MCPサーバー

MCP Surface Lint

io.github.DLeibner/mcp-surface-lint

このMCPでできること

Audits MCP tool definitions for token cost, schema quality, and interface design issues.

check_mcp_server
Check MCP server
Statically audit an MCP tool surface from a public HTTPS URL or tools/list snapshot. Returns deterministic scores and findings without invoking any target tool or making LLM calls. When the user asks to check another installed MCP server, read that server's complete tool definitions from client context and pass them as snapshot (MCP `name` or Cursor-style `tool` both work; do not use file paths or $ref). If those definitions are unavailable, ask the user for its public endpoint or tools/list JSON instead of inventing an audit.
読み取り専用 外部アクセスあり 冪等
入力スキーマ
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'properties': {'url': {'type': 'string', 'format': 'uri', 'description': 'Public HTTPS Streamable HTTP MCP endpoint to inspect.'}, 'headers': {'type': 'object', 'description': 'Optional HTTP headers sent only while reading the remote tools/list response.', 'additionalProperties': {'type': 'string'}}, 'snapshot': {'description': "A tools/list JSON response, MCP Surface Lint snapshot, or client tool dump containing a tools array. Each tool needs `name`, or the Cursor-style `tool` alias. Forward another installed server's complete tool definitions here — do not invent schemas."}}, 'additionalProperties': False}
出力スキーマ
{'type': 'object', '$schema': 'http://json-schema.org/draft-07/schema#', 'required': ['staticAnalysis', 'targetToolsInvoked', 'grade', 'server', 'source', 'stats', 'scores', 'findingCounts', 'findings'], 'properties': {'grade': {'enum': ['A', 'B', 'C', 'D', 'F'], 'type': 'string'}, 'stats': {'type': 'object', 'required': ['toolCount', 'approxTokens', 'encoding'], 'properties': {'encoding': {'type': 'string'}, 'toolCount': {'type': 'integer', 'minimum': 0}, 'approxTokens': {'type': 'integer', 'minimum': 0}}, 'additionalProperties': False}, 'scores': {'type': 'object', 'required': ['composite', 'categories'], 'properties': {'composite': {'type': 'integer', 'maximum': 100, 'minimum': 0}, 'categories': {'type': 'object', 'required': ['surface', 'naming', 'descriptions', 'schemas', 'annotations', 'design'], 'properties': {'design': {'type': 'integer', 'maximum': 100, 'minimum': 0}, 'naming': {'type': 'integer', 'maximum': 100, 'minimum': 0}, 'schemas': {'type': 'integer', 'maximum': 100, 'minimum': 0}, 'surface': {'type': 'integer', 'maximum': 100, 'minimum': 0}, 'annotations': {'type': 'integer', 'maximum': 100, 'minimum': 0}, 'descriptions': {'type': 'integer', 'maximum': 100, 'minimum': 0}}, 'additionalProperties': False}}, 'additionalProperties': False}, 'server': {'type': 'object', 'properties': {'name': {'type': 'string'}, 'version': {'type': 'string'}}, 'additionalProperties': False}, 'source': {'type': 'string'}, 'findings': {'type': 'array', 'items': {'type': 'object', 'required': ['ruleId', 'message', 'severity', 'category', 'docsUrl'], 'properties': {'path': {'type': 'string'}, 'ruleId': {'type': 'string'}, 'docsUrl': {'type': 'string'}, 'message': {'type': 'string'}, 'category': {'enum': ['surface', 'naming', 'descriptions', 'schemas', 'annotations', 'design'], 'type': 'string'}, 'evidence': {'type': 'string'}, 'severity': {'enum': ['error', 'warn', 'info'], 'type': 'string'}, 'toolName': {'type': 'string'}}, 'additionalProperties': False}}, 'findingCounts': {'type': 'object', 'required': ['bySeverity', 'byCategory'], 'properties': {'byCategory': {'type': 'object', 'required': ['surface', 'naming', 'descriptions', 'schemas', 'annotations', 'design'], 'properties': {'design': {'type': 'integer', 'minimum': 0}, 'naming': {'type': 'integer', 'minimum': 0}, 'schemas': {'type': 'integer', 'minimum': 0}, 'surface': {'type': 'integer', 'minimum': 0}, 'annotations': {'type': 'integer', 'minimum': 0}, 'descriptions': {'type': 'integer', 'minimum': 0}}, 'additionalProperties': False}, 'bySeverity': {'type': 'object', 'required': ['error', 'warn', 'info'], 'properties': {'info': {'type': 'integer', 'minimum': 0}, 'warn': {'type': 'integer', 'minimum': 0}, 'error': {'type': 'integer', 'minimum': 0}}, 'additionalProperties': False}}, 'additionalProperties': False}, 'staticAnalysis': {'type': 'boolean', 'const': True}, 'targetToolsInvoked': {'type': 'boolean', 'const': False}}, 'additionalProperties': False}
変更
check_mcp_server
2026年9月23日2:43
追加
check_mcp_server
2026年9月17日12:41

hyperion

com.thetempleofdoom.hyperion/hyperion

Acts as a paid MCP tool marketplace and utility gateway with server discovery, HTTP and JavaScript tools, research, data conversi…

XGR MCP Gateway

io.github.xgr-network/xdala-workflow-builder

Provides an MCP gateway for XGRChain and XDaLa workflows, including blockchain explorer queries, session inspection, transaction …

aaaa-nexus — Formally Verified AI Safety APIs

io.github.atomadictech/aaaa-nexus

Provides formally constrained agent safety and governance APIs for tool authorization, prompt-injection-resistant execution, iden…

Slid Phi Labs

io.github.ceedot-rock/slid-phi-labs

Provides searchable catalogs and documentation for agent services, issues agent API keys, exposes x402-purchasable SKUs, and offe…

AgentResolver — Agent Commerce Health Monitoring

io.github.waxsway/agentresolver

Resolves missing agent capabilities and provides MCP and HTTP endpoint checks, tool compatibility analysis, OpenAPI selection, en…

Aziel Runtime

io.github.AzielEliab/aziel-runtime

Provides a governed MCP runtime with registry discovery, controlled tool execution, provenance receipts, integrity checks, memory…

agent-exec

io.sslip.128.221.67.45.agent-exec/agent-exec

Provides pay-per-use sandbox code execution, temporary storage, distributed locks, attestations, durable watches, and process han…

HeyClaude — Claude & AI workflow directory

io.github.JSONbored/heyclaude

Searches and evaluates a registry of Claude Code agents, MCP servers, skills, and tools, providing entry details, compatibility, …