Zearch

io.github.zearchcomputerPublished by GitHub account zearchcomputerv0.1.0Updated Oct 24, 2026

Research with answers you can check: every paragraph verified against its cited source.

VerifiedSTDIODesktop onlyWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Zearch MCP gives an assistant cited research answers whose every paragraph is checked against its source, plus verification of text against your own sources.

What you can do
  • Run checked research: standard answers, deep reports from up to 8 sources, comparisons, single-page scrapes, small site crawls, and static-analysis breakdowns of an app, repo or site
  • Verify your own draft text paragraph by paragraph against sources you supply, with pass/fail and support scores
  • Reopen past runs, list recent runs, and check on queued reverse runs
  • Read credit balance, lots, expiry and ledger entries, and the public price list
  • Use bundled resources and prompts for run Markdown, pricing, cited briefs, fact checks and comparison tables
When to use it
Useful when you want research output you can audit rather than trust: answers with numbered sources and the exact passage read, or a check of model-written text against documents you already have. Best suited to fact-checking, briefs and comparisons where citations matter.
Requirements
Runs locally via npx from the npm package @zearchcomputer/mcp (Node.js). Requires a Zearch API key (zk_live_…) created in the Zearch app under Account → API keys, passed as ZEARCH_API_KEY. Optional settings include ZEARCH_API_URL, ZEARCH_TIMEOUT_MS, ZEARCH_REVERSE_WAIT_MS and ZEARCH_UI. Network access to the Zearch API is needed.
Before you install
Research and verify calls spend credits from your Zearch account; deep research costs 5 credits and reverse 10, while errors are not charged. The API key is a billable secret, so keep it out of shared configs and prefer the prompt-based setup where offered. In HTTP mode callers send their own key and the server stores none. Access is described as early and not open to everyone yet.

Installation

In SourceWeft

  1. Open Zearch in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

[zearch]

Answers you can check, inside any MCP client.

@zearchcomputer/mcp connects Claude, Cursor, VS Code and other Model Context Protocol clients to Zearch. Ask a question and you get an answer whose every paragraph was checked against the source it cites, with the exact passage Zearch read. Or check text your own model wrote against sources you already have.

Status: early. The Zearch API is not open to everyone yet.

[npm]

How an answer is made

mermaid
flowchart LR  Q([Question]) --> S[Search]  S --> J1[Jev selects<br/>passages]  J1 --> W[Writer drafts from<br/>those passages only]  W --> J2[Jev checks<br/>each paragraph]  J2 -->|supported| A([Cited answer])  J2 -->|not supported| E([The source<br/>passage itself])

Jev is TypeSafe AI's evidence model. When a paragraph can't be supported it is cut, and when nothing survives you get the best source passage instead of a guess (answer_type: "excerpt").

Tools

ToolWhat it doesCredits
researchChecked answer with numbered sources and the passages Jev read. Modes: standard, deep (a report from up to 8 sources), compare, scrape (one page), crawl (up to five pages of a site), reverse (how an app, repo or site works, from static analysis). Follow-ups with parent_id.1 · 5 · 2 · 1 · 3 · 10; follow-up 0.3
verifyChecks your text against your sources, paragraph by paragraph: pass/fail, support and attribution scores. Cite sources as [1], [2]…1
get_runReopens a run, or checks on a queued reverse run.free
list_runsYour recent runs (shared with the Zearch app).free
get_walletCredit balance, lots and expiry, recent ledger entries.free
get_pricingPublic price list. No key needed.free

Errors are never charged. A run that can only return a source passage costs half.

Progress. research streams its stages (Searching the web → Choosing the most relevant evidence → Checking each claim against its source) as MCP progress notifications, so clients that show progress show what Zearch is doing.

Answer view. In clients that support MCP Apps, research, get_run and verify render an inline card: the answer with citation chips, source cards with the excerpt Jev read, an Open button for each source, and follow-up suggestions. It follows the client's light or dark theme. Other clients get the same content as text. Set ZEARCH_UI=0 to turn it off.

Resources. zearch://runs/{id} (a run as Markdown; your recent runs are listed), zearch://pricing.

Prompts. research_brief (a cited brief from deep research), fact_check (find sources for a draft, then verify it), compare (a table with a citation in every cell).

Install

You need a Zearch API key (zk_live_…). Create one in the Zearch app under Account → API keys.

Claude Code

sh
claude mcp add zearch --env ZEARCH_API_KEY=zk_live_your_key -- npx -y @zearchcomputer/mcp

Claude Desktop

In Settings → Developer → Edit config, add:

json
{  "mcpServers": {    "zearch": {      "command": "npx",      "args": ["-y", "@zearchcomputer/mcp"],      "env": { "ZEARCH_API_KEY": "zk_live_your_key" }    }  }}

Cursor

.cursor/mcp.json (project) or ~/.cursor/mcp.json (global): the same mcpServers block as Claude Desktop.

VS Code

.vscode/mcp.json, which prompts for the key instead of storing it:

json
{  "inputs": [{ "type": "promptString", "id": "zearch-key", "description": "Zearch API key", "password": true }],  "servers": {    "zearch": {      "type": "stdio",      "command": "npx",      "args": ["-y", "@zearchcomputer/mcp"],      "env": { "ZEARCH_API_KEY": "${input:zearch-key}" }    }  }}

Run from source

sh
git clone https://github.com/zearchcomputer/zearch-mcpcd zearch-mcpnpm ci && npm run build

Then use node /absolute/path/to/zearch-mcp/dist/index.js as the command in any config above, instead of npx -y @zearchcomputer/mcp.

Remote (HTTP) mode

sh
npx -y @zearchcomputer/mcp --http --port 8787            # http://127.0.0.1:8787/mcp

Every request uses the caller's own key, sent as Authorization: Bearer zk_live_…; the server stores no keys. ZEARCH_API_KEY is used as a fallback only when the server listens on loopback, so a public deployment can't spend the operator's credits for someone else. GET /healthz reports liveness.

To serve on a public interface, bind it and list the hostnames you serve, so requests with other Host headers are refused:

sh
npx -y @zearchcomputer/mcp --http --host 0.0.0.0 --port 8080 --allowed-hosts mcp.zearch.computer

A Dockerfile is included for this.

Configuration

VariableDefaultPurpose
ZEARCH_API_KEYYour API key. In HTTP mode, callers send their own.
ZEARCH_API_URLhttps://zearch.computer/v1API base URL. http:// is accepted only for localhost.
ZEARCH_TIMEOUT_MS120000Per-request timeout. Research streams get at least 180 s.
ZEARCH_REVERSE_WAIT_MS300000How long research waits for a reverse run before returning its id for get_run.
ZEARCH_UIon0 turns off the inline answer view.
ZEARCH_MCP_ALLOWED_HOSTSSame as --allowed-hosts.
PORT8787HTTP port when --port isn't given.

Reliability

  • Each research call carries an idempotency key, reused across retries, so a retried request never runs or charges twice.
  • Network failures, 5xx responses and per-minute rate limits are retried with backoff that honours Retry-After. Out-of-credit, auth and validation errors are not retried; they come back as a tool error that says what to do next.
  • If a research stream drops, the server reads the finished run instead of failing.
  • Cancelling a tool call in the client cancels the request to Zearch.
  • Logs go to stderr. Keys are never logged.

Development

sh
npm cinpm test        # builds, then runs the tests against a local mock of the Zearch API

Tests make no network calls beyond localhost and spend no credits. The view is a single dependency-free HTML file in src/ui/answer.html.

The server is built on the MCP TypeScript SDK v2 (protocol revision 2026-07-28, with 2025-era clients still served) and talks to the Zearch API.

Security

Report vulnerabilities privately through GitHub security advisories. See the security policy.

License

MIT

Source: README.md at commit e44af87

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestOct 13, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts