# io.github.tracelane/tracelane-mcp (npm · @tracelanedev/mcp)

Read-only, tenant-scoped access to Tracelane agent traces and guardrail verdicts

- Trust score: 80/100 (high trust)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-16

## Components

- npm · `@tracelanedev/mcp`: 80/100 (this document), [markdown](https://verifymcp.io/servers/tracelane-tracelane-mcp/tracelanedev-mcp.md), [page](https://verifymcp.io/servers/tracelane-tracelane-mcp/tracelanedev-mcp)

## Channel facts

- Registry: `npm`
- Package: `@tracelanedev/mcp`
- Version: `0.4.0`
- 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 2026-10-16.

- **Supply Chain Security**: 98/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - 31 of 94 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to tracelane/tracelane).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 6 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 76/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 712 tokens (~89/item across 8 items; 8 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **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.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "get_eval_result" implies "eval" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the io.github.tracelane/tracelane-mcp server?

io.github.tracelane/tracelane-mcp runs locally as an npm package, launched with npx -y @tracelanedev/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add tracelane-tracelane-mcp -- npx -y @tracelanedev/mcp
```

### Cursor

```json
{
  "mcpServers": {
    "tracelane-tracelane-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@tracelanedev/mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "tracelane-tracelane-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@tracelanedev/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add tracelane-tracelane-mcp -- npx -y @tracelanedev/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tracelane-tracelane-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@tracelanedev/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add tracelane-tracelane-mcp --command npx --arg -y --arg @tracelanedev/mcp
```

### Hermes

```yaml
mcp_servers:
  tracelane-tracelane-mcp:
    command: "npx"
    args: ["-y", "@tracelanedev/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "tracelane-tracelane-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@tracelanedev/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add tracelane-tracelane-mcp -t stdio -c npx -a -y @tracelanedev/mcp
```

### Other

```json
{
  "mcpServers": {
    "tracelane-tracelane-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@tracelanedev/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.

### 2026-10-14 (score 80, +31)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Destructive annotations: 0
- [functional] First check of Schema quality: pass
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 100

### 2026-10-11 (score 49)

First indexed and scored.

## MCP tools (8)

### `list_traces` (~73 tokens)

List recent traces for the authenticated tenant

Input parameters:

- `has_error` (boolean): Filter to traces with at least one error span
- `limit` (number): Maximum traces to return (1-100)
- `model_filter` (string): Filter by model name, e.g. claude-sonnet-4-6

### `get_trace` (~29 tokens)

Get all spans for a specific trace

Input parameters:

- `trace_id` (string, required): The trace ID to fetch

### `get_span` (~87 tokens)

Get details for a specific span including all LLM attributes. trace_id is REQUIRED in Cloud (gateway) mode — there is no span-by-id gateway route, so the span is located via GET /v1/traces/{trace_id}/spans.

Input parameters:

- `span_id` (string, required): The span ID
- `trace_id` (string): The trace ID (required — see tool description).

### `search_traces` (~151 tokens)

Search traces by free-text substring across span names and the attributes JSON blob, optionally narrowed by model name or error status. Read-only; tenant-scoped. In gateway (Cloud) mode the gateway rejects a search term shorter than 4 characters.

Input parameters:

- `has_error` (boolean): Restrict to error spans (status_code = 2) when true
- `limit` (number): Maximum distinct traces to return (1-50)
- `model_filter` (string): Restrict to spans whose attributes mention this model
- `query` (string, required): Case-insensitive substring matched against span name and the attributes JSON (model names, prompts, tool names, etc.). Gateway mode requires at least 4 characters.

### `replay_trace` (~136 tokens)

Fetch the full stored structure of a trace (ordered spans with their LLM/tool attributes) for offline inspection and step-through debugging. Read-only: this returns the recorded trace as-is and does NOT re-execute any model or tool — live shadow re-execution requires the gateway and is not part of the MCP server surface.

Input parameters:

- `include_tool_calls` (boolean): Include non-LLM (tool / browser / MCP) spans in the result. When false, only LLM spans (those whose attributes carry a gen_ai/llm model) are returned.
- `trace_id` (string, required): The trace ID to fetch for inspection

### `explain_guardrail_block` (~168 tokens)

Explain a Tracelane guardrail signal. Two independent id kinds, pick the one you have: `correlation_id` — the id in a guardrail 403 response body, for a request that was blocked pre-flight (there is no trace/span for it, since the request never dispatched); or `trace_id` + `span_id` together — to explain a detection-layer (AFT) flag recorded on a span that DID execute.

Input parameters:

- `correlation_id` (string): The correlation id from a guardrail block's 403 response body.
- `span_id` (string): The span ID carrying an AFT detection flag. Use with trace_id.
- `trace_id` (string): The trace ID containing an AFT-flagged span. Use with span_id.

### `list_evals` (~24 tokens)

List all pain-point and fault-tolerance evals and their current status

### `get_eval_result` (~44 tokens)

Get the latest result for a specific eval

Input parameters:

- `eval_id` (string, required): Eval ID, e.g. PP-G3, PP-PR1, FT-01

## Diagnostics

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

## Score history

- 2026-10-16: 80
- 2026-10-15: 80
- 2026-10-14: 80
- 2026-10-13: 49
- 2026-10-12: 49
- 2026-10-11: 49

## Common questions

### What is the io.github.tracelane/tracelane-mcp server?

io.github.tracelane/tracelane-mcp is listed in the public MCP registry as io.github.tracelane/tracelane-mcp. Read-only, tenant-scoped access to Tracelane agent traces and guardrail verdicts. This page covers its npm package (@tracelanedev/mcp).

### Is the io.github.tracelane/tracelane-mcp server safe to use?

io.github.tracelane/tracelane-mcp scores 80 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 16 October 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the io.github.tracelane/tracelane-mcp server expose?

io.github.tracelane/tracelane-mcp exposes 8 tools: list_traces, get_trace, get_span, search_traces, replay_trace, and 3 more. Their descriptions and schemas cost roughly 712 tokens of context every time the server is loaded.

### Is the io.github.tracelane/tracelane-mcp server still maintained?

io.github.tracelane/tracelane-mcp is still listed as active in the MCP registry. We last reached this channel on 16 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the io.github.tracelane/tracelane-mcp server under?

io.github.tracelane/tracelane-mcp declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@tracelanedev/mcp
- Socket report: https://socket.dev/npm/package/@tracelanedev/mcp
- Repository: https://github.com/tracelane/tracelane
- Website: https://tracelane.dev/docs/mcp-server
- Changelog RSS feed: https://verifymcp.io/servers/tracelane-tracelane-mcp/tracelanedev-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/tracelane-tracelane-mcp/tracelanedev-mcp.json
- HTML version of this page: https://verifymcp.io/servers/tracelane-tracelane-mcp/tracelanedev-mcp