Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, email [email protected] and we’ll put it right.

io.github.mdfifty50-boop/trace-forge

NPM · TRACE-FORGE-MCP · SCANNED AUG 3

Structured execution trace and span logging for AI agents

Available components

−9 this week 63 Trust /100
Trust breakdown (6 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score →

Supply Chain Security87
  • No malware found by supply-chain analysis.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability45
  • 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Fail
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 656 tokens (~65/item across 10 items; 8 tools + 2 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management23
  • Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

Add this component to your MCP client. Where a client-specific snippet is available, pick your client below and copy it straight into your config; otherwise use the connection detail shown.

npm · trace-forge-mcp

# add to Claude Code
claude mcp add mdfifty50-boop-trace-forge -- npx -y trace-forge-mcp
# add to Codex CLI
codex mcp add mdfifty50-boop-trace-forge -- npx -y trace-forge-mcp
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mdfifty50-boop-trace-forge": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "trace-forge-mcp"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add mdfifty50-boop-trace-forge --command npx --arg -y --arg trace-forge-mcp
# ~/.hermes/config.yaml
mcp_servers:
  mdfifty50-boop-trace-forge:
    command: "npx"
    args: ["-y", "trace-forge-mcp"]
// mcp.json
{
  "mcpServers": {
    "mdfifty50-boop-trace-forge": {
      "command": "npx",
      "args": [
        "-y",
        "trace-forge-mcp"
      ]
    }
  }
}
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 3 Aug 26 +4
    • Stability: unverified → 0.23 functional
  • 2 Aug 26 +30
    • Provenance: unverified → fail security
    • Known CVEs: unverified → partial security
    • Install scripts: unverified → pass security
    • Malware scan: unverified → pass security
    • Stability: Stability not yet verified: we do not have a sandbox capture of the MCP schema this version of the package serves yet. security
    • Capabilities: pass → unverified functional
    • Tool coverage: 100 → unverified functional
    • Schema quality: 0 → unverified functional
    • Maintenance: unverified → pass functional
    • Dependency health: unverified → partial functional
    • License: unverified → pass functional
    • Licence: MIT functional
  • 1 Aug 26 +24
    • Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window). security
    • MCP protocol: unverified → pass functional
    • Tool coverage: unverified → 100 functional
    • Schema quality: unverified → 0 functional
  • 31 Jul 26 −1
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 30 Jul 26 −66
    • Install scripts: pass → unverified security
    • Provenance: fail → unverified security
    • Known CVEs: partial → unverified security
    • Malware scan: pass → unverified security
    • Maintenance: pass → unverified functional
    • Dependency health: partial → unverified functional
    • Tool coverage: 100 → unverified functional
    • Schema quality: 0 → unverified functional
    • License: pass → unverified functional
    • Licence: MIT functional
  • 27 Jul 26 72

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 3 Aug 2026 · Analysed npm/[email protected]

Provenance none

Ecosystem: npm · Outcome: none

Dependencies 95 packages

95 packages in the resolved dependency tree · 95 deprecated · 29 stale.

The dependency tree was only partially resolved, so these counts may be incomplete.

MCP tools — 8 exposed · ~644 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability.

Tool Tokens
get_trace ~37

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

NameTypeReqDescription
trace_idstringyesTrace ID to retrieve

No output schema declared.

No examples provided.

health_check ~20

Returns server health, uptime, version, and call stats

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

search_traces ~76

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

NameTypeReqDescription
agent_idstringFilter by agent ID
limitintegerMax results to return (default 20)
statusstringFilter by status (active, success, failure, partial, timeout)

No output schema declared.

No examples provided.

trace_decision ~109

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

NameTypeReqDescription
alternatives_consideredarrayyesOther options the agent evaluated
chosen_actionstringyesWhat the agent decided to do
confidencenumberyesAgent confidence in this decision (0.0 to 1.0)
reasoningstringyesWhy the agent made this decision
trace_idstringyesTrace this decision belongs to

No output schema declared.

No examples provided.

trace_end ~62

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

NameTypeReqDescription
outcomestringyesFinal outcome of the traced task
summarystringOptional summary of what happened
trace_idstringyesTrace to complete

No output schema declared.

No examples provided.

trace_span ~98

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

NameTypeReqDescription
metadataobjectOptional span metadata
parent_span_idstringParent span ID for nesting (creates a tree)
span_namestringyesName of this span (e.g. "research", "code_generation", "validation")
trace_idstringyesTrace to attach this span to

No output schema declared.

No examples provided.

trace_start ~82

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

NameTypeReqDescription
agent_idstringyesUnique identifier for the agent starting the trace
metadataobjectOptional metadata (model, department, priority, etc.)
task_descriptionstringyesHuman-readable description of what the agent is doing

No output schema declared.

No examples provided.

trace_tool_call ~160

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

NameTypeReqDescription
argsobjectyesArguments passed to the tool
duration_msnumberyesHow long the tool call took in milliseconds
result_previewstringyesBrief preview of the result (max 500 chars)
span_idstringSpan this tool call belongs to (optional)
statusstringyesOutcome of the tool call
tokens_usedintegerToken count for this call (optional, enables cost estimation)
tool_namestringyesName of the tool that was called
trace_idstringyesTrace this tool call belongs to

No output schema declared.

No examples provided.