MCPExplorer MCP server
The trust and capability graph for MCP servers — as an MCP server.
MCPExplorer indexes MCP servers, extracts their tools and auth scopes, verifies health in a sandbox, and scores trust with explainable reasons. This is that whole graph exposed as an MCP server — not just lookup, but a decision layer: your agent can find a trustworthy server for any capability, plan a whole governed toolset from a plain-language goal, generate the exact install config for its runtime, and check trust and risk before wiring anything up.
Who it’s for: Agents and agent builders who want to discover, vet, assemble, and install other MCP servers programmatically — without leaving the loop.
Remote MCP server (Streamable HTTP).
The real tool surface, each labeled by risk. Full trust breakdown on the server page · safety review: Is MCPExplorer MCP safe?.
| Tool | Risk |
|---|---|
| list_runtimes List the runtimes generate_runtime_config supports (Claude Desktop, Cursor, VS Code, agent frameworks, …), with each one's config path. Enumerate these instead of guessing runtime slugs. | read |
| get_alternatives Find verified MCP servers with the same capabilities as a given server, ranked by trust. | read |
| get_server Fetch the full record for one MCP server by slug: install methods, tools, trust, verification, and provenance. | read |
| report_broken_server Report that an MCP server's install, docs, or endpoint is broken. Creates a submission for editorial review. | unknown |
| list_loadouts List curated loadouts — deliberately-assembled kits of MCP servers + governance + plays for a specific job (GTM, coding, research, support, infra). The agent-facing version of the /loadouts product. Use get_loadout for the full kit with live trust. | read |
| compare_servers Compare two MCP servers side by side: trust, transport, tools, install, and links. | unknown |
| get_ecosystem_stats Live snapshot of the indexed MCP ecosystem: totals (servers, tools, handshake-verified), provenance and transport breakdowns, and the current top-trust / most-adopted / newest / biggest-trust-riser servers. | read |
| list_capabilities List the capability slugs an agent can filter or look up by (e.g. 'send-email', 'query-database'), most-populated first. Use these with get_capability or search_servers' capability filter — the taxonomy isn't guessable. | read |
| get_loadout Fetch one curated loadout: its servers (each with role + LIVE trust/transport/tool-risk from the index), an aggregated governance posture for the whole kit, and the plays (see→decide→act sequences) it's designed to run. | read |
| get_capability List the best MCP servers that provide a capability (e.g. 'send-email', 'web-search'), ranked by trust. | read |
| generate_runtime_config Generate the install + client config for an MCP server in a given runtime (claude-desktop, cursor, vscode, windsurf, cline, continue, goose, openai-agents, langgraph, crewai). | unknown |
| check_trust Return the explainable trust score, label, scoring reasons, and verification history for an MCP server. | unknown |
| plan_toolset Turn a plain-language goal into a recommended, governed toolset: the best-fit curated loadout (matched transparently by goal terms) plus an assembled set of the most relevant indexed servers, each with LIVE trust and tool-risk, and an aggregate governance posture for the kit. The decision layer over search/capability/trust/loadouts. | read |
| search_servers Search the MCPExplorer index of MCP servers by free text and filters. Omit `query` to browse the whole index ranked by trust score. Every filter either applies or is echoed back in `ignored_filters` with a reason — filters never silently do nothing. | read |
The write/destructive access this server can exercise, from its verified tools.
What is MCPExplorer MCP?
MCPExplorer indexes MCP servers, extracts their tools and auth scopes, verifies health in a sandbox, and scores trust with explainable reasons. This is that whole graph exposed as an MCP server — not just lookup, but a decision layer: your agent can find a trustworthy server for any capability, plan a whole governed toolset from a plain-language goal, generate the exact install config for its runtime, and check trust and risk before wiring anything up.
Who is MCPExplorer for?
Agents and agent builders who want to discover, vet, assemble, and install other MCP servers programmatically — without leaving the loop.
What tools does MCPExplorer expose?
MCPExplorer exposes 14 verified tools, including list_runtimes, get_alternatives, get_server, report_broken_server, list_loadouts, compare_servers. Each is labeled by read / write / destructive risk on this page.
How do I connect MCPExplorer to my agent?
MCPExplorer is a remote MCP server at https://mcpexplorer.com/mcp. Add it in Claude, Cursor, or any MCP client — for example: claude mcp add --transport http mcpexplorer https://mcpexplorer.com/mcp.
Is MCPExplorer verified on MCPExplorer?
Yes — MCPExplorer is hand-checked and featured on MCPExplorer. We pull its real tool surface, required scopes, and risk labels from the live index so you can see exactly what it does before connecting.
Other MCP servers worth a look.
MCPExplorer is featured on MCPExplorer. Add this badge to MCPExplorer’s site or README — it links back to this page.
HTML — for your website
Markdown — for a README
Set up MCPExplorer and put it to work. Or see its full verified profile.