claude plugin install search@levirge-search

Installs the /search:* commands and connects the MCP server — sign in with OAuth on first use; workspace tokens remain as a fallback.

for agents MCP · Streamable HTTP
discovery
levirge.com/llms.txt
docs
levirge.com/search.md
endpoint
https://search.levirge.com/mcp
definition
levirge.com/search/mcp.json
auth
OAuth sign-in · bearer token as fallback
verify
call stealth_list — read-only
tools
6 — search · fetch · fetch_async · fetch_results · stealth_list · stealth_add
Client config — OAuth is negotiated on connect; add an Authorization header only for token fallback.

Restart your client after installing (on claude.ai, remove and re-add the connector), then ask a research question — /search:research to start. Connecting by hand? The endpoint speaks Streamable HTTP; REST is available too.

Next step

Give your agents something real to read

Install in your client in about a minute — or have an engineer walk you through it live, on a source that stops ordinary tools.