webshift-mcp

Denoised web search MCP server — single static binary, zero runtime dependencies.

webshift-mcp exposes three MCP tools over stdio:

Built on top of the webshift library.

Installation

cargo install webshift-mcp

The binary is called mcp-webshift.

Quick start

1. Set up a search backend

The easiest option is SearXNG — free, self-hosted, no API key:

docker run -d -p 8080:8080 searxng/searxng

No Docker? Use a cloud backend — see Search backends.

2. Configure your MCP client

{
  "mcpServers": {
    "webshift": {
      "command": "mcp-webshift",
      "args": ["--default-backend", "searxng"]
    }
  }
}

That's it. Your AI agent now has web search with clean, budget-controlled text output.

For client-specific setup (Claude Desktop, Claude Code, Zed, Cursor, Windsurf, VS Code, Gemini CLI) see docs/integrations/.

MCP tool parameters

webshift_query

webshift_fetch

Configuration

Resolution order (highest priority first):

1. CLI args — --default-backend, --brave-api-key, etc.
2. Environment variables — WEBSHIFT_* prefix
3. Config file — webshift.toml (current dir, then ~/webshift.toml)
4. Built-in defaults

Config file (webshift.toml)

[server]
max_query_budget    = 32000   # total char budget across all sources
max_result_length   = 8000    # per-page char cap
max_total_results   = 20      # hard cap on results per call
max_download_mb     = 1       # streaming cap per page (MB)
search_timeout      = 8       # seconds
results_per_query   = 5
adaptive_budget     = "auto"  # "auto" | "on" | "off"

[backends]
default = "searxng"

[backends.searxng]
url = "http://localhost:8080"

[backends.brave]
api_key = "BSA-..."

[backends.tavily]
api_key = "tvly-..."

[backends.exa]
api_key = "..."

[backends.serpapi]
api_key = "..."
engine  = "google"

[backends.google]
api_key = "..."
cx      = "..."

[backends.bing]
api_key = "..."
market  = "en-US"

[llm]
enabled               = false
base_url              = "http://localhost:11434/v1"
model                 = "gemma3:27b"
expansion_enabled     = true
summarization_enabled = true

For the full configuration reference (all TOML keys, env vars, CLI args) see docs/CONFIGURATION.md.

Key CLI args

mcp-webshift \
  --default-backend searxng \
  --searxng-url http://localhost:8080 \
  --brave-api-key BSA-xxx \
  --google-api-key xxx --google-cx xxx \
  --bing-api-key xxx \
  --llm-enabled true \
  --llm-base-url http://localhost:11434/v1 \
  --llm-model gemma3:27b

Key environment variables

WEBSHIFT_DEFAULT_BACKEND=searxng
WEBSHIFT_SEARXNG_URL=http://localhost:8080
WEBSHIFT_BRAVE_API_KEY=BSA-xxx
WEBSHIFT_LLM_ENABLED=true
WEBSHIFT_LLM_BASE_URL=http://localhost:11434/v1
WEBSHIFT_LLM_MODEL=gemma3:27b

Search backends

LLM features (optional)

All opt-in — disabled by default. Works with any OpenAI-compatible API (OpenAI, Ollama, vLLM, LM Studio):

[llm]
enabled  = true
base_url = "http://localhost:11434/v1"
model    = "gemma3:27b"

Anti-flooding protections

Always active:

Links

• GitHub Repository — Source code and issues
• webshift library — Rust library crate
• Configuration Reference
• Use Cases & Examples
• IDE & Agent Integration Guides
• MCP Protocol

License

MIT License — see LICENSE for details.