# MCP Retrieval (oci · ghcr.io/role1776/mcp-retrieval:0.1.7)

Local Go MCP server: DuckDuckGo/Bing web + image search, readability scraping to Markdown.

- Trust score: 37/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-23

## Components

- mcpb · `mcp-retrieval_0.1.7_darwin_amd64.mcpb`: 13/100, [markdown](https://verifymcp.io/servers/role1776-mcp-retrieval/https-github-com-role1776-mcp-retrieval-releases-download-v0-1-7-mcp-retrieval-0.md), [page](https://verifymcp.io/servers/role1776-mcp-retrieval/https-github-com-role1776-mcp-retrieval-releases-download-v0-1-7-mcp-retrieval-0)
- mcpb · `mcp-retrieval_0.1.7_darwin_arm64.mcpb`: 13/100, [markdown](https://verifymcp.io/servers/role1776-mcp-retrieval/https-github-com-role1776-mcp-retrieval-releases-download-v0-1-7-mcp-retrieval-0-2.md), [page](https://verifymcp.io/servers/role1776-mcp-retrieval/https-github-com-role1776-mcp-retrieval-releases-download-v0-1-7-mcp-retrieval-0-2)
- mcpb · `mcp-retrieval_0.1.7_linux_amd64.mcpb`: 13/100, [markdown](https://verifymcp.io/servers/role1776-mcp-retrieval/https-github-com-role1776-mcp-retrieval-releases-download-v0-1-7-mcp-retrieval-0-3.md), [page](https://verifymcp.io/servers/role1776-mcp-retrieval/https-github-com-role1776-mcp-retrieval-releases-download-v0-1-7-mcp-retrieval-0-3)
- mcpb · `mcp-retrieval_0.1.7_linux_arm64.mcpb`: 13/100, [markdown](https://verifymcp.io/servers/role1776-mcp-retrieval/https-github-com-role1776-mcp-retrieval-releases-download-v0-1-7-mcp-retrieval-0-4.md), [page](https://verifymcp.io/servers/role1776-mcp-retrieval/https-github-com-role1776-mcp-retrieval-releases-download-v0-1-7-mcp-retrieval-0-4)
- mcpb · `mcp-retrieval_0.1.7_windows_amd64.mcpb`: 13/100, [markdown](https://verifymcp.io/servers/role1776-mcp-retrieval/https-github-com-role1776-mcp-retrieval-releases-download-v0-1-7-mcp-retrieval-0-5.md), [page](https://verifymcp.io/servers/role1776-mcp-retrieval/https-github-com-role1776-mcp-retrieval-releases-download-v0-1-7-mcp-retrieval-0-5)
- mcpb · `mcp-retrieval_0.1.7_windows_arm64.mcpb`: 13/100, [markdown](https://verifymcp.io/servers/role1776-mcp-retrieval/https-github-com-role1776-mcp-retrieval-releases-download-v0-1-7-mcp-retrieval-0-6.md), [page](https://verifymcp.io/servers/role1776-mcp-retrieval/https-github-com-role1776-mcp-retrieval-releases-download-v0-1-7-mcp-retrieval-0-6)
- oci · `ghcr.io/role1776/mcp-retrieval:0.1.7`: 37/100 (this document), [markdown](https://verifymcp.io/servers/role1776-mcp-retrieval/ghcr-io-role1776-mcp-retrieval-0-1-7.md), [page](https://verifymcp.io/servers/role1776-mcp-retrieval/ghcr-io-role1776-mcp-retrieval-0-1-7)

## Channel facts

- Registry: `oci`
- Package: `ghcr.io/role1776/mcp-retrieval:0.1.7`
- 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 2026-08-23.

- **Supply Chain Security**: 0/100
  - Malware scan not yet available for this package.
  - Known CVEs could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.
  - Install-script risk not yet assessed.
  - Dependency health could not be checked: this artifact ships no SBOM, so there is no dependency list to read. Publishing one would let us assess it.
- **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 5 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 67/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 760 tokens (~253/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **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.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 2 categories.** Categories scored 0 because we could not verify them: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

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

MCP Retrieval runs locally as a container image, launched with docker run --rm -i ghcr.io/role1776/mcp-retrieval:0.1.7. Ready-made configuration for Claude, Cursor, VS Code, Codex and 3 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add role1776-mcp-retrieval -- docker run --rm -i ghcr.io/role1776/mcp-retrieval:0.1.7
```

### Cursor

```json
{
  "mcpServers": {
    "role1776-mcp-retrieval": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/role1776/mcp-retrieval:0.1.7"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "role1776-mcp-retrieval": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/role1776/mcp-retrieval:0.1.7"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add role1776-mcp-retrieval -- docker run --rm -i ghcr.io/role1776/mcp-retrieval:0.1.7
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "role1776-mcp-retrieval": {
      "type": "local",
      "command": [
        "docker",
        "run",
        "--rm",
        "-i",
        "ghcr.io/role1776/mcp-retrieval:0.1.7"
      ],
      "enabled": true
    }
  }
}
```

### Hermes

```yaml
mcp_servers:
  role1776-mcp-retrieval:
    command: "docker"
    args: ["run", "--rm", "-i", "ghcr.io/role1776/mcp-retrieval:0.1.7"]
```

### Netclaw

```json
{
  "McpServers": {
    "role1776-mcp-retrieval": {
      "Transport": "stdio",
      "Command": "docker",
      "Arguments": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/role1776/mcp-retrieval:0.1.7"
      ]
    }
  }
}
```

### Other

```json
{
  "mcpServers": {
    "role1776-mcp-retrieval": {
      "command": "docker",
      "args": [
        "run",
        "--rm",
        "-i",
        "ghcr.io/role1776/mcp-retrieval:0.1.7"
      ]
    }
  }
}
```

## 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.

### 2026-08-17 (score 37)

First indexed and scored.

## MCP tools (3)

### `web_scrape` (~233 tokens)

Web scrape

Downloads pages by their links and returns the main text as markdown. Links are fetched in parallel; a single call handles up to 10 of them, so batch all links you need into one call instead of calling the tool per link.

Size: the 'max_chars' limit applies to each page separately, not to the whole response — 5 links stay under the limit each and the response holds all 5 texts. The limit counts characters, not tokens. A page cut short ends with '[truncated]' and its 'truncated' field is set; the cut-off part cannot be fetched afterwards, so treat what you got as all there is for that page.

Input parameters:

- `max_chars` (integer): truncate each page separately to N characters, default and maximum 20000; only lowers the limit, higher values are ignored
- `remove_links` (boolean): strip markdown links from the text
- `robots_txt` (boolean): respect the page robots.txt
- `timeout_ms` (integer): timeout for the whole call in milliseconds
- `urls` (null|array, required): links to pages, downloaded in parallel

Output parameters:

- `metadata` (object)
- `results` (null|array)

### `web_search` (~320 tokens)

Web search

Searches the web for one or more queries and returns snippets with links. Queries run in parallel. IMPORTANT: Always write search queries in English for best results and relevance. For images use the 'web_search_images' tool; both tools can be called in the same turn when a query needs text and images.

Freshness: set the 'date' field to restrict results by recency — 'd' (past day), 'w' (past week), 'm' (past month), 'y' (past year). Use it to prefer the most recent pages when the user asks about news or anything time-sensitive; leave it empty for all time.

Query operators (put them inside the query string itself): 'site:example.com term' limits the search to one site; 'filetype:pdf term' restricts to a file type; double quotes "exact phrase" force an exact match; a leading '-' excludes a word (term -foo); 'intitle:term' requires the word in the page title. Operators can be combined, e.g. 'site:arxiv.org filetype:pdf transformers'.

Input parameters:

- `date` (string): filter results by freshness: 'd' past day, 'w' past week, 'm' past month, 'y' past year; empty means all time
- `max_results` (integer): maximum number of snippets per query
- `queries` (null|array, required): search queries in English, executed in parallel
- `timeout_ms` (integer): timeout for the whole call in milliseconds

Output parameters:

- `metadata` (object)
- `results` (null|array)

### `web_search_images` (~207 tokens)

Web image search

Searches for images by one or more queries, executed in parallel. IMPORTANT: Queries must be in English ONLY.

Freshness: set the 'date' field to restrict results by recency — 'd' (past day), 'w' (past week), 'm' (past month), 'y' (past year); leave it empty for all time.

Query operators can be embedded in the query string: 'site:example.com term' limits to one site, double quotes "exact phrase" force an exact match, and a leading '-' excludes a word.

Input parameters:

- `date` (string): filter results by freshness: 'd' past day, 'w' past week, 'm' past month, 'y' past year; empty means all time
- `max_images` (integer): maximum number of images per query
- `queries` (null|array, required): queries in English for image search
- `timeout_ms` (integer): timeout for the whole call in milliseconds

Output parameters:

- `metadata` (object)
- `results` (null|array)

## Diagnostics

Captured diagnostic sections: Provenance. The full working is on the page: https://verifymcp.io/servers/role1776-mcp-retrieval/ghcr-io-role1776-mcp-retrieval-0-1-7#diagnostics

## Score history

- 2026-08-23: 37
- 2026-08-22: 37
- 2026-08-21: 37
- 2026-08-20: 37
- 2026-08-19: 37
- 2026-08-18: 37
- 2026-08-17: 37

## Common questions

### What is the MCP Retrieval server?

MCP Retrieval is listed in the public MCP registry as io.github.Role1776/mcp-retrieval. Local Go MCP server: DuckDuckGo/Bing web + image search, readability scraping to Markdown. This page covers its container image (ghcr.io/role1776/mcp-retrieval:0.1.7).

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

MCP Retrieval scores 37 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 MCP Retrieval server expose?

MCP Retrieval exposes 3 tools: web_scrape, web_search, web_search_images. Their descriptions and schemas cost roughly 760 tokens of context every time the server is loaded.

### Is the MCP Retrieval server still maintained?

MCP Retrieval is still listed as active in the MCP registry. We last reached this channel on 23 August 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 MCP Retrieval server under?

MCP Retrieval 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

- Repository: https://github.com/Role1776/mcp-retrieval
- Changelog RSS feed: https://verifymcp.io/servers/role1776-mcp-retrieval/ghcr-io-role1776-mcp-retrieval-0-1-7.xml
- Changelog JSON feed: https://verifymcp.io/servers/role1776-mcp-retrieval/ghcr-io-role1776-mcp-retrieval-0-1-7.json
- HTML version of this page: https://verifymcp.io/servers/role1776-mcp-retrieval/ghcr-io-role1776-mcp-retrieval-0-1-7