# io.github.jakeyoung1/veris (npm · veris-mcp)

Provenance-first web + SEC EDGAR data for AI agents: every fact carries its verifiable source.

- Trust score: 69/100 (medium)
- Change this week: +23
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `veris-mcp`: 69/100 (this document), [markdown](https://verifymcp.io/servers/jakeyoung1-veris/veris-mcp.md), [page](https://verifymcp.io/servers/jakeyoung1-veris/veris-mcp)

## Channel facts

- Registry: `npm`
- Package: `veris-mcp`
- Version: `0.2.0`
- 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 2026-08-03.

- **Supply Chain Security**: 84/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known low-severity CVE affects @mozilla/readability 0.5.0, a direct dependency. A fixed version is available.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (146 of 148), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 53 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 77/100
  - AI-judged instruction clarity (excellent).
  - Tool/resource definitions use about 730 tokens (~91/item across 8 items; 8 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 27/100
  - Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add jakeyoung1-veris -- npx -y veris-mcp
```

### Codex

```bash
codex mcp add jakeyoung1-veris -- npx -y veris-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "jakeyoung1-veris": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "veris-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add jakeyoung1-veris --command npx --arg -y --arg veris-mcp
```

### Hermes

```yaml
mcp_servers:
  jakeyoung1-veris:
    command: "npx"
    args: ["-y", "veris-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "jakeyoung1-veris": {
      "command": "npx",
      "args": [
        "-y",
        "veris-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.

### 2026-08-03 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-08-02 (score 68, +63)

- [security regression] CVE-2025-2792 affects this package: low
- [security regression] Provenance: unverified → fail
- [security regression] Known CVEs: unverified → fail
- [security improvement] Install scripts: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] License: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Stability: unverified → 0.23
- [functional improvement] Schema quality: unverified → excellent
- [functional] Licence: MIT

### 2026-08-01 (score 5, −16)

- [functional regression] Tool coverage: 100 → unverified
- [functional] First check of Schema quality: unverified

### 2026-07-31 (score 21, −25)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-27 (score 46)

First indexed and scored.

## MCP tools (8)

### `web_search` (~66 tokens)

Web Search

Search the web. Returns ranked results (title, url, snippet) as structured JSON. Uses Brave Search when BRAVE_API_KEY is set, otherwise keyless DuckDuckGo.

Input parameters:

- `n` (integer): Max results (default 5)
- `query` (string, required): Search query

### `web_read` (~78 tokens)

Web Read (provenance-tracked)

Fetch a URL and return clean markdown PLUS provenance: published date, author, canonical URL, content hash, fetch time, and license signals. The provenance is the point — verifiable source metadata an AI normally cannot get.

Input parameters:

- `fresh` (boolean): Bypass cache and refetch (default false)
- `url` (string, required): URL to read

### `web_research` (~67 tokens)

Web Research (search + read + cite)

One-shot research: search the web, fetch the top results, and return their clean content bundled with full provenance per source. Ideal for grounding an answer with citations.

Input parameters:

- `n` (integer): Sources to read (default 3)
- `query` (string, required): Research question or topic

### `finance_filings` (~120 tokens)

SEC Filings (EDGAR)

List a company's recent SEC filings from EDGAR by ticker, name, or CIK. Free, official, no API key. Returns form type, filing/report dates, accession number, and direct document URL — provenance is authoritative (straight from SEC).

Input parameters:

- `formType` (string): Filter by form, e.g. "10-K", "10-Q", "8-K"
- `limit` (integer): Max filings (default 10)
- `query` (string, required): Ticker (e.g. NVDA), company name, or CIK

### `finance_filing_read` (~110 tokens)

Read SEC Filing

Fetch and clean a specific SEC filing. Pass a filing document URL, OR a company query plus formType to auto-read the most recent matching filing (e.g. latest 10-K for NVDA). Returns clean text plus provenance.

Input parameters:

- `formType` (string): Form to auto-pick with query, e.g. "10-K"
- `query` (string): Ticker/name/CIK (used when url is omitted)
- `url` (string): EDGAR filing document URL

### `finance_financials` (~96 tokens)

Company Financials (SEC XBRL)

Key structured financials (revenue, net income, total assets, cash, diluted EPS) from SEC XBRL data. Each figure is stamped with the exact filing it came from (form, filed date, accession, fiscal period) — authoritative provenance. Ticker / name / CIK. No API key.

Input parameters:

- `query` (string, required): Ticker (e.g. NVDA), company name, or CIK

### `watch_manage` (~121 tokens)

Manage Watches (change-detection)

Add, remove, or list watches. Watch a company's SEC filings (target = ticker/name/CIK, optional formType like 8-K) or any URL (target = https://…, watched by content hash). Adding baselines current state; use watch_check later to see only what's new.

Input parameters:

- `action` (string, required): What to do
- `formType` (string): Optional form filter for filings watches, e.g. "8-K"
- `target` (string): Ticker/name/CIK, URL, or watch id (for remove)

### `watch_check` (~72 tokens)

Check Watches (alerts)

Check every watch for changes since the last check: new SEC filings, changed page content. Returns only what's new and rolls baselines forward. Run it on a schedule (cron / scheduled agent) to turn veris into an alert feed. Note: the SEC filing index may lag up to ~1h (cache).

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/jakeyoung1-veris/veris-mcp#diagnostics

## Score history

- 2026-08-03: 69
- 2026-08-02: 68
- 2026-08-01: 5
- 2026-07-31: 21
- 2026-07-30: 46
- 2026-07-28: 46
- 2026-07-27: 46

## Links

- npm package: https://www.npmjs.com/package/veris-mcp
- Socket report: https://socket.dev/npm/package/veris-mcp
- Repository: https://github.com/jakeyoung1/veris
- Changelog RSS feed: https://verifymcp.io/servers/jakeyoung1-veris/veris-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/jakeyoung1-veris/veris-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/jakeyoung1-veris/veris-mcp