MCPExplorer

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Search, vet & assemble MCP servers from your agent: verified tools, risk labels, and trust scores.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "MCPExplorer": {
      "url": "https://mcpexplorer.com/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (14)

• 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.

  Parameters:

  • limit — integer — Max results (default 10)
  • query — string — Free-text query, e.g. 'send email' or 'postgres'. Omit to browse the full index ranked by trust.
  • transport — string — Filter by transport. Many servers are still 'unknown' (transport not yet probed by the crawler).
  • capability — string — Filter to servers providing a capability slug, e.g. 'send-email'. An unknown slug is reported in ignored_filters, not silently dropped.
  • risk_level — string — Filter by tool risk. 'read-only' = has tools and none are write/destructive — the safe set to hand an autonomous agent.
  • official_status — string — Filter by provenance

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_server

  Fetch the full record for one MCP server by slug: install methods, tools, trust, verification, and provenance.

  Parameters:

  • slug (required) — string — Server slug, e.g. 'github'

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_capability

  List the best MCP servers that provide a capability (e.g. 'send-email', 'web-search'), ranked by trust.

  Parameters:

  • slug (required) — string — Capability slug, e.g. 'send-email'

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• compare_servers

  Compare two MCP servers side by side: trust, transport, tools, install, and links.

  Parameters:

  • a (required) — string — First server slug
  • b (required) — string — Second server slug

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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).

  Parameters:

  • slug (required) — string — Server slug
  • runtime (required) — string — Runtime slug, e.g. 'claude-desktop'

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• check_trust

  Return the explainable trust score, label, scoring reasons, and verification history for an MCP server.

  Parameters:

  • slug (required) — string — Server slug

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• get_alternatives

  Find verified MCP servers with the same capabilities as a given server, ranked by trust.

  Parameters:

  • slug (required) — string — Server slug

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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.

  Parameters:

  • slug (required) — string — Loadout slug, e.g. 'gtm', 'coding', 'research'

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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.

  Parameters:

  • limit — integer — Max capabilities (default 30)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• 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.

  Parameters:

  • goal (required) — string — What the agent should do, in plain language, e.g. 'triage support tickets and file bugs'.
  • limit — integer — Max assembled servers (default 6).
  • risk_tolerance — string — 'read-only' restricts the assembled set to servers with no write/destructive tools — the safe set for an unsupervised agent. Default 'any'.

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

• report_broken_server

  Report that an MCP server's install, docs, or endpoint is broken. Creates a submission for editorial review.

  Parameters:

  • slug (required) — string — Server slug
  • detail (required) — string — What's broken (install fails, endpoint down, docs wrong, …)

  Hints: read-only not declared · destructive not declared · idempotent not declared · open-world not declared

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.