# Patchwire (remote · patchwire.monowire.dev)

Hourly security advisories for JS, AI and web3 packages: ranges, fixes and exploit conditions.

- Trust score: 74/100 (medium)
- Change this week: −1
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- remote · `patchwire.monowire.dev`: 74/100 (this document), [markdown](https://verifymcp.io/servers/dev-monowire-patchwire/patchwire.md), [page](https://verifymcp.io/servers/dev-monowire-patchwire/patchwire)

## Channel facts

- Endpoint: `https://patchwire.monowire.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.0.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, 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.

- **Endpoint Security**: 69/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation.
  - HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 71/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 952 tokens (~190/item across 5 items; 5 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 40/100
  - Stability observed for 12 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.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 6 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).

## Install

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

Patchwire is a hosted endpoint at https://patchwire.monowire.dev/mcp, so there is nothing to install locally. 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 --transport http dev-monowire-patchwire 'https://patchwire.monowire.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-monowire-patchwire": {
      "url": "https://patchwire.monowire.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-monowire-patchwire": {
      "type": "http",
      "url": "https://patchwire.monowire.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-monowire-patchwire]
url = "https://patchwire.monowire.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-monowire-patchwire": {
      "type": "remote",
      "url": "https://patchwire.monowire.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-monowire-patchwire --url 'https://patchwire.monowire.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-monowire-patchwire:
    url: "https://patchwire.monowire.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-monowire-patchwire": {
      "Transport": "http",
      "Url": "https://patchwire.monowire.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-monowire-patchwire -t streamable-http -u 'https://patchwire.monowire.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dev-monowire-patchwire": {
      "type": "http",
      "url": "https://patchwire.monowire.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-11-04 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-03 (score 73, −4)

- [security regression] HTTPS: pass → unverified

### 2026-11-01 (score 77, +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.

### 2026-10-30 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 75, 0)

- [security] Tool “get_advisories” rewrote its description, which is the text the model reads
- [security] Tool “latest_safe” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 163 → 190
- [cosmetic] “get_advisories” added an optional parameter “since”

### 2026-10-27 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-26 (score 74, +5)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “latest_safe” rewrote its description, which is the text the model reads
- [security] Tool “get_advisories” rewrote its description, which is the text the model reads
- [security] Tool “get_advisory” rewrote its description, which is the text the model reads
- [security] Tool “get_platform_bulletins” rewrote its description, which is the text the model reads
- [security] Tool “list_feed” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 0% → 100%
- [functional] Schema quality: fair → excellent
- [cosmetic] “get_advisories” reworded the description of “packages”
- [cosmetic] “get_advisory” reworded the description of “id”
- [cosmetic] “get_platform_bulletins” reworded the description of “platform”
- [cosmetic] “latest_safe” reworded the description of “package”
- [cosmetic] “list_feed” reworded the description of “days”
- [cosmetic] “list_feed” reworded the description of “limit”
- [cosmetic] “list_feed” reworded the description of “section”
- [cosmetic] “list_feed” reworded the description of “severity”

### 2026-10-25 (score 69, 0)

- [functional improvement] Stability: unverified → 0.03

## MCP tools (5)

### `get_advisories` (~269 tokens)

Advisories for packages

Check npm packages for security advisories. Start here before installing, upgrading or deploying: send 1 to 50 package names (never versions) and get, per package, its total and up to 20 advisories of the last 120 days, newest first, each with vulnerable ranges, fixed versions and the conditions that make it exploitable. A package with none returns total 0. Compare the ranges with your lockfile. For a daily check, pass since (the time of your last check) to get only what is new. For one advisory in full use get_advisory; for the version to upgrade to, use latest_safe.

Input parameters:

- `packages` (array, required): npm package names as written in package.json, 1 to 50, for example ["next", "@supabase/supabase-js"]. Names only, never versions: compare the returned ranges with your lockfile.
- `since` (string): Only advisories new since this ISO date or date-time ("2026-10-27" is UTC midnight, or "2026-10-27T08:00:00Z"): published, or first read by Patchwire, after it. For a daily check, pass the time of yo…

### `get_advisory` (~137 tokens)

One advisory in full

Read one advisory in full by id: CVE, GHSA, MAL or Patchwire id, any case, aliases resolve. Returns its ranges, fixed versions, exploit conditions with the source sentence they come from, a summary and the sources. Use it after get_advisories or list_feed gave you an id. An unknown id, or one older than 120 days, returns an error.

Input parameters:

- `id` (string, required): An advisory id: CVE (CVE-2026-12345), GHSA (GHSA-xxxx-xxxx-xxxx), MAL or a Patchwire id. Any case; aliases resolve.

### `latest_safe` (~165 tokens)

Safe version per release line

Find the version to upgrade to for one npm package. Returns, per release line (major, or minor for 0.x), the version that fixes every known advisory of the last 120 days; a line still affected has safe: null and the ids that keep it affected; a line hit with no fix of its own (14.x when only 15.x is fixed) has safe: null and upgrade_to, the lowest safe version above it. Also lists advisories with no fix found, and says whether this package name itself is flagged as malicious. Use it after get_advisories, to pick one target version per line.

Input parameters:

- `package` (string, required): One npm package name as written in package.json, for example "next" or "@solana/web3.js".

### `list_feed` (~204 tokens)

Latest advisories

List the latest advisories across every tracked stack, newest first, without a package list. Filter by sector (js, stack, ai, crypto) and severity; by default the last 7 days and at most 20 advisories (days 1 to 30, limit 1 to 50). An empty list means nothing matched. To check your own packages, use get_advisories instead.

Input parameters:

- `days` (integer): How many days back, from 1 to 30. Default 7.
- `limit` (integer): How many advisories at most, from 1 to 50. Default 20.
- `section` (string): Sector: js (JS runtimes and frameworks), stack (hosting and data platforms), ai (AI SDKs and agent tools), crypto (web3 libraries). Omit for every sector.
- `severity` (string): Only this severity; watch is an announced change or upcoming fix. Omit for all.

### `get_platform_bulletins` (~113 tokens)

Platform bulletins

Get the security bulletins and announced changes of hosting and data platforms, which are not npm packages and never show in a lockfile: Vercel, Supabase, Neon and the other platforms of the platform parameter. Returns up to 50, newest first; omit platform for all of them. For npm packages, use get_advisories.

Input parameters:

- `platform` (string): One platform: vercel, supabase, cloudflare, railway, neon, postgres, clerk. Omit for every platform.

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-monowire-patchwire/patchwire#diagnostics

## Score history

- 2026-11-05: 74
- 2026-11-04: 74
- 2026-11-03: 73
- 2026-11-02: 77
- 2026-11-01: 77
- 2026-10-31: 76
- 2026-10-30: 76
- 2026-10-29: 75
- 2026-10-28: 75
- 2026-10-27: 75
- 2026-10-26: 74
- 2026-10-25: 69
- 2026-10-24: 69

## Common questions

### What is the Patchwire MCP server?

Patchwire is an MCP server listed in the public MCP registry as dev.monowire/patchwire. Hourly security advisories for JS, AI and web3 packages: ranges, fixes and exploit conditions. This page covers its hosted endpoint (https://patchwire.monowire.dev/mcp).

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

Patchwire scores 74 out of 100 on VerifyMCP. 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 Patchwire MCP server expose?

Patchwire exposes 5 tools: get_advisories, get_advisory, latest_safe, list_feed, get_platform_bulletins. Their descriptions and schemas cost roughly 888 tokens of context every time the server is loaded.

### Does the Patchwire MCP server require authentication?

No. We connected to Patchwire without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Patchwire MCP server still maintained?

Patchwire 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 did VerifyMCP test on the Patchwire MCP server?

VerifyMCP ran 12 checks on Patchwire, covering TLS certificate, Authorization, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Patchwire: HTTPS. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://patchwire.monowire.dev/mcp
- Website: https://patchwire.monowire.dev/agent
- Changelog RSS feed: https://verifymcp.io/servers/dev-monowire-patchwire/patchwire.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-monowire-patchwire/patchwire/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/dev-monowire-patchwire/patchwire.json
- HTML version of this page: https://verifymcp.io/servers/dev-monowire-patchwire/patchwire