# Zearch (npm · @zearchcomputer/mcp)

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

- Trust score: 92/100 (high trust)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `@zearchcomputer/mcp`: 92/100 (this document), [markdown](https://verifymcp.io/servers/zearchcomputer-zearch-mcp/zearchcomputer-mcp.md), [page](https://verifymcp.io/servers/zearchcomputer-zearch-mcp/zearchcomputer-mcp)

## Channel facts

- Registry: `npm`
- Package: `@zearchcomputer/mcp`
- Version: `0.1.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 0 of 3 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 97/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to zearchcomputer/zearch-mcp).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 22 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 83/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 926 tokens (~115/item across 8 items; 6 tools + 2 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 73/100
  - Stability observed for 22 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 92% of tool parameters carry a description.
  - Structured output schemas are declared (83% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).
  - Supports UI / widget rendering.

## Install

### How do I install the Zearch MCP server?

Zearch runs locally as an npm package, launched with npx -y @zearchcomputer/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add zearchcomputer-zearch-mcp -- npx -y @zearchcomputer/mcp
```

### Cursor

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

### VS Code

```json
{
  "servers": {
    "zearchcomputer-zearch-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@zearchcomputer/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add zearchcomputer-zearch-mcp -- npx -y @zearchcomputer/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "zearchcomputer-zearch-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@zearchcomputer/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add zearchcomputer-zearch-mcp --command npx --arg -y --arg @zearchcomputer/mcp
```

### Hermes

```yaml
mcp_servers:
  zearchcomputer-zearch-mcp:
    command: "npx"
    args: ["-y", "@zearchcomputer/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "zearchcomputer-zearch-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@zearchcomputer/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add zearchcomputer-zearch-mcp -t stdio -c npx -a -y @zearchcomputer/mcp
```

### Other

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

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-03 (score 92, +1)

No change was recorded against any check on this day. Stability & Change Management went from 63 to 67. That category is still filling its 30-day observation window: 19 days of observed history at the previous scan, 20 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-01 (score 91, +1)

No change was recorded against any check on this day. Stability & Change Management went from 57 to 60. That category is still filling its 30-day observation window: 17 days of observed history at the previous scan, 18 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-30 (score 90, +1)

No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 89, +1)

No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 88, +1)

No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-24 (score 87, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-22 (score 86, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-10-14 (score 82, +33)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional regression] Security disclosure: unverified → fail
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: pass
- [functional] First check of Tool coverage: 92
- [functional] First check of Schema quality: fail
- [functional] First check of Capabilities: pass
- [functional] First check of Tool coverage: 83
- [functional] First check of Schema quality: good

## MCP tools (6)

### `research` (~327 tokens)

Research with checked answers

Ask Zearch a question. Zearch searches the web (or reads the page or site you give it), Jev selects the passages that answer it, a writer drafts from those passages only, and Jev checks every paragraph against its cited source before the answer is returned. Unsupported paragraphs are cut; if nothing survives you get the selected source passage (answer_type "excerpt").

Modes and credits: standard (1, a direct answer in seconds), deep (5, a cited report from up to 8 sources), compare (2, a side-by-side comparison), scrape (1, what one public HTTPS page says; needs url), crawl (3, up to five pages of one site; needs url), reverse (10, static analysis of how an app, repo or site works; needs url, runs on a queue and can take minutes). A follow-up with parent_id that needs no new search costs 0.3. Errors are free.

Returns the answer as Markdown with [n] citations, the sources with the exact excerpt Jev read, per-paragraph support scores, and suggested follow-ups.

Input parameters:

- `mode` (string): How much research to do. See the tool description for costs.
- `parent_id` (string): Id of a previous run, to ask a follow-up in the same conversation.
- `query` (string, required): The question, in plain language.
- `url` (string): Public HTTPS URL. Required for scrape, crawl and reverse; ignored otherwise.
- `use_notes` (boolean): Also use the account's private Zearch notes and documents as evidence.

Output parameters:

- `answer` (string|null): Markdown with [n] citations.
- `answer_type` (string|null): verified: every paragraph passed Jev. excerpt: the selected source passage, because no draft could be supported.
- `created` (number)
- `error` (string|null)
- `followups` (array)
- `id` (string)
- `mode` (string)
- `object` (string)
- `parent_id` (string|null)
- `query` (string)
- `sources` (array)
- `status` (string): pending, streaming, complete, error, interrupted or redacted.
- `timing_ms` (number|null)
- `updated` (number)
- `verification`

### `verify` (~177 tokens)

Verify text against sources

Check text against the sources it cites, paragraph by paragraph, with Jev (the same check Zearch runs on its own answers). Cite sources inline as [1], [2]… in the order you list them. Use it to gate output from your own model before a person sees it.

Limits: text up to 8,000 characters; 1 to 8 sources of up to 20,000 characters each. Costs 1 credit, charged only when the check completes. Returns pass/fail per paragraph with support and attribution probabilities.

Input parameters:

- `question` (string): The question the text answers, if any. Improves the check.
- `sources` (array, required): Sources in citation order: the first is [1].
- `text` (string, required): Markdown to check. Every paragraph should cite at least one source as [n].

Output parameters:

- `model` (string|null)
- `object` (string)
- `paragraphs` (array)
- `passed` (boolean): True when every paragraph met the support threshold.
- `threshold` (number)

### `get_run` (~63 tokens)

Get a research run

Fetch one of your Zearch runs by id: its answer, sources, verification and status. Use it to check on a queued Reverse engineer run, or to reopen an earlier answer. Free.

Input parameters:

- `id` (string, required): The run id returned by research or list_runs.

Output parameters:

- `answer` (string|null): Markdown with [n] citations.
- `answer_type` (string|null): verified: every paragraph passed Jev. excerpt: the selected source passage, because no draft could be supported.
- `created` (number)
- `error` (string|null)
- `followups` (array)
- `id` (string)
- `mode` (string)
- `object` (string)
- `parent_id` (string|null)
- `query` (string)
- `sources` (array)
- `status` (string): pending, streaming, complete, error, interrupted or redacted.
- `timing_ms` (number|null)
- `updated` (number)
- `verification`

### `list_runs` (~55 tokens)

List research runs

List your recent Zearch runs, newest first. The app and the API share one history. Free. Page with starting_after.

Input parameters:

- `limit` (integer)
- `starting_after` (string): Run id from the previous page.

Output parameters:

- `data` (array)
- `has_more` (boolean)
- `object` (string)

### `get_wallet` (~73 tokens)

Credit balance

Show the Zearch credit balance this key spends from: available and held credits, plan, credit lots and when they expire. Optionally include recent ledger entries. Free.

Input parameters:

- `before` (integer): next_before cursor from a previous call, for older entries.
- `include_entries` (boolean): Also return recent ledger entries.

Output parameters:

- `entries` (object)
- `wallet` (object)

### `get_pricing` (~33 tokens)

Zearch pricing

The public Zearch price list: credits per request type, plans and top-ups. Free; no API key needed.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/zearchcomputer-zearch-mcp/zearchcomputer-mcp#diagnostics

## Score history

- 2026-11-05: 92
- 2026-11-04: 92
- 2026-11-03: 92
- 2026-11-02: 91
- 2026-11-01: 91
- 2026-10-31: 90
- 2026-10-30: 90
- 2026-10-29: 89
- 2026-10-28: 89
- 2026-10-27: 88
- 2026-10-26: 88
- 2026-10-25: 87
- 2026-10-24: 87
- 2026-10-23: 86
- 2026-10-22: 86
- 2026-10-21: 82
- 2026-10-20: 82
- 2026-10-19: 82
- 2026-10-18: 82
- 2026-10-17: 82
- 2026-10-16: 82
- 2026-10-15: 82
- 2026-10-14: 82
- 2026-10-13: 49

## Common questions

### What is the Zearch MCP server?

Zearch is an MCP server listed in the public MCP registry as io.github.zearchcomputer/zearch-mcp. Research with answers you can check: every paragraph verified against its cited source. This page covers its npm package (@zearchcomputer/mcp).

### Is the Zearch MCP server safe to use?

Zearch scores 92 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Zearch MCP server expose?

Zearch exposes 6 tools: research, verify, get_run, list_runs, get_wallet, get_pricing. Their descriptions and schemas cost roughly 728 tokens of context every time the server is loaded.

### Is the Zearch MCP server still maintained?

Zearch is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Zearch MCP server under?

Zearch declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@zearchcomputer/mcp
- Socket report: https://socket.dev/npm/package/@zearchcomputer/mcp
- Repository: https://github.com/zearchcomputer/zearch-mcp
- Website: https://zearch.computer/
- Changelog RSS feed: https://verifymcp.io/servers/zearchcomputer-zearch-mcp/zearchcomputer-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/zearchcomputer-zearch-mcp/zearchcomputer-mcp.json
- HTML version of this page: https://verifymcp.io/servers/zearchcomputer-zearch-mcp/zearchcomputer-mcp