MCP server for interacting with LLM traces - search, analyze, and debug your AI agent executions
Drift inferred · capture-to-capture
No drift recorded — single capability capture; advisories appear once its surface changes.
transport stdio counts 0 tools · 0 res
· 0 prompts
permission surface via code analysis
no tools enumerated yet for this server.
evidence-backed
findings quoted directly from the published source artifact — not inferred
network 1
- net 021_mcp-0.1.4/src/mcp_traces/client.py :8
import httpx
secrets 1
- secrets 021_mcp-0.1.4/src/mcp_traces/server.py :51
api_key = os.environ.get("TRACES_API_KEY")
tool registrations 5
- list_traces 021_mcp-0.1.4/src/mcp_traces/server.py :108
- get_trace 021_mcp-0.1.4/src/mcp_traces/server.py :197
- get_span 021_mcp-0.1.4/src/mcp_traces/server.py :268
- get_analytics 021_mcp-0.1.4/src/mcp_traces/server.py :334
- search_errors 021_mcp-0.1.4/src/mcp_traces/server.py :414
declared dependencies 6
- mcp@>=1.0.0
- httpx@>=0.27.0
- pydantic@>=2.5.0
- pytest@>=7.4.0
- pytest-asyncio@>=0.21.0
- ruff@>=0.1.0