# io.github.mdfifty50-boop/trace-forge (npm · trace-forge-mcp)

Structured execution trace and span logging for AI agents

- Trust score: 63/100 (medium)
- Change this week: −9
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `trace-forge-mcp`: 63/100 (this document), [markdown](https://verifymcp.io/servers/mdfifty50-boop-trace-forge/trace-forge-mcp.md), [page](https://verifymcp.io/servers/mdfifty50-boop-trace-forge/trace-forge-mcp)

## Channel facts

- Registry: `npm`
- Package: `trace-forge-mcp`
- Version: `0.1.1`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 87/100
  - No malware found by supply-chain analysis.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
  - No install/post-install scripts declared.
  - Only part of the dependency tree could be resolved (95 of 99), so this covers what we could see, not the whole tree.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 100 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 45/100
  - 0% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 656 tokens (~65/item across 10 items; 8 tools + 2 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### Claude

```bash
claude mcp add mdfifty50-boop-trace-forge -- npx -y trace-forge-mcp
```

### Codex

```bash
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
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add mdfifty50-boop-trace-forge --command npx --arg -y --arg trace-forge-mcp
```

### Hermes

```yaml
mcp_servers:
  mdfifty50-boop-trace-forge:
    command: "npx"
    args: ["-y", "trace-forge-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "mdfifty50-boop-trace-forge": {
      "command": "npx",
      "args": [
        "-y",
        "trace-forge-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-08-03 (score 63, +4)

- [functional improvement] Stability: unverified → 0.23

### 2026-08-02 (score 59, +30)

- [security regression] Provenance: unverified → fail
- [security improvement] Known CVEs: unverified → partial
- [security improvement] Install scripts: unverified → pass
- [security improvement] 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.
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 0 → unverified
- [functional improvement] Maintenance: unverified → pass
- [functional improvement] Dependency health: unverified → partial
- [functional improvement] License: unverified → pass
- [functional] Licence: MIT

### 2026-08-01 (score 29, +24)

- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] MCP protocol: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Schema quality: unverified → 0

### 2026-07-31 (score 5, −1)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-30 (score 6, −66)

- [security regression] Install scripts: pass → unverified
- [security regression] Provenance: fail → unverified
- [security regression] Known CVEs: partial → unverified
- [security regression] Malware scan: pass → unverified
- [functional regression] Maintenance: pass → unverified
- [functional regression] Dependency health: partial → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Schema quality: 0 → unverified
- [functional regression] License: pass → unverified
- [functional] Licence: MIT

### 2026-07-27 (score 72)

First indexed and scored.

## MCP tools (8)

### `health_check` (~20 tokens)

Returns server health, uptime, version, and call stats

### `trace_start` (~82 tokens)

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

Input parameters:

- `agent_id` (string, required): Unique identifier for the agent starting the trace
- `metadata` (object): Optional metadata (model, department, priority, etc.)
- `task_description` (string, required): Human-readable description of what the agent is doing

### `trace_span` (~98 tokens)

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

Input parameters:

- `metadata` (object): Optional span metadata
- `parent_span_id` (string): Parent span ID for nesting (creates a tree)
- `span_name` (string, required): Name of this span (e.g. "research", "code_generation", "validation")
- `trace_id` (string, required): Trace to attach this span to

### `trace_tool_call` (~160 tokens)

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

Input parameters:

- `args` (object, required): Arguments passed to the tool
- `duration_ms` (number, required): How long the tool call took in milliseconds
- `result_preview` (string, required): Brief preview of the result (max 500 chars)
- `span_id` (string): Span this tool call belongs to (optional)
- `status` (string, required): Outcome of the tool call
- `tokens_used` (integer): Token count for this call (optional, enables cost estimation)
- `tool_name` (string, required): Name of the tool that was called
- `trace_id` (string, required): Trace this tool call belongs to

### `trace_decision` (~109 tokens)

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

Input parameters:

- `alternatives_considered` (array, required): Other options the agent evaluated
- `chosen_action` (string, required): What the agent decided to do
- `confidence` (number, required): Agent confidence in this decision (0.0 to 1.0)
- `reasoning` (string, required): Why the agent made this decision
- `trace_id` (string, required): Trace this decision belongs to

### `trace_end` (~62 tokens)

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

Input parameters:

- `outcome` (string, required): Final outcome of the traced task
- `summary` (string): Optional summary of what happened
- `trace_id` (string, required): Trace to complete

### `get_trace` (~37 tokens)

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

Input parameters:

- `trace_id` (string, required): Trace ID to retrieve

### `search_traces` (~76 tokens)

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

Input parameters:

- `agent_id` (string): Filter by agent ID
- `limit` (integer): Max results to return (default 20)
- `status` (string): Filter by status (active, success, failure, partial, timeout)

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/mdfifty50-boop-trace-forge/trace-forge-mcp#diagnostics

## Score history

- 2026-08-03: 63
- 2026-08-02: 59
- 2026-08-01: 29
- 2026-07-31: 5
- 2026-07-30: 6
- 2026-07-28: 72
- 2026-07-27: 72

## Links

- npm package: https://www.npmjs.com/package/trace-forge-mcp
- Socket report: https://socket.dev/npm/package/trace-forge-mcp
- Repository: https://github.com/mdfifty50-boop/trace-forge-mcp
- Changelog RSS feed: https://verifymcp.io/servers/mdfifty50-boop-trace-forge/trace-forge-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/mdfifty50-boop-trace-forge/trace-forge-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/mdfifty50-boop-trace-forge/trace-forge-mcp