Brave Search
This Brave Search MCP server, developed by Arben Ademi, integrates the Model Context Protocol with the Brave Search API. Built with Python and leveraging libraries like FastMCP and HTTPX, it enables AI agents to perform web searches and local business lookups through natural language queries. The implementation focuses on providing a streamlined interface to Brave's privacy-respecting search capabilities, offering tools for general web searches and geographically-targeted local searches. It's particularly useful for AI assistants and applications needing up-to-date web information or location-based data, enabling use cases such as research assistance, fact-checking, and local recommendations without directly interacting with the Brave Search API.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- ai-ml
- Source
- PulseMCP
- Repository
- github.com/arben-adm/brave-mcp-search
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Brave Search from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.