Trace Forge

io.github.mdfifty50-boopPublished by GitHub account mdfifty50-boopv0.1.1Updated Oct 27, 2026

Structured execution trace and span logging for AI agents

VerifiedSTDIODesktop onlySecurity & Monitoring Data & Analytics AI & ML

Server details

Identifier: io.github.mdfifty50-boop/trace-forge
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account mdfifty50-boop for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.mdfifty50-boop%2Ftrace-forge.svg)](https://sourceweft.com/mcp/io.github.mdfifty50-boop%2Ftrace-forge?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

Local MCP server that lets an assistant record structured execution traces, spans, tool calls and decisions for AI agent tasks, then retrieve and search them.

What you can do: Start and end traces for agent tasks, with agent ID, task description, metadata, outcome and summary
Create nested spans inside a trace to mark logical work units
Log tool calls with arguments, result preview, duration, status and optional token-based cost estimate
Log decision points with reasoning, alternatives considered, chosen action and confidence
Retrieve a full trace tree and search traces by agent ID or status
Read recent traces and aggregate statistics through resources
When to use it: Useful when you want an auditable record of what an agent did and why, for example to review multi-step tool use, compare decisions, or keep traceability documentation for high-risk AI workflows.
Requirements: Runs as a local process via npx (Node.js) or from source with npm install; configured in the client's MCP server config. No accounts, API keys, environment variables or headers are declared.

Before you install

It is a write path: tool arguments, result previews, reasoning and metadata are stored in traces, so avoid passing secrets or personal data. Traces are kept locally by the server; check where and how long they are retained before relying on them for compliance records.

Installation

In SourceWeft

Open Trace Forge in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

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

Claude Desktop

Add to claude_desktop_config.json:

json

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

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

From source

bash

git clone https://github.com/mdfifty50-boop/trace-forge-mcp.gitcd trace-forge-mcpnpm installnode src/index.js

git clone https://github.com/mdfifty50-boop/trace-forge-mcp.gitcd trace-forge-mcpnpm installnode src/index.js

Tools

trace_start

Begin a new trace for an agent task.

Returns: { trace_id, started_at }

trace_span

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

Param	Type	Required	Description
`trace_id`	string	yes	Trace to attach to
`span_name`	string	yes	Span name (e.g. "research", "validation")
`parent_span_id`	string	no	Parent span for nesting
`metadata`	object	no	Optional span metadata

Returns: { span_id, trace_id }

trace_tool_call

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

Param	Type	Required	Description
`trace_id`	string	yes	Trace this belongs to
`span_id`	string	no	Span this belongs to
`tool_name`	string	yes	Tool that was called
`args`	object	yes	Arguments passed
`result_preview`	string	yes	Result preview (max 500 chars)
`tokens_used`	number	no	Token count (enables cost estimation)
`duration_ms`	number	yes	Call duration in milliseconds
`status`	string	yes	`"success"`, `"error"`, or `"timeout"`

Returns: { event_id, logged: true }

trace_decision

Log an agent decision point with reasoning and alternatives considered.

Param	Type	Required	Description
`trace_id`	string	yes	Trace this belongs to
`reasoning`	string	yes	Why the agent made this decision
`alternatives_considered`	string[]	yes	Other options evaluated
`chosen_action`	string	yes	What was decided
`confidence`	number	yes	Confidence 0.0 to 1.0

Returns: { event_id, logged: true }

trace_end

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

Returns: { trace_id, duration_ms, events_count, spans_count, tool_calls_count }

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

1. trace_start — when agent begins a task2. trace_span — create logical work units (research, generation, validation)3. During execution:   - trace_tool_call — after each tool invocation   - trace_decision — at each decision point4. trace_end — when task completes5. get_trace — retrieve full audit trail6. search_traces — find traces by agent or status

1. trace_start — when agent begins a task2. trace_span — create logical work units (research, generation, validation)3. During execution:   - trace_tool_call — after each tool invocation   - trace_decision — at each decision point4. trace_end — when task completes5. get_trace — retrieve full audit trail6. search_traces — find traces by agent or status

EU AI Act Compliance

Article 14 of the EU AI Act requires high-risk AI systems to maintain traceability of decisions and actions. trace-forge-mcp provides:

Structured decision logging with reasoning and alternatives
Complete tool call audit trails with timing and cost
Hierarchical span trees for complex multi-step tasks
Agent identification and task attribution

License

MIT

Source: README.md at commit b613faf

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v0.1.1LatestSep 16, 2026

Score

40% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts
Declare a license in the repository or the registry entry.

URI	Description
`traces://recent`	Last 20 traces with summary
`traces://stats`	Aggregate statistics (total, avg duration, success rate)