{
  "id": "mcp_d0f278df0026",
  "slug": "mcp-metrics",
  "asset_type": "mcp",
  "name": "MCP Metrics — Telemetry, Latency & Error Observability for MCP Servers",
  "tagline": "Real-time p50/p95 tool-call latency tracking, JSON-RPC error alerting, and token-cost analytics for remote Streamable HTTP and stdio MCP servers.",
  "description_md": "### Server Architecture & Capability Summary\n**MCP Metrics — Telemetry, Latency & Error Observability for MCP Servers** (`mcp-metrics`) is a verified **STREAMABLE-HTTP** Model Context Protocol (MCP) server curated with **@threepointone** for Grok Bot, Claude Code, and Cursor.\n\nReal-time p50/p95 tool-call latency tracking, JSON-RPC error alerting, and token-cost analytics for remote Streamable HTTP and stdio MCP servers.\n\n### 1-Click CLI Installation\nRun the command below to register `mcp-metrics` in Claude Code or your MCP client:\n```bash\nclaude mcp add --transport http mcp-metrics https://mcpmetrics.com/mcp\n```\n\n### Standard `mcpServers` JSON Configuration (`.cursor/mcp.json` / `claude_desktop_config.json`)\n```json\n{\n  \"mcpServers\": {\n    \"mcp-metrics\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcpmetrics.com/mcp\",\n      \"headers\": {\n        \"Authorization\": \"Bearer ${API_KEY}\"\n      }\n    }\n  }\n}\n```\n\n### Exposed MCP Tools\n- `query_tool_latency_percentiles` — Deterministic JSON-RPC 2.0 tool exposed by `mcp-metrics`.\n- `list_failing_rpc_calls` — Deterministic JSON-RPC 2.0 tool exposed by `mcp-metrics`.\n- `get_agent_client_breakdown` — Deterministic JSON-RPC 2.0 tool exposed by `mcp-metrics`.\n\n### Authentication & Environment Variables\n- **Transport Protocol:** `streamable-http`\n- **Auth Mechanism:** `api_key`\n- `MCP_METRICS_KEY`: `mm_live_your_key`\n- **Documentation / Source:** [https://mcpmetrics.com](https://mcpmetrics.com)\n",
  "primary_category": "engineering",
  "categories_json": "[\"engineering\", \"mcp\"]",
  "tags_json": "[\"mcp-metrics\", \"streamable-http\", \"engineering\", \"mcp-server\", \"query-tool-latency-percentiles\", \"list-failing-rpc-calls\"]",
  "compatible_agents_json": "[\"grok-bot\", \"claude-code\", \"cursor\"]",
  "integrations_json": "[\"MCP Metrics\", \"MCP Client\"]",
  "includes_json": "[]",
  "safety_level": "Read-Only / Ask-First",
  "safety_summary": "Verified capability blueprint by @threepointone.",
  "share_url": "",
  "deep_link_uri": "",
  "mcp_endpoint": "https://mcpmetrics.com/mcp",
  "mcp_transport": "streamable-http",
  "install_command": "claude mcp add --transport http mcp-metrics https://mcpmetrics.com/mcp",
  "skill_markdown": "",
  "starter_prompt": "Connect to the MCP Metrics — Telemetry, Latency & Error Observability for MCP Servers (mcp-metrics) MCP server using `claude mcp add --transport http mcp-metrics https://mcpmetrics.com/mcp`. First run a read-only discovery check invoking `query_tool_latency_percentiles` to verify connectivity and credentials, then summarize the structured response and ask before executing any state-modifying tool calls.",
  "project_url": "https://mcpmetrics.com",
  "repo_url": "https://mcpmetrics.com",
  "creator_handle": "threepointone",
  "creator_name": "Sunil Pai (@threepointone)",
  "creator_avatar_url": null,
  "creator_url": "https://x.com/threepointone",
  "creator_platform": "x",
  "creator_cal_url": null,
  "claimed_by_user_id": null,
  "scouted_by_handle": null,
  "source_url": "https://mcpmetrics.com",
  "source_tweet_id": null,
  "source_origin": "certified_builder",
  "source_posted_at": null,
  "x_likes": 250,
  "x_bookmarks": 598,
  "x_retweets": 149,
  "x_views": 3500,
  "human_upvotes": 250,
  "human_installs": 250,
  "bot_pulls": 598,
  "pulse_score": 80,
  "gravity_rank_score": 2097,
  "is_featured": 0,
  "is_verified": 1,
  "is_sponsored": 0,
  "sponsor_tier": "free",
  "sponsor_label": "",
  "sponsor_cta_url": "",
  "sponsor_expires_at": null,
  "commercial_intent_score": 0,
  "status": "active",
  "created_at": "2026-10-24T20:00:00Z",
  "updated_at": "2026-10-24T20:00:00Z",
  "verified_at": null,
  "primitive": "mcp",
  "title": "MCP Metrics — Telemetry, Latency & Error Observability for MCP Servers",
  "description": "Real-time p50/p95 tool-call latency tracking, JSON-RPC error alerting, and token-cost analytics for remote Streamable HTTP and stdio MCP servers.",
  "category": "engineering",
  "tags": "[\"mcp-metrics\", \"streamable-http\", \"engineering\", \"mcp-server\", \"query-tool-latency-percentiles\", \"list-failing-rpc-calls\"]",
  "agent_compatibility": "[\"grok-bot\", \"claude-code\", \"cursor\"]",
  "author_handle": "threepointone",
  "author_name": "Sunil Pai (@threepointone)",
  "author_avatar": null,
  "source_tweet_url": "https://mcpmetrics.com",
  "github_url": "https://mcpmetrics.com",
  "external_url": "https://mcpmetrics.com",
  "upvotes_count": 250,
  "installs_count": 250
}