MCPExplorer
Search, vet & assemble MCP servers from your agent: verified tools, risk labels, and trust scores.
使うべきか
品質と安全性
検出事項（5）
- HIGHTool description contains system tag or markerget_ecosystem_stats 内
- HIGHTool poisoning patterns detected
- LOWTool 'compare_servers' description lacks action verbcompare_servers 内
- LOWTool 'check_trust' description lacks action verbcheck_trust 内
- LOWTool 'get_ecosystem_stats' description lacks action verbget_ecosystem_stats 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"mcpexplorer": {
"url": "https://mcpexplorer.com/mcp"
}
}
}リモートエンドポイント
https://mcpexplorer.com/mcpstreamable-httpできること
ツール一覧
ツール（14）
🟢search_servers(query, official_status, transport, risk_level, capability, ...)
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.
入力スキーマ
{
"type": "object",
"properties": {
"query": {
"type": "string",
"description": "Free-text query, e.g. 'send email' or 'postgres'. Omit to browse the full index ranked by trust."
},
"official_status": {
"type": "string",
"enum": [
"official",
"partner",
"community",
"unknown"
],
"description": "Filter by provenance"
},
"transport": {
"type": "string",
"enum": [
"stdio",
"sse",
"streamable_http",
"websocket",
"unknown"
],
"description": "Filter by transport. Many servers are still 'unknown' (transport not yet probed by the crawler)."
},
"risk_level": {
"type": "string",
"enum": [
"read-only",
"read",
"write",
"destructive"
],
"description": "Filter by tool risk. 'read-only' = has tools and none are write/destructive — the safe set to hand an autonomous agent."
},
"capability": {
"type": "string",
"description": "Filter to servers providing a capability slug, e.g. 'send-email'. An unknown slug is reported in ignored_filters, not silently dropped."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 50,
"description": "Max results (default 10)"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_server(slug)
Fetch the full record for one MCP server by slug: install methods, tools, trust, verification, and provenance.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Server slug, e.g. 'github'"
}
},
"required": [
"slug"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_capability(slug)
List the best MCP servers that provide a capability (e.g. 'send-email', 'web-search'), ranked by trust.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Capability slug, e.g. 'send-email'"
}
},
"required": [
"slug"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪compare_servers(a, b)
Compare two MCP servers side by side: trust, transport, tools, install, and links.
入力スキーマ
{
"type": "object",
"properties": {
"a": {
"type": "string",
"description": "First server slug"
},
"b": {
"type": "string",
"description": "Second server slug"
}
},
"required": [
"a",
"b"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪generate_runtime_config(slug, runtime)
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).
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Server slug"
},
"runtime": {
"type": "string",
"description": "Runtime slug, e.g. 'claude-desktop'"
}
},
"required": [
"slug",
"runtime"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢check_trust(slug)
Return the explainable trust score, label, scoring reasons, and verification history for an MCP server.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Server slug"
}
},
"required": [
"slug"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_alternatives(slug)
Find verified MCP servers with the same capabilities as a given server, ranked by trust.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Server slug"
}
},
"required": [
"slug"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢list_loadouts
List curated loadouts — deliberately-assembled kits of MCP servers + governance + plays for a specific job (GTM, coding, research, support, infra). The agent-facing version of the /loadouts product. Use get_loadout for the full kit with live trust.
入力スキーマ
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢get_loadout(slug)
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.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Loadout slug, e.g. 'gtm', 'coding', 'research'"
}
},
"required": [
"slug"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢list_capabilities(limit)
List the capability slugs an agent can filter or look up by (e.g. 'send-email', 'query-database'), most-populated first. Use these with get_capability or search_servers' capability filter — the taxonomy isn't guessable.
入力スキーマ
{
"type": "object",
"properties": {
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 100,
"description": "Max capabilities (default 30)"
}
},
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢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.
入力スキーマ
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟢list_runtimes
List the runtimes generate_runtime_config supports (Claude Desktop, Cursor, VS Code, agent frameworks, …), with each one's config path. Enumerate these instead of guessing runtime slugs.
入力スキーマ
{
"type": "object",
"properties": {},
"$schema": "http://json-schema.org/draft-07/schema#"
}🟡plan_toolset(goal, risk_tolerance, limit)
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.
入力スキーマ
{
"type": "object",
"properties": {
"goal": {
"type": "string",
"minLength": 3,
"description": "What the agent should do, in plain language, e.g. 'triage support tickets and file bugs'."
},
"risk_tolerance": {
"type": "string",
"enum": [
"any",
"read-only"
],
"description": "'read-only' restricts the assembled set to servers with no write/destructive tools — the safe set for an unsupervised agent. Default 'any'."
},
"limit": {
"type": "integer",
"minimum": 1,
"maximum": 10,
"description": "Max assembled servers (default 6)."
}
},
"required": [
"goal"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}⚪report_broken_server(slug, detail)
Report that an MCP server's install, docs, or endpoint is broken. Creates a submission for editorial review.
入力スキーマ
{
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "Server slug"
},
"detail": {
"type": "string",
"maxLength": 1000,
"description": "What's broken (install fails, endpoint down, docs wrong, …)"
}
},
"required": [
"slug",
"detail"
],
"additionalProperties": false,
"$schema": "http://json-schema.org/draft-07/schema#"
}コミュニティ
エビデンス