Tokenscope
NPM · @WARTZAR-BEE/TOKENSCOPE-MCP · SCANNED SEP 20
Analyze Claude Code session cost & context attribution: output, cached re-reads, cache writes.
Available components
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
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 56 days ago).Pass
- Disclosure check failed: no security disclosure policy was found in the source repository. See how to fix → Fail
Schema Quality & AI Usability75
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 536 tokens (~178/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
- Stability observed for 29 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
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the Tokenscope MCP server?
Tokenscope runs locally as an npm package, launched with npx -y @wartzar-bee/tokenscope-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · @wartzar-bee/tokenscope-mcp
claude mcp add wartzar-bee-tokenscope -- npx -y @wartzar-bee/tokenscope-mcp
{
"mcpServers": {
"wartzar-bee-tokenscope": {
"command": "npx",
"args": [
"-y",
"@wartzar-bee/tokenscope-mcp"
]
}
}
} {
"servers": {
"wartzar-bee-tokenscope": {
"command": "npx",
"args": [
"-y",
"@wartzar-bee/tokenscope-mcp"
]
}
}
} codex mcp add wartzar-bee-tokenscope -- npx -y @wartzar-bee/tokenscope-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"wartzar-bee-tokenscope": {
"type": "local",
"command": [
"npx",
"-y",
"@wartzar-bee/tokenscope-mcp"
],
"enabled": true
}
}
} openclaw mcp add wartzar-bee-tokenscope --command npx --arg -y --arg @wartzar-bee/tokenscope-mcp
mcp_servers:
wartzar-bee-tokenscope:
command: "npx"
args: ["-y", "@wartzar-bee/tokenscope-mcp"] {
"McpServers": {
"wartzar-bee-tokenscope": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"@wartzar-bee/tokenscope-mcp"
]
}
}
} assistant mcp add wartzar-bee-tokenscope -t stdio -c npx -a -y @wartzar-bee/tokenscope-mcp
{
"mcpServers": {
"wartzar-bee-tokenscope": {
"command": "npx",
"args": [
"-y",
"@wartzar-bee/tokenscope-mcp"
]
}
}
} 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.
- 18 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Sept 26 −2
- Stability: pass → 0.83 functional
- 15 Sept 26 +1
- Stability: 0.97 → pass security
- 12 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 9 Sept 26 −3
- Stability: pass → 0.80 functional
- 8 Sept 26 +1
- Stability: 0.97 → pass security
- 5 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
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/@wartzar-bee/tokenscope-mcp@0.2.3
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 96 packages
| Packages resolved | 96 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
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 →
analyze_claude_cost ~206
Analyze a Claude Code session's token cost and context attribution. Reads Claude Code session JSONL (read-only, local) and returns the total cost, the spend breakdown (model output vs re-sent cached context vs cache-write vs fresh input), the per-turn context-growth peak/avg, cache efficiency, cost by model, subagent spend, tool-call counts, and plain-language insights. With no path it analyzes your most recent Claude Code session under ~/.claude/projects.
| Name | Type | Req | Description |
|---|---|---|---|
| all | boolean | – | Aggregate ALL sessions under ~/.claude/projects (ignored if `path` is set). Default false. |
| path | string | – | Optional path to a session .jsonl file or a directory of them. Omit to use your latest Claude Code session. |
| pricing | object | – | Optional per-model price overrides, e.g. {"claude-opus-4": {"in": 15, "out": 75}} (USD per 1M tokens). |
No output schema declared.
No examples provided.
get_cost_benchmark ~224
Compare a Claude Code session against tokenscope's shipped reference set of real sessions (n=66) and report percentiles: how big the session's cost is vs the set, its re-sent-context share, and how cache-efficient it is ('more cache-efficient than ~P% of measured sessions'). Either pass a `path` to a session, or pass explicit `totalCost`/`resentPct`/`cacheEfficiency` numbers. This is a yardstick reference set, not a population census.
| Name | Type | Req | Description |
|---|---|---|---|
| all | boolean | – | With no path-derived metrics, aggregate ALL sessions. Default false. |
| cacheEfficiency | number | – | Cache efficiency percent (0-100). Used if `path` is omitted. |
| path | string | – | Optional session .jsonl path/dir to derive the metrics from. |
| resentPct | number | – | Percent of spend that was re-sent (cached) context. Used if `path` is omitted. |
| totalCost | number | – | Session total cost (USD). Used if `path` is omitted. |
No output schema declared.
No examples provided.
tokenscope_share_summary ~106
Produce a privacy-safe, shareable summary of a Claude Code session built ONLY from aggregate numbers (no file paths, no prompt/response content) — safe to paste in public. Returns both a structured summary object and a ready-to-paste markdown block. With no path it uses your latest session.
| Name | Type | Req | Description |
|---|---|---|---|
| all | boolean | – | Aggregate ALL sessions. Default false. |
| path | string | – | Optional session .jsonl path/dir. Omit to use your latest session. |
No output schema declared.
No examples provided.
What is the Tokenscope MCP server?
Tokenscope is an MCP server listed in the public MCP registry as io.github.wartzar-bee/tokenscope. Analyze Claude Code session cost & context attribution: output, cached re-reads, cache writes. This page covers its npm package (@wartzar-bee/tokenscope-mcp).
Is the Tokenscope MCP server safe to use?
Tokenscope scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. 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 Tokenscope MCP server expose?
Tokenscope exposes 3 tools: analyze_claude_cost, get_cost_benchmark, tokenscope_share_summary. Their descriptions and schemas cost roughly 536 tokens of context every time the server is loaded.
Is the Tokenscope MCP server still maintained?
Tokenscope 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 Tokenscope MCP server under?
Tokenscope declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.