# io.github.VelvetSP/web-retrieval-mcp

> io.github.VelvetSP/web-retrieval-mcp — velvetsp-web-retrieval-mcp. Use this tool when you need to enhance AI agents' web search capabilities with a secure and reliable MCP server, providing neural web search and tiered web fetch to solve problems related to information retrieval and provenance preservation. It accepts queries as input and returns relevant search results as output, serving as a drop-in replacement for built-in web tools. Ideal for use cases requiring robust and secure web data retrieval, such as research, data mining, and knowledge graph construction.

Canonical page: https://skillsregistry.net/skills/velvetsp-web-retrieval-mcp  
JSON: https://api.skillsregistry.net/v1/skills/velvetsp-web-retrieval-mcp

## Description

An open-source MCP server providing AI agents with neural web search via Exa and tiered web fetch (Exa, local browser, Firecrawl) as a drop-in replacement for built-in web tools, preserving provenance and guarding against SSRF.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/cflpgq7e06)
- **Repository:** <https://github.com/VelvetSP/web-retrieval-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "velvetsp-web-retrieval-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/velvetsp-web-retrieval-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/velvetsp-web-retrieval-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt