Skip to main content
Glama

pit.world

Private search, and the front door to the Moshpit network.

An MCP server for private web search. pit mcp is a stdio Model Context Protocol server that gives any agent (Claude, Cursor, any MCP client) web search with no API key and no logging, plus Moshpit name lookups. It is in the official MCP Registry as world.pit/pit.

pit.world is a search engine that keeps nothing about you: no query logs, no cookies, no profile, no trackers, no JavaScript required. It is also where the Moshpit network lives in public: type a Moshpit name like chovy.hacker and it resolves through the registry, next to your web results.

# the web
https://pit.world/search?q=anything

# the CLI and TUI
bun add -g pitworld
pit search "private search engines"
pit resolve chovy.hacker
pit                      # interactive

# your agent
claude mcp add pit -- pit mcp

MCP server

claude mcp add pit -- bunx pitworld mcp
{ "mcpServers": { "pit": { "command": "bunx", "args": ["pitworld", "mcp"] } } }

Tools:

  • search: private web search (Google and Bing indexes, merged), returns titles, URLs and snippets.

  • moshpit_resolve: resolve a Moshpit name such as chovy.hacker to where it points.

  • moshpit_network: live numbers for the Moshpit network.

No key is needed. PIT_URL points it at another pit.world instance (default https://pit.world).

Related MCP server: qsearch

What it does

  • Web search, privately. Your browser talks only to pit.world. pit.world asks the Google index (through Serper) and the Bing index (through DataForSEO) at the same time, merges the two lists, and tags each result with the engine that found it. The providers get the words, never your IP, browser, cookies or referrer. Linkup, Exa and Perplexity are fallbacks if both fail.

  • Moshpit names. A query that looks like label.ending is checked against the Moshpit registry, and a registered name gets a card with where it points.

  • Bangs. !gh hqtui, rust lifetimes !so, !pit chovy.hacker: straight to that site's search, without a referrer. The full list is at pit.world/about#bangs.

  • Default search engine. OpenSearch description at /opensearch.xml, suggestions at /suggest, and https://pit.world/search?q=%s for any browser.

Privacy, by construction

  • nginx writes no access log for the site (ACCESS_LOG=off in bin/install.conf), and the app logs nothing per request.

  • No cookies. The server strips Set-Cookie from every response.

  • Rate limiting keys on an HMAC of the IP under a secret regenerated every hour, in memory only.

  • Identical searches are cached in memory for ten minutes to avoid paying twice; the cache holds words and results, nothing about who asked, and never touches disk.

  • Strict CSP (default-src 'none', same-origin scripts and styles only), Referrer-Policy: no-referrer, results link straight to the site.

The page says the same in plain words: pit.world/privacy.

API

GET /api/search?q=…&n=10

{ query, provider, cached, results: [{ url, title, description, host }], moshpit }

GET /api/resolve?name=chovy.hacker

the registry's answer for a Moshpit name

GET /api/network

endings claimed, registry events, recent claims, endings for sale

GET /api/bangs

every bang

No key. Rate limited per visitor (429 with Retry-After).

Surfaces

The house rule: everything ships a TUI, a CLI, an MCP and an API.

Web + API

bun src/server.ts (PORT, HOST; provider keys SERPER_API_KEY, DATAFORSEO_LOGIN + DATAFORSEO_PASSWORD (Bing), LINKUP_API_KEY, EXA_API_KEY, PERPLEXITY_API_KEY)

CLI

pit search, pit resolve, pit network, pit open

TUI

pit

MCP

pit mcp: tools search, moshpit_resolve, moshpit_network. In the official MCP Registry as world.pit/pit (server.json)

PWA

installable from any browser (/manifest.webmanifest, share target into /search); the worker in public/sw.js caches the static shell and an offline page, never a search

The CLI, TUI and MCP talk to https://pit.world (or PIT_URL), so they need no keys.

Run your own

git clone https://github.com/moshcoder/pit.world && cd pit.world
bun install
SERPER_API_KEY=… bun src/server.ts        # http://127.0.0.1:8787

Production runs on bare metal with bin/install.sh (OpenInstall): nginx + Let's Encrypt + a systemd unit running bun.

The Moshpit network

Moshpit is a namespace beside ICANN's. Anyone can claim an ending (.hacker, .eggs, .pit), put names under it and point them anywhere; the registry is open and append-only, and it signs certificates, so the names are real HTTPS sites to anyone on the network. Get on it with moshcode (curl -fsSL https://moshcoding.com/install.sh | sh, then moshcode dns enable) or by setting your browser's secure DNS to https://dns.moshcode.sh/dns-query. Every method (moshcode, TronBrowser, browser DoH, an Apple profile, Windows, Android) and how to trust the Moshpit Root CA is at pit.world/connect; pit.world serves the root at /moshpit-root-ca.crt and the Apple profile at /moshpit.mobileconfig. Claim an ending at pit.moshcode.sh.

License

MIT

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to perform web searches with full content retrieval and multi-engine provenance, including trust scoring and local corpus persistence, via MCP integration.
    1 npm
    3
    Apache 2.0
  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI agents to perform live web searches across 9 engines, scrape web pages into clean formats, and run agentic research with citations via MCP.
    115 PyPI
    3
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to perform local-first web search, fetch, crawl, extract, cache, research, and autonomous information gathering through MCP, with no API keys or cloud dependencies.
    677 npm
    AGPL 3.0