Observed since 20 Oct, 15:00 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
021-mcp
MCP server for interacting with LLM traces - search, analyze, and debug your AI agent executions
MCP server for interacting with LLM traces. Search, analyze, and debug your AI agent executions through any MCP-compatible client.
pip install 021-mcp
Or with uvx:
uvx 021-mcp
| Variable | Required | Description |
|---|---|---|
TRACES_API_KEY | Yes | Your API key for authentication |
TRACES_BASE_URL | No | Base URL of the traces API (default: https://api.021labs.ai) |
Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"traces": {
"command": "uvx",
"args": ["021-mcp"],
"env": {
"TRACES_API_KEY": "your-api-key-here"
}
}
}
}
Add to your Manus MCP configuration:
{
"servers": {
"traces": {
"command": "uvx",
"args": ["021-mcp"],
"env": {
"TRACES_API_KEY": "your-api-key-here"
}
}
}
}
Most MCP clients support a similar configuration format. The key elements are:
uvx (or python -m mcp_traces.server if installed via pip)["021-mcp"]TRACES_API_KEYlist_tracesList traces with optional filters.
Parameters:
status - Filter by status: SUCCESS, ERROR, or RUNNINGsearch - Full-text search querystart_time - Filter traces after this ISO timestampend_time - Filter traces before this ISO timestampsession_id - Filter by session IDuser_id - Filter by user IDproject_id - Filter by project IDlimit - Maximum results (1-100, default 20)Example usage:
"Show me the last 10 traces that failed" "Find traces from yesterday that mention 'database'"
get_traceGet detailed information about a specific trace.
Parameters:
trace_id - The trace ID to fetchinclude_io - Include full input/output data (default: false)Example usage:
"Get details for trace abc123" "Show me trace xyz789 with all the LLM inputs and outputs"
get_spanGet full details for a specific span including input/output.
Parameters:
span_id - The span ID to fetchExample usage:
"What was the input to span def456?" "Show me the LLM response in span ghi789"
get_analyticsGet analytics summary for traces.
Parameters:
start_time - Start of time rangeend_time - End of time rangegranularity - hour, day, or week (default: day)project_id - Filter by project IDExample usage:
"Show me trace analytics for the last week" "What's the error rate for project X?"
search_errorsFind recent traces that ended in errors.
Parameters:
limit - Maximum results (default: 10)start_time - Filter errors after this timestampproject_id - Filter by project IDExample usage:
"Find recent errors" "What failed in the last hour?"
# Clone and install
git clone https://github.com/021labs/rl.git
cd rl/packages/mcp
# Install dependencies
uv sync
# Run locally
uv run 021-mcp
# Run tests
uv run pytest
MIT
Download counts and popularity will appear here as the collector receives them.
| Package / target | Requirement | Relationship |
|---|---|---|
httpxEnvironment{
"extras": "",
"marker": null,
"requires_python": ">=3.10",
"evaluation": "NOT_EVALUATED"
} | httpx>=0.27.0 | runtime |
mcpEnvironment{
"extras": "",
"marker": null,
"requires_python": ">=3.10",
"evaluation": "NOT_EVALUATED"
} | mcp>=1.0.0 | runtime |
pydanticEnvironment{
"extras": "",
"marker": null,
"requires_python": ">=3.10",
"evaluation": "NOT_EVALUATED"
} | pydantic>=2.5.0 | runtime |
pytest-asyncioEnvironment{
"extras": "",
"marker": "extra == \"dev\"",
"requires_python": ">=3.10",
"evaluation": "NOT_EVALUATED"
} | pytest-asyncio>=0.21.0; extra == "dev" | runtime |
pytestEnvironment{
"extras": "",
"marker": "extra == \"dev\"",
"requires_python": ">=3.10",
"evaluation": "NOT_EVALUATED"
} | pytest>=7.4.0; extra == "dev" | runtime |
ruffEnvironment{
"extras": "",
"marker": "extra == \"dev\"",
"requires_python": ">=3.10",
"evaluation": "NOT_EVALUATED"
} | ruff>=0.1.0; extra == "dev" | runtime |
bdist_wheel · 10.86 KB · Python py3
sdist · 9.57 KB · Python source
Observed since 20 Oct, 15:00 UTC
No superseded metadata states collected. Unchanged observations do not create new revisions.
package_version:c5a514e551a39501de4e66bd1b94b0bd61e92ce33e840e47e7dc77dec0f8495b