Mithrandir — free MCP gateway test
Observe MCP tools, verify repeated reads, then try bounded exact reuse for free.
使うべきか
品質と安全性
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": {
"mithrandir": {
"url": "https://mithrandir-production.up.railway.app/mcp"
}
}
}リモートエンドポイント
https://mithrandir-production.up.railway.app/mcpstreamable-httpできること
ツール一覧
ツール（3）
🟢mithrandir_demo(scenario)
Run a free isolated synthetic Reuse Autopilot demonstration. No production account, upload, payment or private data is used. Compare unchanged, one-partition-changed and missing-source behavior before onboarding.
入力スキーマ
{
"type": "object",
"properties": {
"scenario": {
"enum": [
"unchanged",
"one_partition_changed",
"missing_source"
],
"default": "one_partition_changed"
}
},
"required": [],
"additionalProperties": false
}🔴mithrandir_gateway_trial_start(name, upstream_url, policy_version, accept_terms, cache_ttl_seconds, ...)
Start a bounded free gateway test. Connect your public HTTPS MCP server, then approve safe reads and verify repetition before free Optimize activation.
入力スキーマ
{
"type": "object",
"properties": {
"name": {
"type": "string",
"pattern": "^[A-Za-z0-9_.-]{1,80}$"
},
"upstream_url": {
"type": "string",
"minLength": 12,
"maxLength": 1000
},
"policy_version": {
"type": "string",
"minLength": 1,
"maxLength": 80
},
"accept_terms": {
"const": true
},
"cache_ttl_seconds": {
"type": "integer",
"minimum": 30,
"maximum": 86400,
"default": 300
},
"safe_read_tools": {
"type": "array",
"items": {
"type": "string",
"pattern": "^[A-Za-z0-9_.:/-]{1,160}$"
},
"maxItems": 100,
"default": []
},
"tool_costs_microusd": {
"type": "object",
"additionalProperties": {
"type": "integer",
"minimum": 0,
"maximum": 1000000000000
},
"default": {}
},
"min_shadow_matches": {
"type": "integer",
"minimum": 1,
"maximum": 20,
"default": 2
},
"idempotency_key": {
"type": "string",
"minLength": 32,
"maxLength": 128
}
},
"required": [
"name",
"upstream_url",
"policy_version",
"accept_terms",
"idempotency_key"
],
"additionalProperties": false
}🟢mithrandir_security_profile
Free machine-readable description of the v17 Cognitive Membrane trust model: origin-bound authority, task-scoped exact-call capabilities, replay protection, egress control and two-phase effectful actions. This is a security contract description, not proof that a deployment is vulnerability-free.
入力スキーマ
{
"type": "object",
"properties": {},
"required": [],
"additionalProperties": false
}コミュニティ
エビデンス