io.github.abhishekash/mcp-trace-inspector — MCP Trace Inspector

This MCP server provides an interface to query OpenTelemetry traces generated from agent runs. It is identified by the slug io-github-abhishekash-mcp-trace-inspector and described as enabling trace queries via MCP for trace data associated with agent execution.

🛠️ Key Features

Query OpenTelemetry traces
Target traces from agent runs
Expose trace querying through MCP

🚀 Use Cases

Inspecting and searching OpenTelemetry trace data produced during agent runs
Retrieving trace information for debugging or analysis via MCP

⚡ Developer Benefits

Centralized access to OpenTelemetry traces from agent runs through MCP
Simplifies integration of trace querying into MCP-based tooling workflows

⚠️ Limitations

Available source data does not specify supported trace operations beyond “query OpenTelemetry traces.”

AgentHawk

AgentHawk is a small, local-first stdio MCP server for querying JSONL OpenTelemetry spans emitted by agent runs. It exposes focused queries for run summaries, tool failures, approvals, activity, and comparisons instead of requiring an application-specific dashboard.

It pairs with agent-harness, but the reader is format-simple: any JSONL of OTel-shaped spans works. The project's concrete origin was a shell-boundary regression: the harness blocked cat ../outside.txt, but the old trace recorded only that run_shell was called, not the returned diagnostic. AgentHawk and the harness now preserve and query that bounded error.

AI-native use cases

Question during an agent run	MCP tool	Evidence returned
"Why did yesterday's run stall?"	`list_runs` → `slowest_spans`	Run IDs and the longest model or tool spans.
"Did the agent act after I denied the write?"	`approval_log` → `span_tree`	The recorded decision and subsequent execution path.
"How many model tokens did this run use?"	`token_usage` → `span_tree`	Run-level usage totals and the span tree for context.
"Which tool is failing or timing out?"	`failure_report` / `tool_stats`	Redacted diagnostics, error rates, denials, and p95 latency.
"Who/what was allowed to act?"	`security_audit`	Caller, tenant, server provenance, risk, and missing-evidence findings.
"What is happening in the run right now?"	`recent_activity`	Cursor-based polling of newly written spans.
"Did this model/version regress?"	`compare_runs`	Cost, latency, tokens, tool calls, and failure deltas.

The tools read stored traces and can poll files being written, but they do not push events or infer intent from the final answer. Start with the installation and user guide, then see the real trace fixture and the tool descriptions for the query contract.

Install & run

bash

uvx agenthawk --trace-dir ./traces
# or, for local development:
git clone https://github.com/abhishekash/mcp-trace-inspector
cd mcp-trace-inspector && uv pip install -e .
agenthawk --trace-dir ./traces

Client configuration

Claude Desktop (claude_desktop_config.json):

json

{
  "mcpServers": {
    "agent-traces": {
      "command": "uvx",
      "args": ["agenthawk", "--trace-dir", "/path/to/traces"]
    }
  }
}

pi (~/.pi/agent/settings.json):

json

{
  "mcpServers": {
    "agent-traces": {
      "command": "uvx",
      "args": ["agenthawk", "--trace-dir", "/path/to/traces"]
    }
  }
}

agent-harness (mounted as gated tools):

bash

harness run "Why was my last run slow?" --mcp "uvx agenthawk --trace-dir ./traces"

Tools

Tool	Use it when
`list_runs`	Starting out — recent runs with task, model, duration, cost, decision counts
`run_summary`	One run at a glance (accepts trace-id prefix)
`span_tree`	"What did the agent actually do?" — nested shape of the run
`slowest_spans`	"Why was it slow?" — top-k spans by duration
`approval_log`	HITL audit — every approve/deny/edit, who decided, and the rationale
`token_usage`	Cost questions — aggregated across runs or per-run
`search_spans`	Find spans by tool name, file path, "denied", …
`failure_report`	Find actionable, bounded, redacted errors and failed tool calls.
`tool_stats`	Rank tools by volume, error rate, denials, and latency.
`security_audit`	Audit caller identity, tenant, server provenance, risk, and approval evidence.
`recent_activity`	Poll new spans with a cursor while a run is active.
`compare_runs`	Compare selected traces for regressions across models or versions.

Tool descriptions are written as prompts (when-to-use, not just what-it-does) — descriptions are the interface for agent-called tools.

Example session (real fixture trace)

code

> list_runs
[{ "trace_id": "f920798dd255…", "task": "Summarize the workspace's notes…",
   "tool_calls": 4, "human_decisions": 2, "stopped_reason": "completed" }]

> approval_log
[{ "tool": "write_file", "decision": "approve", "approver": "auto", … },
 { "tool": "run_shell",  "decision": "approve", "approver": "auto", … }]

Design