Web search that doesn't wreck your AI's memory.
Web search that doesn't wreck your AI's memory. Exposed over MCP by the mcp mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.
mcp-webgate is an MCP server that gives your AI clean, bounded web content — across all major AI clients: - IDEs: Claude Desktop, Claude Code, Zed, Cursor, Windsurf, VSCode - CLI Agents: Gemini CLI, Claude CLI, custom agents
webgate measures text in characters (not tokens). A rough conversion for English text:
Everything the assistant can do here goes through one of these:
Setup — base_url accepts any OpenAI-compatible endpoint: OpenAI, Ollama, LM Studio, vLLM, Together AI, Groq, and othersSummarization — When summarization_enabled = true, the LLM reads all fetched pages and writes a structured Markdown report with inline citations. Your AI receivesReranking — Results are always reranked by BM25 (keyword overlap, zero cost) before being returned. Optionally, the LLM can do a second pass for semanticYou will need 8 environment variables: WEBGATE_DEFAULT_BACKEND, WEBGATE_SEARXNG_URL, WEBGATE_LLM_ENABLED, WEBGATE_LLM_BASE_URL, WEBGATE_LLM_MODEL, WEBGATE_LLM_TIMEOUT, WEBGATE_DEBUG, WEBGATE_LOG_FILE. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.
Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. MCP's toolset — Setup, Summarization, Reranking — is a fair guide to whether it matches your workflow. It is maintained by annibale-x; worth a glance at recent repository activity before you build anything load-bearing on it.
This entry was verified against MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.
| Tool | What it does |
|---|---|
| Setup | base_url accepts any OpenAI-compatible endpoint: **OpenAI**, **Ollama**, **LM Studio**, **vLLM**, **Together AI**, **Groq**, and others. |
| Summarization | When summarization_enabled = true, the LLM reads all fetched pages and writes a structured Markdown report with inline citations. Your AI receives the report instead of the raw text. |
| Reranking | Results are always reranked by BM25 (keyword overlap, zero cost) before being returned. Optionally, the LLM can do a second pass for semantic relevance: |
{
"mcpServers": {
"webgate": {
"command": "uvx",
"args": ["mcp-webgate"],
"env": {
"WEBGATE_DEFAULT_BACKEND": "your-value",
"WEBGATE_SEARXNG_URL": "your-value",
"WEBGATE_LLM_ENABLED": "your-value",
"WEBGATE_LLM_BASE_URL": "your-value",
"WEBGATE_LLM_MODEL": "your-value",
"WEBGATE_LLM_TIMEOUT": "your-value",
"WEBGATE_DEBUG": "your-value",
"WEBGATE_LOG_FILE": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| WEBGATE_DEFAULT_BACKEND | Configuration value read at startup. | Optional |
| WEBGATE_SEARXNG_URL | Endpoint or connection string the server talks to. | Yes |
| WEBGATE_LLM_ENABLED | Configuration value read at startup. | Optional |
| WEBGATE_LLM_BASE_URL | Endpoint or connection string the server talks to. | Yes |
| WEBGATE_LLM_MODEL | Configuration value read at startup. | Optional |
| WEBGATE_LLM_TIMEOUT | Configuration value read at startup. | Optional |
| WEBGATE_DEBUG | Configuration value read at startup. | Optional |
| WEBGATE_LOG_FILE | Configuration value read at startup. | Optional |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.