pulsemcp verified Safe content atomic mcp-remote

Exa Search

This MCP server provides intelligent discovery and research of Model Context Protocol servers using Exa AI search, enabling AI assistants to find relevant MCPs based on user requirements, analyze their features and categories, and get detailed information about specific implementations. Built by Hari Ayappane using Python with FastMCP and the Exa search API, it features automated relevance scoring that identifies MCP-specific content, repository extraction from GitHub and other platforms, categorization by functionality (database, web APIs, file system, etc.), and tools for finding similar MCPs and asking direct questions about the MCP ecosystem. The implementation includes confidence scoring to rank results, feature extraction from documentation, and structured recommendations with installation notes, making it valuable for developers discovering existing MCP tools for specific use cases, researchers exploring the MCP ecosystem, and anyone needing to quickly identify the most relevant MCP servers for their particular requirements without manually searching through repositories.

Cognium trust score

90%

Tier

Verified

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: database
Source: PulseMCP
Repository: github.com/haran2001/mcp-search-server
Author type: human
Last scanned: 2026-09-28
Updated: 2026-09-28

View source Find related skills

MCP

Resolve Exa 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

Swap --scope user for --scope project to commit it to .mcp.json.

Your client Same endpoint everywhere; only the config key differs. The full list is in the descriptor.

Claude Desktop · Settings → Connectors → Add custom connector

https://api.skillsregistry.net/mcp

Paste the URL as the connector endpoint. No authentication.

ChatGPT · Settings → Connectors → Create (developer mode) → MCP server URL

https://api.skillsregistry.net/mcp

Authentication: none. Works in chat and deep research — the server exposes the connector search and fetch tools.

Codex CLI · ~/.codex/config.toml

[mcp_servers.skillsregistry]
url = "https://api.skillsregistry.net/mcp"