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

TokenTrace

NPM · TOKENTRACE · SCANNED SEP 20

Local-first AI CLI usage analytics for agents.

Available components

0 this week 90 Trust /100
Trust breakdown (7 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 → Why this is hard to score →

Supply Chain Security98
  • No malware found by supply-chain analysis.Pass
  • Known CVEs were checked across the 290 of 291 dependencies we could resolve, so this covers what we could see, not the whole tree.Partial
  • No install/post-install scripts declared.Pass
  • Dependency health was assessed across the 290 of 291 dependencies we could resolve, so this covers what we could see, not the whole tree. View diagnostics → Partial
Provenance & Transparency100
  • Source repository is publicly reachable at the declared URL. View diagnostics → Pass
  • Cryptographically verified build provenance (signed, bound to abhiyoheswaran1/tokentrace). View diagnostics → Pass
  • Clear OSI-approved license (MIT).Pass
  • Actively maintained (last published 85 days ago).Pass
  • Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability72
  • AI-judged instruction clarity (good).Pass
  • Tool/resource definitions use about 662 tokens (~50/item across 13 items; 13 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management83
  • Stability observed for 25 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage96
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 87% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 13 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 14 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Install

How do I install the TokenTrace MCP server?

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

npm · tokentrace

# add to Claude Code
claude mcp add abhiyoheswaran1-tokentrace -- npx -y tokentrace
// .cursor/mcp.json
{
  "mcpServers": {
    "abhiyoheswaran1-tokentrace": {
      "command": "npx",
      "args": [
        "-y",
        "tokentrace"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "abhiyoheswaran1-tokentrace": {
      "command": "npx",
      "args": [
        "-y",
        "tokentrace"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add abhiyoheswaran1-tokentrace -- npx -y tokentrace
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "abhiyoheswaran1-tokentrace": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "tokentrace"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add abhiyoheswaran1-tokentrace --command npx --arg -y --arg tokentrace
# ~/.hermes/config.yaml
mcp_servers:
  abhiyoheswaran1-tokentrace:
    command: "npx"
    args: ["-y", "tokentrace"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "abhiyoheswaran1-tokentrace": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "tokentrace"
      ]
    }
  }
}
# add to Vellum
assistant mcp add abhiyoheswaran1-tokentrace -t stdio -c npx -a -y tokentrace
// mcp.json
{
  "mcpServers": {
    "abhiyoheswaran1-tokentrace": {
      "command": "npx",
      "args": [
        "-y",
        "tokentrace"
      ]
    }
  }
}
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.

  • 19 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 18 Sept 26 0
    • Stability: 0.97 → pass security
  • 17 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

  • 12 Sept 26 −2
    • Stability: pass → 0.80 functional
  • 11 Sept 26 0
    • Stability: 0.97 → pass security
  • 10 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 7 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 83 to 87. That category is still filling its 30-day observation window: 25 days of observed history at the previous scan, 26 at this one. The score rises as the window fills, whether or not the server changes.

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 20 Sept 2026 · Analysed npm/tokentrace@0.21.2

Provenance Verified

A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.

Result Verified
Ecosystem npm
Reason Verified
Discovered via Registry attestation endpoint
Source repo abhiyoheswaran1/tokentrace
Certificate issuer https://token.actions.githubusercontent.com
Certificate SAN https://github.com/abhiyoheswaran1/tokentrace/.github/workflows/npm-publish.yml@refs/tags/v0.21.2
Rekor log index 1972449890
Predicate type https://slsa.dev/provenance/v1
Subject digest sha512:1e4dcc5d6a5ff6a51eeaea1bcecab66f0b94b01bd83cee4c111284d5f32b1c17790253a917e5d20392e80647313e1f65c2723daf19619ae293b182979

Background: How many MCP packages publish verified provenance →

Dependencies 290 packages
Packages resolved 290
Deprecated 1
Stale 78
No linked repository 1
Tree resolution Partial

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

Background: SBOMs and build attestations, explained →

MCP tools · 13 exposed · ~633 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. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
get_agent_guide ~34

Return the recommended MCP operating loop, install snippets, copy-paste AGENTS.md guidance, and local-first guardrails.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_anomalies ~72

Return modified-z-score (MAD) anomalies for the local daily token and cost trend. Pure-stats detector; spends zero AI tokens.

NameTypeReqDescription
metricstringFilter anomalies to a specific metric. Defaults to 'all'.
windowintegerTrailing window size in days (default 14).

No output schema declared.

No examples provided.

get_capabilities ~26

Return the read-only TokenTrace agent discovery manifest. Does not initialize local app data.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_classifications ~60

Return the local unknown-cost repair queue with deterministic classification suggestions (exact-model, family-fragment, or parser-source). Read-only; spends zero AI tokens.

NameTypeReqDescription
minConfidencenumberFilter to suggestions with confidence >= this value (default 0).

No output schema declared.

No examples provided.

get_evidence ~40

Return evidence behind a TokenTrace metric without raw prompt or message bodies.

NameTypeReqDescription
metricstringEvidence metric to inspect. Defaults to processed-tokens.

No output schema declared.

No examples provided.

get_handoff ~48

Return the schema-versioned tokentrace.handoff.v1 envelope summarizing local scan state, repair queue, confidence, recent agent actions, and suggested next actions. Pure read; no scan.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_preflight ~35

Return a read-only local preflight decision before another coding-agent run: proceed, caution, or blocked with evidence and next actions.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_repair_queue ~24

Return grouped unknown-cost repair causes, next actions, and review state.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_report ~51

Return a deterministic local report as markdown or JSON.

NameTypeReqDescription
formatstringReport format. Defaults to markdown.
sincestringOptional scope: last-scan, yesterday, or YYYY-MM-DD.

No output schema declared.

No examples provided.

get_status ~20

Return the current local TokenTrace usage status snapshot as JSON.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

query_usage ~106

Run a deterministic, parameterized query over the local TokenTrace database. The caller supplies structured arguments; TokenTrace executes the SQL. No NL parsing happens server-side, so zero AI tokens are spent.

NameTypeReqDescription
filtersobject
groupBystringyesGrouping dimension.
metricstringyesMetric to aggregate per group.
rangeobject
sortstringDefault 'desc'.
topNintegerDefault 20.

No output schema declared.

No examples provided.

run_doctor ~26

Inspect scan freshness, parser trust, source coverage, package trust, and repair recommendations.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

run_scan ~91

Explicitly scan local AI CLI artifacts and update the local TokenTrace database. Requires confirmLocalScan=true.

NameTypeReqDescription
confirmLocalScanbooleanyesMust be true to confirm local file reads and local database writes.
foldersarrayOptional local folders to scan. Defaults to TokenTrace's supported local roots.
forcebooleanForce parser reprocessing for files that would otherwise be deduplicated.

No output schema declared.

No examples provided.

Common questions

What is the TokenTrace MCP server?

TokenTrace is an MCP server listed in the public MCP registry as io.github.abhiyoheswaran1/tokentrace. Local-first AI CLI usage analytics for agents. This page covers its npm package (tokentrace).

Is the TokenTrace MCP server safe to use?

TokenTrace scores 90 out of 100 on VerifyMCP. 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 TokenTrace MCP server expose?

TokenTrace exposes 13 tools: get_agent_guide, get_capabilities, get_status, get_preflight, run_doctor, and 8 more. Their descriptions and schemas cost roughly 633 tokens of context every time the server is loaded.

Is the TokenTrace MCP server still maintained?

TokenTrace is still listed as active in the MCP registry. We last reached this channel on 20 September 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 TokenTrace MCP server under?

TokenTrace declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.