Home › Search & Research › nab
nab
Token-optimized HTTP client for LLMs: fetches any URL as clean markdown. CLI and MCP server.
Topics: Search & Data Extraction
Connect
Review any command before running it. Package names and URLs come from the server's own registry entry.
Package (cargo 0.12.6)
Package: cargo nab
NAB_SSRF_ALLOW_PRIVATE— Set to allow fetching private/internal IP addresses (corporate dashboards). Never unblocks loopback, link-local/cloud-metadata, or other always-denied ranges. Off by default.NAB_SSRF_ALLOWLIST— Comma-separated list of private IP/CIDR ranges to exempt from the SSRF guard (e.g. 10.252.0.0/16,192.168.1.5). Narrower, preferred alternative to NAB_SSRF_ALLOW_PRIVATE. Empty by default.NAB_WEBMCP_STRICT— Set to a truthy value to require fetched pages advertising a WebMCP manifest to match NAB_WEBMCP_OPT_IN before ingestion is allowed (defense against prompt injection via fetched content). Off by default.NAB_WEBMCP_OPT_IN— Comma-separated allowlist consulted when NAB_WEBMCP_STRICT is enabled. Empty by default.NAB_STATE_DIR— Overrides the directory used to persist session/cookie state (default: ~/.nab).NAB_KEYCHAIN_INTERACTION— Controls whether cookie extraction may prompt macOS Keychain for authorization. Set to 'never' in automated/headless callers so a background fetch cannot open a GUI dialog.NAB_OP_BIN— Path to the 1Password CLI binary used for credential retrieval during the login tool (default: op).NAB_MCP_CLI_BIN— Path to the mcp-cli binary used for MCP-based credential retrieval (default: mcp-cli).NAB_NO_TELEMETRY— Set to anything other than 0 or false to skip the daily heartbeat. NO_TELEMETRY and DO_NOT_TRACK do the same.NAB_TELEMETRY_ENDPOINT— Replace the daily heartbeat URL. An empty value leaves the default.
Related servers
modelcontextprotocol/servers
Direct local file system access.
wigolo
Local-first web intelligence MCP server for AI coding agents
exa-labs/exa-mcp-server
Connect AI agents to Exa for web search, content fetching, and multi-step research.
blazickjp/arxiv-mcp-server
Search arXiv papers, download full text, semantic search, citation graphs, and alerts via MCP.
trieve
Crawl, embed, chunk, search and retrieve information from datasets through Trieve.
brightdata-mcp
Bright Data's Web MCP server enabling AI agents to search, extract & navigate the web
Listed in punkpeye/awesome-mcp-servers (MIT)
Data from the Official MCP Registry