MCP.Market

Trace Forge MCP server

by mdfifty50-boop·io.github.mdfifty50-boop/trace-forge·v0.1.1
No reviews yet

Structured execution trace and span logging for AI agents

B78/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B78/100

full report

Adoption
New

0 stars45 downloads/wk

Reviews

Write one

Nobody has reviewed Trace Forge yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Trace Forge tools (8, 1 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • get_trace

    Retrieve a complete trace tree with all spans, events, tool calls, and decisions.

  • health_check

    Returns server health, uptime, version, and call stats

  • search_traces

    Find traces by agent ID and/or status. Returns matching traces sorted by recency with summary stats.

  • trace_decision

    Log an agent decision point — what it considered, what it chose, and why. Critical for EU AI Act explainability.

  • trace_end

    Complete a trace. Auto-calculates total duration, event counts, and span counts.

  • trace_spanwrite action

    Create a span within a trace. Spans represent logical units of work and can be nested via parent_span_id.

  • trace_start

    Begin a new trace for an agent task. Returns a trace_id used to attach spans, tool calls, and decisions.

  • trace_tool_call

    Log a tool call within a trace. Records tool name, arguments, result, duration, and token usage. Auto-calculates cost estimate.

Public scan report

scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it

no findings
  • Code scan9 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 156 days ago8/15
  • Maintainer identityregistry namespace matches repository owner6/10
Overall 78/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Trace Forge compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
78/100
higher than 57% of 48,255 servers
Tools
8
the typical server has 7
Tools that change things
13%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
45
more than 37% of 12,191 servers with a package

What its tools let an agent do: 7 read · 1 change

Install Trace Forge in Claude Code, Cursor or VS Code

Runs npx -y trace-forge-mcp on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add trace-forge -- npx -y trace-forge-mcp
Add to Cursor

What the publisher says

From the Trace Forge repository's README, as published. We do not edit it. Read it on GitHub

trace-forge-mcp

MCP server for writing structured traces, spans, and decisions. The only write-path observability MCP — all 9 existing observability MCPs are read-only.

Built for EU AI Act traceability compliance (Article 14, due August 2026).

Install

npx trace-forge-mcp

Claude Desktop

Add to claudedesktopconfig.json:

{
  "mcpServers": {
    "trace-forge": {
      "command": "npx",
      "args": ["trace-forge-mcp"]
    }
  }
}

From source

git clone https://github.com/mdfifty50-boop/trace-forge-mcp.git
cd trace-forge-mcp
npm install
node src/index.js

Tools

trace_start

Begin a new trace for an agent task.

Returns: { traceid, startedat }

trace_span

Create a span within a trace. Spans can be nested via parentspanid.

Returns: { spanid, traceid }

tracetoolcall

Log a tool call within a trace. Auto-calculates cost estimate from token count.

Returns: { event_id, logged: true }

trace_decision

Log an agent decision point with reasoning and alternatives considered.

Returns: { event_id, logged: true }

trace_end

Complete a trace. Auto-calculates total duration, event counts, and span counts.

Returns: { traceid, durationms, eventscount, spanscount, toolcallscount }

get_trace

Retrieve a complete trace tree with all spans, events, tool calls, and decisions.

Returns: Full trace object with nested span tree, all events, and computed totals.

search_traces

Find traces by agent ID and/or status.

Returns: Matching traces sorted by recency with summary stats.

Resources

Usage Pattern

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Trace Forge: common questions

Is Trace Forge MCP server safe?
Mostly: it is graded B (78/100). Read the Trace Forge safety report
How do I install Trace Forge?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Trace Forge need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Trace Forge maintained?
The last commit was 194 days ago (2026-04-24). The latest release is v0.1.1.
How does Trace Forge compare with other MCP servers?
safety score 78/100 (higher than 57% of 48,255 servers); tools 8 (the typical server has 7); tools that change things 13% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

More from mdfifty50-boop →